Image matting is the process of extracting a precise alpha matte that separates foreground and background objects in an image. This technique has been traditionally used in the filmmaking and photography industry for image and video editing purposes, e.g., background replacement, synthetic bokeh and other visual effects. Image matting assumes that an image is a composite of foreground and background images, and hence, the intensity of each pixel is a linear combination of the foreground and the background.
In the case of traditional image segmentation, the image is segmented in a binary manner, in which a pixel either belongs to the foreground or background. This type of segmentation, however, is unable to deal with natural scenes that contain fine details, e.g., hair and fur, which require estimating a transparency value for each pixel of the foreground object.
Alpha mattes, unlike segmentation masks, are usually extremely precise, preserving strand-level hair details and accurate foreground boundaries. While recent deep learning techniques have shown their potential in image matting, many challenges remain, such as generation of accurate ground truth alpha mattes, improving generalization on in-the-wild images and performing inference on mobile devices treating high-resolution images.
With the Pixel 6, we have significantly improved the appearance of selfies taken in Portrait Mode by introducing a new approach to estimate a high-resolution and accurate alpha matte from a selfie image. When synthesizing the depth-of-field effect, the usage of the alpha matte allows us to extract a more accurate silhouette of the photographed subject and have a better foreground-background separation. This allows users with a wide variety of hairstyles to take great-looking Portrait Mode shots using the selfie camera. In this post, we describe the technology we used to achieve this improvement and discuss how we tackled the challenges mentioned above.
Portrait Matting In designing Portrait Matting, we trained a fully convolutional neural network consisting of a sequence of encoder-decoder blocks to progressively estimate a high-quality alpha matte. We concatenate the input RGB image together with a coarse alpha matte (generated using a low-resolution person segmenter) that is passed as an input to the network. The new Portrait Matting model uses a MobileNetV3 backbone and a shallow (i.e., having a low number of layers) decoder to first predict a refined low-resolution alpha matte that operates on a low-resolution image. Then we use a shallow encoder-decoder and a series of residual blocks to process a high-resolution image and the refined alpha matte from the previous step. The shallow encoder-decoder relies more on lower-level features than the previous MobileNetV3 backbone, focusing on high-resolution structural features to predict final transparency values for each pixel. In this way, the model is able to refine an initial foreground alpha matte and accurately extract very fine details like hair strands. The proposed neural network architecture efficiently runs on Pixel 6 using Tensorflow Lite.
Most recent deep learning work for image matting relies on manually annotated per-pixel alpha mattes used to separate the foreground from the background that are generated with image editing tools or green screens. This process is tedious and does not scale for the generation of large datasets. Also, it often produces inaccurate alpha mattes and foreground images that are contaminated (e.g., by reflected light from the background, or “green spill”). Moreover, this does nothing to ensure that the lighting on the subject appears consistent with the lighting in the new background environment.
To address these challenges, Portrait Matting is trained using a high-quality dataset generated using a custom volumetric capture system, Light Stage. Compared with previous datasets, this is more realistic, as relighting allows the illumination of the foreground subject to match the background. Additionally, we supervise the training of the model using pseudo–ground truth alpha mattes from in-the-wild images to improve model generalization, explained below. This ground truth data generation process is one of the key components of this work.
Ground Truth Data Generation To generate accurate ground truth data, Light Stage produces near-photorealistic models of people using a geodesic sphere outfitted with 331 custom color LED lights, an array of high-resolution cameras, and a set of custom high-resolution depth sensors. Together with Light Stage data, we compute accurate alpha mattes using time-multiplexed lights and a previously recorded “clean plate”. This technique is also known as ratio matting.
Then, we extrapolate the recorded alpha mattes to all the camera viewpoints in Light Stage using a deep learning–based matting network that leverages captured clean plates as an input. This approach allows us to extend the alpha mattes computation to unconstrained backgrounds without the need for specialized time-multiplexed lighting or a clean background. This deep learning architecture was solely trained using ground truth mattes generated using the ratio matting approach.
Leveraging the reflectance field for each subject and the alpha matte generated with our ground truth matte generation system, we can relight each portrait using a given HDR lighting environment. We composite these relit subjects into backgrounds corresponding to the target illumination following the alpha blending equation. The background images are then generated from the HDR panoramas by positioning a virtual camera at the center and ray-tracing into the panorama from the camera’s center of projection. We ensure that the projected view into the panorama matches its orientation as used for relighting. We use virtual cameras with different focal lengths to simulate the different fields-of-view of consumer cameras. This pipeline produces realistic composites by handling matting, relighting, and compositing in one system, which we then use to train the Portrait Matting model.
Training Supervision Using In-the-Wild Portraits To bridge the gap between portraits generated using Light Stage and in-the-wild portraits, we created a pipeline to automatically annotate in-the-wild photos generating pseudo–ground truth alpha mattes. For this purpose, we leveraged the Deep Matting model proposed in Total Relighting to create an ensemble of models that computes multiple high-resolution alpha mattes from in-the-wild images. We ran this pipeline on an extensive dataset of portrait photos captured in-house using Pixel phones. Additionally, during this process we performed test-time augmentation by doing inference on input images at different scales and rotations, and finally aggregating per-pixel alpha values across all estimated alpha mattes.
Generated alpha mattes are visually evaluated with respect to the input RGB image. The alpha mattes that are perceptually correct, i.e., following the subject's silhouette and fine details (e.g., hair), are added to the training set. During training, both datasets are sampled using different weights. Using the proposed supervision strategy exposes the model to a larger variety of scenes and human poses, improving its predictions on photos in the wild (model generalization).
Portrait Mode Selfies The Portrait Mode effect is particularly sensitive to errors around the subject boundary (see image below). For example, errors caused by the usage of a coarse alpha matte keep sharp focus on background regions near the subject boundaries or hair area. The usage of a high-quality alpha matte allows us to extract a more accurate silhouette of the photographed subject and improve foreground-background separation.
Try It Out Yourself We have made front-facing camera Portrait Mode on the Pixel 6 better by improving alpha matte quality, resulting in fewer errors in the final rendered image and by improving the look of the blurred background around the hair region and subject boundary. Additionally, our ML model uses diverse training datasets that cover a wide variety of skin tones and hair styles. You can try this improved version of Portrait Mode by taking a selfie shot with the new Pixel 6 phones.
Acknowledgments This work wouldn’t have been possible without Sergio Orts Escolano, Jana Ehmann, Sean Fanello, Christoph Rhemann, Junlan Yang, Andy Hsu, Hossam Isack, Rohit Pandey, David Aguilar, Yi Jinn, Christian Hane, Jay Busch, Cynthia Herrera, Matt Whalen, Philip Davidson, Jonathan Taylor, Peter Lincoln, Geoff Harvey, Nisha Masharani, Alexander Schiffhauer, Chloe LeGendre, Paul Debevec, Sofien Bouaziz, Adarsh Kowdle, Thabo Beeler, Chia-Kai Liang and Shahram Izadi. Special thanks to our photographers James Adamson, Christopher Farro and Cort Muller who took numerous test photographs for us.
Birds are all around us, and just by listening, we can learn many things about our environment. Ecologists use birds to understand food systems and forest health — for example, if there are more woodpeckers in a forest, that means there’s a lot of dead wood. Because birds communicate and mark territory with songs and calls, it’s most efficient to identify them by ear. In fact, experts may identify up to 10x as many birds by ear as by sight.
In recent years, autonomous recording units (ARUs) have made it easy to capture thousands of hours of audio in forests that could be used to better understand ecosystems and identify critical habitat. However, manually reviewing the audio data is very time consuming, and experts in birdsong are rare. But an approach based on machine learning (ML) has the potential to greatly reduce the amount of expert review needed for understanding a habitat.
However, ML-based audio classification of bird species can be challenging for several reasons. For one, birds often sing over one another, especially during the “dawn chorus” when many birds are most active. Also, there aren’t clear recordings of individual birds to learn from — almost all of the available training data is recorded in noisy outdoor conditions, where other sounds from the wind, insects, and other environmental sources are often present. As a result, existing birdsong classification models struggle to identify quiet, distant and overlapping vocalizations. Additionally, some of the most common species often appear unlabeled in the background of training recordings for less common species, leading models to discount the common species. These difficult cases are very important for ecologists who want to identify endangered or invasive species using automated systems.
To address the general challenge of training ML models to automatically separate audio recordings without access to examples of isolated sounds, we recently proposed a new unsupervised method called mixture invariant training (MixIT) in our paper, “Unsupervised Sound Separation Using Mixture Invariant Training”. Moreover, in our new paper, “Improving Bird Classification with Unsupervised Sound Separation,” we use MixIT training to separate birdsong and improve species classification. We found that including the separated audio in the classification improves precision and classification quality on three independent soundscape datasets. We are also happy to announce the open-source release of the birdsong separation models on GitHub.
Birdsong Audio Separation MixIT learns to separate single-channel recordings into multiple individual tracks, and can be trained entirely with noisy, real-world recordings. To train the separation model, we create a “mixture of mixtures” (MoM) by mixing together two real-world recordings. The separation model then learns to take the MoM apart into many channels to minimize a loss function that uses the two original real-world recordings as ground-truth references. The loss function uses these references to group the separated channels such that they can be mixed back together to recreate the two original real-world recordings. Since there’s no way to know how the different sounds in the MoM were grouped together in the original recordings, the separation model has no choice but to separate the individual sounds themselves, and thus learns to place each singing bird in a different output audio channel, also separate from wind and other background noise.
We trained a new MixIT separation model using birdsong recordings from Xeno-Canto and the Macaulay Library. We found that for separating birdsong, this new model outperformed a MixIT separation model trained on a large amount of general audio from the AudioSet dataset. We measure the quality of the separation by mixing two recordings together, applying separation, and then remixing the separated audio channels such that they reconstruct the original two recordings. We measure the signal-to-noise ratio (SNR) of the remixed audio relative to the original recordings. We found that the model trained specifically for birds achieved 6.1 decibels (dB) better SNR than the model trained on AudioSet (10.5 dB vs 4.4 dB). Subjectively, we also found many examples where the system worked incredibly well, separating very difficult to distinguish calls in real-world data.
The following videos demonstrate separation of birdsong from two different regions (Caples and the High Sierras). The videos show the mel-spectrogram of the mixed audio (a 2D image that shows the frequency content of the audio over time) and highlight the audio separated into different tracks.
Classifying Bird Species To classify birds in real-world audio captured with ARUs, we first split the audio into five-second segments and then create a mel-spectrogram of each segment. We then train an EfficientNet classifier to identify bird species from the mel-spectrogram images, training on audio from Xeno-Canto and the Macaulay Library. We trained two separate classifiers, one for species in the Sierra Nevada mountains and one for upstate New York. Note that these classifiers are not trained on separated audio; that’s an area for future improvement.
We also introduced some new techniques to improve classifier training. Taxonomic training asks the classifier to provide labels for each level of the species taxonomy (genus, family, and order), which allows the model to learn groupings of species before learning the sometimes-subtle differences between similar species. Taxonomic training also allows the model to benefit from expert information about the taxonomic relationships between different species. We also found that random low-pass filtering was helpful for simulating distant sounds during training: As an audio source gets further away, the high-frequency parts fade away before the low-frequency parts. This was particularly effective for identifying species from the High Sierras region, where birdsongs cover very long distances, unimpeded by trees.
Classifying Separated Audio We found that separating audio with the new MixIT model before classification improved the classifier performance on three independent real-world datasets. The separation was particularly successful for identification of quiet and background birds, and in many cases helped with overlapping vocalizations as well.
The separation model does have some potential limitations. Occasionally we observe over-separation, where a single song is broken into multiple channels, which can cause misclassifications. We also notice that when multiple birds are vocalizing, the most prominent song often gets a lower score after separation. This may be due to loss of environmental context or other artifacts introduced by separation that do not appear during classifier training. For now, we get the best results by running the classifier on the separated channels and the original audio, and taking the maximum score for each species. We expect that further work will allow us to reduce over-separation and find better ways to combine separation and classification. You can see and hear more examples of the full system at our GitHub repo.
Future Directions We are currently working with partners at the California Academy of Sciences to understand how habitat and species mix changes after prescribed fires and wildfires, applying these models to ARU audio collected over many years.
We also foresee many potential applications for the unsupervised separation models in ecology, beyond just birds. For example, the separated audio can be used to create better acoustic indices, which could measure ecosystem health by tracking the total activity of birds, insects, and amphibians without identifying particular species. Similar methods could also be adapted for use underwater to track coral reef health.
Acknowledgements We would like to thank Mary Clapp, Jack Dumbacher, and Durrell Kapan from the California Academy of Sciences for providing extensive annotated soundscapes from the Sierra Nevadas. Stefan Kahl and Holger Klinck from the Cornell Lab of Ornithology provided soundscapes from Sapsucker Woods. Training data for both the separation and classification models came from Xeno-Canto and the Macaulay Library. Finally, we would like to thank Julie Cattiau, Lauren Harrell, Matt Harvey, and our co-author, John Hershey, from the Google Bioacoustics and Sound Separation teams.
Language models are becoming more capable than ever before and are helpful in a variety of tasks — translating one language into another, summarizing a long document into a brief highlight, or answering information-seeking questions. Among these, open-domain dialog, where a model needs to be able to converse about any topic, is probably one of the most difficult, with a wide range of potential applications and open challenges. In addition to producing responses that humans judge as sensible, interesting, and specific to the context, dialog models should adhere to Responsible AI practices, and avoid making factual statements that are not supported by external information sources.
Today we’re excited to share recent advances in our “LaMDA: Language Models for Dialog Applications” project. In this post, we’ll give an overview on how we’re making progress towards safe, grounded, and high-quality dialog applications. LaMDA is built by fine-tuning a family of Transformer-based neural language models specialized for dialog, with up to 137B model parameters, and teaching the models to leverage external knowledge sources.
Objectives & Metrics Defining objectives and metrics is critical to guide training dialog models. LaMDA has three key objectives — Quality, Safety, and Groundedness — each of which we measure using carefully designed metrics:
Quality: We decompose Quality into three dimensions, Sensibleness, Specificity, and Interestingness (SSI), which are evaluated by human raters. Sensibleness refers to whether the model produces responses that make sense in the dialog context (e.g., no common sense mistakes, no absurd responses, and no contradictions with earlier responses). Specificity is measured by judging whether the system's response is specific to the preceding dialog context, and not a generic response that could apply to most contexts (e.g., “ok” or “I don’t know”). Finally, Interestingness measures whether the model produces responses that are also insightful, unexpected or witty, and are therefore more likely to create better dialog.
Safety: We’re also making progress towards addressing important questions related to the development and deployment of Responsible AI. Our Safety metric is composed of an illustrative set of safety objectives that captures the behavior that the model should exhibit in a dialog. These objectives attempt to constrain the model’s output to avoid any unintended results that create risks of harm for the user, and to avoid reinforcing unfair bias. For example, these objectives train the model to avoid producing outputs that contain violent or gory content, promote slurs or hateful stereotypes towards groups of people, or contain profanity. Our research towards developing a practical Safety metric represents very early work, and there is still a great deal of progress for us to make in this area.
Groundedness: The current generation of language models often generate statements that seem plausible, but actually contradict facts established in known external sources. This motivates our study of groundedness in LaMDA. Groundedness is defined as the percentage of responses with claims about the external world that can be supported by authoritative external sources, as a share of all responses containing claims about the external world. A related metric, Informativeness, is defined as the percentage of responses with information about the external world that can be supported by known sources, as a share of all responses. Therefore, casual responses that do not carry any real world information (e.g., “That’s a great idea”), affect Informativeness but not Groundedness. While grounding LaMDA generated responses in known sources does not in itself guarantee factual accuracy, it allows users or external systems to judge the validity of a response based on the reliability of its source.
LaMDA Pre-Training With the objectives and metrics defined, we describe LaMDA’s two-stage training: pre-training and fine-tuning. In the pre-training stage, we first created a dataset of 1.56T words — nearly 40 times more words than what were used to train previous dialog models — from public dialog data and other public web documents. After tokenizing the dataset into 2.81T SentencePiece tokens, we pre-train the model using GSPMD to predict every next token in a sentence, given the previous tokens. The pre-trained LaMDA model has also been widely used for natural language processing research across Google, including program synthesis, zero-shot learning, style transfer, as well as in the BIG-bench workshop.
LaMDA Fine-Tuning In the fine-tuning stage, we train LaMDA to perform a mix of generative tasks to generate natural-language responses to given contexts, and classification tasks on whether a response is safe and high-quality, resulting in a single multi-task model that can do both. The LaMDA generator is trained to predict the next token on a dialog dataset restricted to back-and-forth dialog between two authors, while the LaMDA classifiers are trained to predict the Safety and Quality (SSI) ratings for the response in context using annotated data. During a dialog, the LaMDA generator first generates several candidate responses given the current multi-turn dialog context, and the LaMDA classifiers predict the SSI and Safety scores for every response candidate. Candidate responses with low Safety scores are first filtered out. Remaining candidates are re-ranked by their SSI scores, and the top result is selected as the response. We further filter the training data used for the generation task with LaMDA classifiers to increase the density of high-quality response candidates.
Factual Grounding While people are capable of checking their facts by using tools and referencing established knowledge bases, many language models draw their knowledge on their internal model parameters only. To improve the groundedness of LaMDA’s original response, we collect a dataset of dialogs between people and LaMDA, which are annotated with information retrieval queries and the retrieved results where applicable. We then fine-tune LaMDA’s generator and classifier on this dataset to learn to call an external information retrieval system during its interaction with the user to improve the groundedness of its responses. While this is very early work, we’re seeing promising results.
Evaluation In order to quantify progress against our key metrics, we collect responses from the pre-trained model, fine-tuned model, and human raters (i.e., human-generated responses) to multi-turn two-author dialogs, and then ask a different set of human raters a series of questions to evaluate these responses against the Quality, Safety, and Groundedness metrics.
We observe that LaMDA significantly outperforms the pre-trained model in every dimension and across all model sizes. Quality metrics (Sensibleness, Specificity, and Interestingness, in the first column below) generally improve with the number of model parameters, with or without fine-tuning. Safety does not seem to benefit from model scaling alone, but it does improve with fine-tuning. Groundedness improves as model size increases, perhaps because larger models have a greater capacity to memorize uncommon knowledge, but fine-tuning allows the model to access external knowledge sources and effectively shift some of the load of remembering knowledge to an external knowledge source. With fine-tuning, the quality gap to human levels can be narrowed, though the model’s performance remains below human levels in safety and groundedness.
Future Research & Challenges LaMDA’s level of Sensibleness, Specificity and Interestingness unlocks new avenues for understanding the benefits and risks of open-ended dialog agents. It also presents encouraging evidence that key challenges with neural language models, such as using a safety metric and improving groundedness, can improve with larger models and fine-tuning with more well-labeled data. However, this is very early work, and there are significant limitations. Exploring new ways to improve our Safety metric and LaMDA's groundedness, aligned with our AI Principles, will continue to be our main areas of focus going forward.
Acknowledgements We'd to like to thank everyone for contributing to the project and paper, including: Blaise Aguera-Arcas, Javier Alberca, Thushan Amarasiriwardena, Lora Aroyo, Martin Baeuml, Leslie Baker, Rachel Bernstein, Taylor Bos, Maarten Bosma, Jonas Bragagnolo, Alena Butryna, Bill Byrne, Chung-Ching Chang, Zhifeng Chen, Dehao Chen, Heng-Tze Cheng, Ed Chi, Aaron Cohen, Eli Collins, Marian Croak, Claire Cui, Andrew Dai, Dipanjan Das, Daniel De Freitas, Jeff Dean, Rajat Dewan, Mark Diaz, Tulsee Doshi, Yu Du, Toju Duke, Doug Eck, Joe Fenton, Noah Fiedel, Christian Frueh, Harish Ganapathy, Saravanan Ganesh, Amin Ghafouri, Zoubin Ghahramani, Kourosh Gharachorloo, Jamie Hall, Erin Hoffman-John, Sissie Hsiao, Yanping Huang, Ben Hutchinson, Daphne Ippolito, Alicia Jin, Thomas Jurdi, Ashwin Kakarla, Nand Kishore, Maxim Krikun, Karthik Krishnamoorthi, Igor Krivokon, Apoorv Kulshreshtha, Ray Kurzweil, Viktoriya Kuzmina, Vivek Kwatra, Matthew Lamm, Quoc Le, Max Lee, Katherine Lee, Hongrae Lee, Josh Lee, Dmitry Lepikhin, YaGuang Li, Yifeng Lu, David Luan, Daphne Luong, Laichee Man, Jianchang (JC) Mao, Yossi Matias, Kathleen Meier-Hellstern, Marcelo Menegali, Muqthar Mohammad,, Muqthar Mohammad, Alejandra Molina, Erica Moreira, Meredith Ringel Morris, Maysam Moussalem, Jiaqi Mu, Tyler Mullen, Tyler Mullen, Eric Ni, Kristen Olson, Alexander Passos, Fernando Pereira, Slav Petrov, Marc Pickett, Roberto Pieraccini, Christian Plagemann, Sahitya Potluri, Vinodkumar Prabhakaran, Andy Pratt, James Qin, Ravi Rajakumar, Adam Roberts, Will Rusch, Renelito Delos Santos, Noam Shazeer, RJ Skerry-Ryan, Grigori Somin, Johnny Soraker, Pranesh Srinivasan, Amarnag Subramanya, Mustafa Suleyman, Romal Thoppilan, Song Wang, Sheng Wang, Chris Wassman, Yuanzhong Xu, Yuanzhong Xu, Ni Yan, Ben Zevenbergen, Vincent Zhao, Huaixiu Steven Zheng, Denny Zhou, Hao Zhou, Yanqi Zhou, and more.
Neural networks can perform certain tasks remarkably well, but understanding how they reach their decisions — e.g., identifying which signals in an image cause a model to determine it to be of one class and not another — is often a mystery. Explaining a neural model’s decision process may have high social impact in certain areas, such as analysis of medical images and autonomous driving, where human oversight is critical. These insights can also be helpful in guiding health care providers, revealing model biases, providing support for downstream decision makers, and even aiding scientific discovery.
Previous approaches for visual explanations of classifiers, such as attention maps (e.g., Grad-CAM), highlight which regions in an image affect the classification, but they do not explain what attributes within those regions determine the classification outcome: For example, is it their color? Their shape? Another family of methods provides an explanation by smoothly transforming the image between one class and another (e.g., GANalyze). However, these methods tend to change all attributes at once, thus making it difficult to isolate the individual affecting attributes.
In “Explaining in Style: Training a GAN to explain a classifier in StyleSpace”, presented at ICCV 2021, we propose a new approach for a visual explanation of classifiers. Our approach, StylEx, automatically discovers and visualizes disentangled attributes that affect a classifier. It allows exploring the effect of individual attributes by manipulating those attributes separately (changing one attribute does not affect others). StylEx is applicable to a wide range of domains, including animals, leaves, faces, and retinal images. Our results show that StylEx finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are interpretable by people as measured in user studies.
For instance, to understand a cat vs. dog classifier on a given image, StylEx can automatically detect disentangled attributes and visualize how manipulating each attribute can affect the classifier probability. The user can then view these attributes and make semantic interpretations for what they represent. For example, in the figure above, one can draw conclusions such as “dogs are more likely to have their mouth open than cats” (attribute #4 in the GIF above), “cats’ pupils are more slit-like” (attribute #5), “cats’ ears do not tend to be folded” (attribute #1), and so on.
The video below provides a short explanation of the method:
How StylEx Works: Training StyleGAN to Explain a Classifier Given a classifier and an input image, we want to find and visualize the individual attributes that affect its classification. For that, we utilize the StyleGAN2 architecture, which is known to generate high quality images. Our method consists of two phases:
Phase 1: Training StylEx
A recent work showed that StyleGAN2 contains a disentangled latent space called “StyleSpace”, which contains individual semantically meaningful attributes of the images in the training dataset. However, because StyleGAN training is not dependent on the classifier, it may not represent those attributes that are important for the decision of the specific classifier we want to explain. Therefore, we train a StyleGAN-like generator to satisfy the classifier, thus encouraging its StyleSpace to accommodate classifier-specific attributes. This is achieved by training the StyleGAN generator with two additional components. The first is an encoder, trained together with the GAN with a reconstruction-loss, which forces the generated output image to be visually similar to the input. This allows us to apply the generator on any given input image. However, visual similarity of the image is not enough, as it may not necessarily capture subtle visual details important for a particular classifier (such as medical pathologies). To ensure this, we add a classification-loss to the StyleGAN training, which forces the classifier probability of the generated image to be the same as the classifier probability of the input image. This guarantees that subtle visual details important for the classifier (such as medical pathologies) will be included in the generated image.
A recent work showed that StyleGAN2 contains a disentangled latent space called “StyleSpace”, which contains individual semantically meaningful attributes of the images in the training dataset. However, because StyleGAN training is not dependent on the classifier, it may not represent those attributes that are important for the decision of the specific classifier we want to explain. Therefore, we train a StyleGAN-like generator to satisfy the classifier, thus encouraging its StyleSpace to accommodate classifier-specific attributes.
This is achieved by training the StyleGAN generator with two additional components. The first is an encoder, trained together with the GAN with a reconstruction-loss, which forces the generated output image to be visually similar to the input. This allows us to apply the generator on any given input image. However, visual similarity of the image is not enough, as it may not necessarily capture subtle visual details important for a particular classifier (such as medical pathologies). To ensure this, we add a classification-loss to the StyleGAN training, which forces the classifier probability of the generated image to be the same as the classifier probability of the input image. This guarantees that subtle visual details important for the classifier (such as medical pathologies) will be included in the generated image.
Phase 2: Extracting Disentangled Attributes
Once trained, we search the StyleSpace of the trained Generator for attributes that significantly affect the classifier. To do so, we manipulate each StyleSpace coordinate and measure its effect on the classification probability. We seek the top attributes that maximize the change in classification probability for the given image. This provides the top-K image-specific attributes. By repeating this process for a large number of images per class, we can further discover the top-K class-specific attributes, which teaches us what the classifier has learned about the specific class. We call our end-to-end system “StylEx”. A visual illustration of image-specific attribute extraction: once trained, we search for the StyleSpace coordinates that have the highest effect on the classification probability of a given image.
Once trained, we search the StyleSpace of the trained Generator for attributes that significantly affect the classifier. To do so, we manipulate each StyleSpace coordinate and measure its effect on the classification probability. We seek the top attributes that maximize the change in classification probability for the given image. This provides the top-K image-specific attributes. By repeating this process for a large number of images per class, we can further discover the top-K class-specific attributes, which teaches us what the classifier has learned about the specific class. We call our end-to-end system “StylEx”.
StylEx is Applicable to a Wide Range of Domains and Classifiers Our method works on a wide variety of domains and classifiers (binary and multi-class). Below are some examples of class-specific explanations. In all the domains tested, the top attributes detected by our method correspond to coherent semantic notions when interpreted by humans, as verified by human evaluation.
For perceived gender and age classifiers, below are the top four detected attributes per classifier. Our method exemplifies each attribute on multiple images that are automatically selected to best demonstrate that attribute. For each attribute we flicker between the source and attribute-manipulated image. The degree to which manipulating the attribute affects the classifier probability is shown at the top-left corner of each image.
Note that our method explains a classifier, not reality. That is, the method is designed to reveal image attributes that a given classifier has learned to utilize from data; those attributes may not necessarily characterize actual physical differences between class labels (e.g., a younger or older age) in reality. In particular, these detected attributes may reveal biases in the classifier training or dataset, which is another key benefit of our method. It can further be used to improve fairness of neural networks, for example, by augmenting the training dataset with examples that compensate for the biases our method reveals.
Adding the classifier loss into StyleGAN training turns out to be crucial in domains where the classification depends on fine details. For example, a GAN trained on retinal images without a classifier loss will not necessarily generate fine pathological details corresponding to a particular disease. Adding the classification loss causes the GAN to generate these subtle pathologies as an explanation of the classifier. This is exemplified below for a retinal image classifier (DME disease) and a sick/healthy leaf classifier. StylEx is able to discover attributes that are aligned with disease indicators, for instance “hard exudates”, which is a well known marker for retinal DME, and rot for leaf diseases.
Finally, this method is also applicable to multi-class problems, as demonstrated on a 200-way bird species classifier.
Broader Impact and Next Steps Overall, we have introduced a new technique that enables the generation of meaningful explanations for a given classifier on a given image or class. We believe that our technique is a promising step towards detection and mitigation of previously unknown biases in classifiers and/or datasets, in line with Google’s AI Principles. Additionally, our focus on multiple-attribute based explanation is key to providing new insights about previously opaque classification processes and aiding in the process of scientific discovery. Finally, our GitHub repository includes a Colab and model weights for the GANs used in our paper.
Acknowledgements The research described in this post was done by Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald (as an intern), Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola, Amir Globerson, Michal Irani and Inbar Mosseri. We would like to thank Jenny Huang and Marilyn Zhang for leading the writing process for this blogpost, and Reena Jana, Paul Nicholas, and Johnny Soraker for ethics reviews of our research paper and this post.
Scaling large language models has resulted in significant quality improvements in natural language understanding (T5), generation (GPT-3) and multilingual neural machine translation (M4). One common approach to building a larger model is to increase the depth (number of layers) and width (layer dimensionality), simply enlarging existing dimensions of the network. Such dense models take an input sequence (divided into smaller components, called tokens) and pass every token through the full network, activating every layer and parameter. While these large, dense models have achieved state-of-the-art results on multiple natural language processing (NLP) tasks, their training cost increases linearly with model size.
An alternative, and increasingly popular, approach is to build sparsely activated models based on a mixture of experts (MoE) (e.g., GShard-M4 or GLaM), where each token passed to the network follows a separate subnetwork by skipping some of the model parameters. The choice of how to distribute the input tokens to each subnetwork (the “experts”) is determined by small router networks that are trained together with the rest of the network. This allows researchers to increase model size (and hence, performance) without a proportional increase in training cost.
While this is an effective strategy at training time, sending tokens of a long sequence to multiple experts, again makes inference computationally expensive because the experts have to be distributed among a large number of accelerators. For example, serving the 1.2T parameter GLaM model requires 256 TPU-v3 chips. Much like dense models, the number of processors needed to serve an MoE model still scales linearly with respect to the model size, increasing compute requirements while also resulting in significant communication overhead and added engineering complexity.
In “Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference”, we introduce a method called Task-level Mixture-of-Experts (TaskMoE), that takes advantage of the quality gains of model scaling while still being efficient to serve. Our solution is to train a large multi-task model from which we then extract smaller, stand-alone per-task subnetworks suitable for inference with no loss in model quality and with significantly reduced inference latency. We demonstrate the effectiveness of this method for multilingual neural machine translation (NMT) compared to other mixture of experts models and to models compressed using knowledge distillation.
Training Large Sparsely Activated Models with Task Information We train a sparsely activated model, where router networks learn to send tokens of each task-specific input to different subnetworks of the model associated with the task of interest. For example, in the case of multilingual NMT, every token of a given language is routed to the same subnetwork. This differs from other recent approaches, such as the sparsely gated mixture of expert models (e.g., TokenMoE), where router networks learn to send different tokens in an input to different subnetworks independent of task.
Inference: Bypassing Distillation by Extracting Subnetworks A consequence of this difference in training between TaskMoE and models like TokenMoE is in how we approach inference. Because TokenMoE follows the practice of distributing tokens of the same task to many experts at both training and inference time, it is still computationally expensive at inference.
For TaskMoE, we dedicate a smaller subnetwork to a single task identity during training and inference. At inference time, we extract subnetworks by discarding unused experts for each task. TaskMoE and its variants enable us to train a single large multi-task network and then use a separate subnetwork at inference time for each task without using any additional compression methods post-training. We illustrate the process of training a TaskMoE network and then extracting per-task subnetworks for inference below.
To demonstrate this approach, we train models based on the Transformer architecture. Similar to GShard-M4 and GLaM, we replace the feedforward network of every other transformer layer with a Mixture-of-Experts (MoE) layer that consists of multiple identical feedforward networks, the “experts”. For each task, the routing network, trained along with the rest of the model, keeps track of the task identity for all input tokens and chooses a certain number of experts per layer (two in this case) to form the task-specific subnetwork. The baseline dense Transformer model has 143M parameters and 6 layers on both the encoder and decoder. The TaskMoE and TokenMoE that we train are also both 6 layers deep but with 32 experts for every MoE layer and have a total of 533M parameters. We train our models using publicly available WMT datasets, with over 431M sentences across 30 language pairs from different language families and scripts. We point the reader to the full paper for further details.
A popular approach to building a smaller network that still performs well is through knowledge distillation, in which a large teacher model trains a smaller student model with the goal of matching the teacher’s performance. However, this method comes at the cost of additional computation needed to train the student from the teacher. So, we also compare TaskMoE to a baseline TokenMoE model that we compress using knowledge distillation. The compressed TokenMoE model has a size comparable to the per-task subnetwork extracted from TaskMoE.
We find that in addition to being a simpler method that does not need any additional training, TaskMoE improves upon a distilled TokenMoE model by 2.1 BLEU on average across all languages in our multilingual translation model. We note that distillation retains 43% of the performance gains achieved from scaling a dense multilingual model to a TokenMoE, whereas extracting the smaller subnetwork from the TaskMoE model results in no loss of quality.
Next Steps The quality improvements often seen with scaling machine learning models has incentivized the research community to work toward advancing scaling technology to enable efficient training of large models. The emerging need to train models capable of generalizing to multiple tasks and modalities only increases the need for scaling models even further. However, the practicality of serving these large models remains a major challenge. Efficiently deploying large models is an important direction of research, and we believe TaskMoE is a promising step towards more inference friendly algorithms that retain the quality gains of scaling.
Acknowledgements We would like to first thank our coauthors - Yanping Huang, Ankur Bapna, Maxim Krikun, Dmitry Lepikhin and Minh-Thang Luong. We would also like to thank Wolfgang Macherey, Yuanzhong Xu, Zhifeng Chen and Macduff Richard Hughes for their helpful feedback. Special thanks to the Translate and Brain teams for their useful input and discussions, and the entire GShard development team for their foundational contributions to this project. We would also like to thank Tom Small for creating the animations for the blog post.
Advances in deep learning over the last few decades have been driven by a few key elements. With a small number of simple but flexible mechanisms (i.e., inductive biases such as convolutions or sequence attention), increasingly large datasets, and more specialized hardware, neural networks can now achieve impressive results on a wide range of tasks, such as image classification, machine translation, and protein folding prediction.
However, the use of large models and datasets comes at the expense of significant computational requirements. Yet, recent works suggest that large model sizes might be necessary for strong generalization and robustness, so training large models while limiting resource requirements is becoming increasingly important. One promising approach involves the use of conditional computation: rather than activating the whole network for every single input, different parts of the model are activated for different inputs. This paradigm has been featured in the Pathways vision and recent works on large language models, while it has not been well explored in the context of computer vision.
In “Scaling Vision with Sparse Mixture of Experts”, we present V-MoE, a new vision architecture based on a sparse mixture of experts, which we then use to train the largest vision model to date. We transfer V-MoE to ImageNet and demonstrate matching state-of-the-art accuracy while using about 50% fewer resources than models of comparable performance. We have also open-sourced the code to train sparse models and provided several pre-trained models.
Vision Mixture of Experts (V-MoEs) Vision Transformers (ViT) have emerged as one of the best architectures for vision tasks. ViT first partitions an image into equally-sized square patches. These are called tokens, a term inherited from language models. Still, compared to the largest language models, ViT models are several orders of magnitude smaller in terms of number of parameters and compute.
To massively scale vision models, we replace some dense feedforward layers (FFN) in the ViT architecture with a sparse mixture of independent FFNs (which we call experts). A learnable router layer selects which experts are chosen (and how they are weighted) for every individual token. That is, different tokens from the same image may be routed to different experts. Each token is only routed to at most K (typically 1 or 2) experts, among a total of E experts (in our experiments, E is typically 32). This allows scaling the model’s size while keeping its computation per token roughly constant. The figure below shows the structure of the encoder blocks in more detail.
Experimental Results We first pre-train the model once on JFT-300M, a large dataset of images. The left plot below shows our pre-training results for models of all sizes: from the small S/32 to the huge H/14.
We then transfer the model to new downstream tasks (such as ImageNet), by using a new head (the last layer in a model). We explore two transfer setups: either fine-tuning the entire model on all available examples of the new task, or freezing the pre-trained network and tuning only the new head using a few examples (known as few-shot transfer). The right plot in the figure below summarizes our transfer results to ImageNet, training on only 5 images per class (called 5-shot transfer).
In both cases, the sparse model strongly outperforms its dense counterpart at a given amount of training compute (shown by the V-MoE line being above the ViT line), or achieves similar performance much faster (shown by the V-MoE line being to the left of the ViT line).
To explore the limits of vision models, we trained a 15-billion parameter model with 24 MoE layers (out of 48 blocks) on an extended version of JFT-300M. This massive model — the largest to date in vision as far as we know — achieved 90.35% test accuracy on ImageNet after fine-tuning, near the current state-of-the-art.
Priority Routing In practice, due to hardware constraints, it is not efficient to use buffers with a dynamic size, so models typically use a pre-defined buffer capacity for each expert. Assigned tokens beyond this capacity are dropped and not processed once the expert becomes "full". As a consequence, higher capacities yield higher accuracy, but they are also more computationally expensive.
We leverage this implementation constraint to make V-MoEs faster at inference time. By decreasing the total combined buffer capacity below the number of tokens to be processed, the network is forced to skip processing some tokens in the expert layers. Instead of choosing the tokens to skip in some arbitrary fashion (as previous works did), the model learns to sort tokens according to an importance score. This maintains high quality predictions while saving a lot of compute. We refer to this approach as Batch Priority Routing (BPR), illustrated below.
Dropping the right tokens turns out to be essential to deliver high-quality and more efficient inference predictions. When the expert capacity decreases, performance quickly decreases with the vanilla routing mechanism. Conversely, BPR is much more robust to low capacities.
Overall, we observed that V-MoEs are highly flexible at inference time: for instance, one can decrease the number of selected experts per token to save time and compute, without any further training on the model weights.
Exploring V-MoEs Because much is yet to be discovered about the internal workings of sparse networks, we also explored the routing patterns of the V-MoE.
One hypothesis is that routers would learn to discriminate and assign tokens to experts based on some semantic grounds (the “car” expert, the “animal” experts, and so on). To test this, below we show plots for two different MoE layers (a very early-on one, and another closer to the head). The x-axis corresponds to each of the 32 experts, and the y-axis shows the ID of the image classes (from 1 to 1000). Each entry in the plot shows how often an expert was selected for tokens corresponding to the specific image class, with darker colors indicating higher frequency. While in the early layers there is little correlation, later in the network, each expert receives and processes tokens from only a handful of classes. Therefore, we can conclude that some semantic clustering of the patches emerges in the deeper layers of the network.
Final Thoughts We train very large vision models using conditional computation, delivering significant improvements in representation and transfer learning for relatively little training cost. Alongside V-MoE, we introduced BPR, which requires the model to process only the most useful tokens in the expert layers.
We believe this is just the beginning of conditional computation at scale for computer vision; extensions include multi-modal and multi-task models, scaling up the expert count, and improving transfer of the representations produced by sparse models. Heterogeneous expert architectures and conditional variable-length routes are also promising directions. Sparse models can especially help in data rich domains such as large-scale video modeling. We hope our open-source code and models help attract and engage researchers new to this field.
Acknowledgments We thank our co-authors: Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, André Susano Pinto, Daniel Keysers, and Neil Houlsby. We thank Alex Kolesnikov, Lucas Beyer, and Xiaohua Zhai for providing continuous help and details about scaling ViT models. We are also grateful to Josip Djolonga, Ilya Tolstikhin, Liam Fedus, and Barret Zoph for feedback on the paper; James Bradbury, Roy Frostig, Blake Hechtman, Dmitry Lepikhin, Anselm Levskaya, and Parker Schuh for invaluable support helping us run our JAX models efficiently on TPUs; and many others from the Brain team for their support. Finally, we would also like to thank and acknowledge Tom Small for the awesome animated figure used in this post.
Over the last several decades, I've witnessed a lot of change in the fields of machine learning (ML) and computer science. Early approaches, which often fell short, eventually gave rise to modern approaches that have been very successful. Following that long-arc pattern of progress, I think we'll see a number of exciting advances over the next several years, advances that will ultimately benefit the lives of billions of people with greater impact than ever before. In this post, I’ll highlight five areas where ML is poised to have such impact. For each, I’ll discuss related research (mostly from 2021) and the directions and progress we’ll likely see in the next few years.
Trend 1: More Capable, General-Purpose ML Models Researchers are training larger, more capable machine learning models than ever before. For example, just in the last couple of years models in the language domain have grown from billions of parameters trained on tens of billions of tokens of data (e.g., the 11B parameter T5 model), to hundreds of billions or trillions of parameters trained on trillions of tokens of data (e.g., dense models such as OpenAI’s 175B parameter GPT-3 model and DeepMind’s 280B parameter Gopher model, and sparse models such as Google’s 600B parameter GShard model and 1.2T parameter GLaM model). These increases in dataset and model size have led to significant increases in accuracy for a wide variety of language tasks, as shown by across-the-board improvements on standard natural language processing (NLP) benchmark tasks (as predicted by work on neural scaling laws for language models and machine translation models).
Many of these advanced models are focused on the single but important modality of written language and have shown state-of-the-art results in language understanding benchmarks and open-ended conversational abilities, even across multiple tasks in a domain. They have also shown exciting capabilities to generalize to new language tasks with relatively little training data, in some cases, with few to no training examples for a new task. A couple of examples include improved long-form question answering, zero-label learning in NLP, and our LaMDA model, which demonstrates a sophisticated ability to carry on open-ended conversations that maintain significant context across multiple turns of dialog.
Transformer models are also having a major impact in image, video, and speech models, all of which also benefit significantly from scale, as predicted by work on scaling laws for visual transformer models. Transformers for image recognition and for video classification are achieving state-of-the-art results on many benchmarks, and we’ve also demonstrated that co-training models on both image data and video data can improve performance on video tasks compared with video data alone. We’ve developed sparse, axial attention mechanisms for image and video transformers that use computation more efficiently, found better ways of tokenizing images for visual transformer models, and improved our understanding of visual transformer methods by examining how they operate compared with convolutional neural networks. Combining transformer models with convolutional operations has shown significant benefits in visual as well as speech recognition tasks.
The outputs of generative models are also substantially improving. This is most apparent in generative models for images, which have made significant strides over the last few years. For example, recent models have demonstrated the ability to create realistic images given just a category (e.g., "irish setter" or "streetcar", if you desire), can "fill in" a low-resolution image to create a natural-looking high-resolution counterpart ("computer, enhance!"), and can even create natural-looking aerial nature scenes of arbitrary length. As another example, images can be converted to a sequence of discrete tokens that can then be synthesized at high fidelity with an autoregressive generative model.
Because these are powerful capabilities that come with great responsibility, we carefully vet potential applications of these sorts of models against our AI Principles.
Beyond advanced single-modality models, we are also starting to see large-scale multi-modal models. These are some of the most advanced models to date because they can accept multiple different input modalities (e.g., language, images, speech, video) and, in some cases, produce different output modalities, for example, generating images from descriptive sentences or paragraphs, or describing the visual content of images in human languages. This is an exciting direction because like the real world, some things are easier to learn in data that is multimodal (e.g., reading about something and seeing a demonstration is more useful than just reading about it). As such, pairing images and text can help with multi-lingual retrieval tasks, and better understanding of how to pair text and image inputs can yield improved results for image captioning tasks. Similarly, jointly training on visual and textual data can also help improve accuracy and robustness on visual classification tasks, while co-training on image, video, and audio tasks improves generalization performance for all modalities. There are also tantalizing hints that natural language can be used as an input for image manipulation, telling robots how to interact with the world and controlling other software systems, portending potential changes to how user interfaces are developed. Modalities handled by these models will include speech, sounds, images, video, and languages, and may even extend to structured data, knowledge graphs, and time series data.
Often these models are trained using self-supervised learning approaches, where the model learns from observations of “raw” data that has not been curated or labeled, e.g., language models used in GPT-3 and GLaM, the self-supervised speech model BigSSL, the visual contrastive learning model SimCLR, and the multimodal contrastive model VATT. Self-supervised learning allows a large speech recognition model to match the previous Voice Search automatic speech recognition (ASR) benchmark accuracy while using only 3% of the annotated training data. These trends are exciting because they can substantially reduce the effort required to enable ML for a particular task, and because they make it easier (though by no means trivial) to train models on more representative data that better reflects different subpopulations, regions, languages, or other important dimensions of representation.
All of these trends are pointing in the direction of training highly capable general-purpose models that can handle multiple modalities of data and solve thousands or millions of tasks. By building in sparsity, so that the only parts of a model that are activated for a given task are those that have been optimized for it, these multimodal models can be made highly efficient. Over the next few years, we are pursuing this vision in a next-generation architecture and umbrella effort called Pathways. We expect to see substantial progress in this area, as we combine together many ideas that to date have been pursued relatively independently.
Top
Trend 2: Continued Efficiency Improvements for ML Improvements in efficiency — arising from advances in computer hardware design as well as ML algorithms and meta-learning research — are driving greater capabilities in ML models. Many aspects of the ML pipeline, from the hardware on which a model is trained and executed to individual components of the ML architecture, can be optimized for efficiency while maintaining or improving on state-of-the-art performance overall. Each of these different threads can improve efficiency by a significant multiplicative factor, and taken together, can reduce computational costs, including CO2 equivalent emissions (CO2e), by orders of magnitude compared to just a few years ago. This greater efficiency has enabled a number of critical advances that will continue to dramatically improve the efficiency of machine learning, enabling larger, higher quality ML models to be developed cost effectively and further democratizing access. I’m very excited about these directions of research!
Continued Improvements in ML Accelerator Performance
Each generation of ML accelerator improves on previous generations, enabling faster performance per chip, and often increasing the scale of the overall systems. Last year, we announced our TPUv4 systems, the fourth generation of Google’s Tensor Processing Unit, which demonstrated a 2.7x improvement over comparable TPUv3 results in the MLPerf benchmarks. Each TPUv4 chip has ~2x the peak performance per chip versus the TPUv3 chip, and the scale of each TPUv4 pod is 4096 chips (4x that of TPUv3 pods), yielding a performance of approximately 1.1 exaflops per pod (versus ~100 petaflops per TPUv3 pod). Having pods with larger numbers of chips that are connected together with high speed networks improves efficiency for larger models. ML capabilities on mobile devices are also increasing significantly. The Pixel 6 phone features a brand new Google Tensor processor that integrates a powerful ML accelerator to better support important on-device features. Left: TPUv4 board; Center: Part of a TPUv4 pod; Right: Google Tensor chip found in Pixel 6 phones. Our use of ML to accelerate the design of computer chips of all kinds (more on this below) is also paying dividends, particularly to produce better ML accelerators.
Each generation of ML accelerator improves on previous generations, enabling faster performance per chip, and often increasing the scale of the overall systems. Last year, we announced our TPUv4 systems, the fourth generation of Google’s Tensor Processing Unit, which demonstrated a 2.7x improvement over comparable TPUv3 results in the MLPerf benchmarks. Each TPUv4 chip has ~2x the peak performance per chip versus the TPUv3 chip, and the scale of each TPUv4 pod is 4096 chips (4x that of TPUv3 pods), yielding a performance of approximately 1.1 exaflops per pod (versus ~100 petaflops per TPUv3 pod). Having pods with larger numbers of chips that are connected together with high speed networks improves efficiency for larger models.
ML capabilities on mobile devices are also increasing significantly. The Pixel 6 phone features a brand new Google Tensor processor that integrates a powerful ML accelerator to better support important on-device features.
Our use of ML to accelerate the design of computer chips of all kinds (more on this below) is also paying dividends, particularly to produce better ML accelerators.
Continued Improvements in ML Compilation and Optimization of ML Workloads
Even when the hardware is unchanged, improvements in compilers and other optimizations in system software for machine learning accelerators can lead to significant improvements in efficiency. For example, “A Flexible Approach to Autotuning Multi-pass Machine Learning Compilers” shows how to use machine learning to perform auto-tuning of compilation settings to get across-the-board performance improvements of 5-15% (and sometimes as much as 2.4x improvement) for a suite of ML programs on the same underlying hardware. GSPMD describes an automatic parallelization system based on the XLA compiler that is capable of scaling most deep learning network architectures beyond the memory capacity of an accelerator and has been applied to many large models, such as GShard-M4, LaMDA, BigSSL, ViT, MetNet-2, and GLaM, leading to state-of-the-art results across several domains.End-to-end model speedups from using ML-based compiler autotuning on 150 ML models. Included are models that achieve improvements of 5% or more. Bar colors represent relative improvement from optimizing different model components.
Even when the hardware is unchanged, improvements in compilers and other optimizations in system software for machine learning accelerators can lead to significant improvements in efficiency. For example, “A Flexible Approach to Autotuning Multi-pass Machine Learning Compilers” shows how to use machine learning to perform auto-tuning of compilation settings to get across-the-board performance improvements of 5-15% (and sometimes as much as 2.4x improvement) for a suite of ML programs on the same underlying hardware. GSPMD describes an automatic parallelization system based on the XLA compiler that is capable of scaling most deep learning network architectures beyond the memory capacity of an accelerator and has been applied to many large models, such as GShard-M4, LaMDA, BigSSL, ViT, MetNet-2, and GLaM, leading to state-of-the-art results across several domains.
Human-Creativity–Driven Discovery of More Efficient Model Architectures
Continued improvements in model architectures give substantial reductions in the amount of computation needed to achieve a given level of accuracy for many problems. For example, the Transformer architecture, which we developed in 2017, was able to improve the state of the art on several NLP and translation benchmarks while simultaneously using 10x to 100x less computation to achieve these results than a variety of other prevalent methods, such as LSTMs and other recurrent architectures. Similarly, the Vision Transformer was able to show improved state-of-the-art results on a number of different image classification tasks despite using 4x to 10x less computation than convolutional neural networks.
Machine-Driven Discovery of More Efficient Model Architectures
Neural architecture search (NAS) can automatically discover new ML architectures that are more efficient for a given problem domain. A primary advantage of NAS is that it can greatly reduce the effort needed for algorithm development, because NAS requires only a one-time effort per search space and problem domain combination. In addition, while the initial effort to perform NAS can be computationally expensive, the resulting models can greatly reduce computation in downstream research and production settings, resulting in greatly reduced resource requirements overall. For example, the one-time search to discover the Evolved Transformer generated only 3.2 tons of CO2e (much less than the 284t CO2e reported elsewhere; see Appendix C and D in this joint Google/UC Berkeley preprint), but yielded a model for use by anyone in the NLP community that is 15-20% more efficient than the plain Transformer model. A more recent use of NAS discovered an even more efficient architecture called Primer (that has also been open-sourced), which reduces training costs by 4x compared to a plain Transformer model. In this way, the discovery costs of NAS searches are often recouped from the use of the more-efficient model architectures that are discovered, even if they are applied to only a handful of downstream uses (and many NAS results are reused thousands of times). The Primer architecture discovered by NAS is 4x as efficient compared with a plain Transformer model. This image shows (in red) the two main modifications that give Primer most of its gains: depthwise convolution added to attention multi-head projections and squared ReLU activations (blue indicates portions of the original Transformer). NAS has also been used to discover more efficient models in the vision domain. The EfficientNetV2 model architecture is the result of a neural architecture search that jointly optimizes for model accuracy, model size, and training speed. On the ImageNet benchmark, EfficientNetV2 improves training speed by 5–11x while substantially reducing model size over previous state-of-the-art models. The CoAtNet model architecture was created with an architecture search that uses ideas from the Vision Transformer and convolutional networks to create a hybrid model architecture that trains 4x faster than the Vision Transformer and achieves a new ImageNet state of the art. EfficientNetV2 achieves much better training efficiency than prior models for ImageNet classification. The broad use of search to help improve ML model architectures and algorithms, including the use of reinforcement learning and evolutionary techniques, has inspired other researchers to apply this approach to different domains. To aid others in creating their own model searches, we have open-sourced Model Search, a platform that enables others to explore model search for their domains of interest. In addition to model architectures, automated search can also be used to find new, more efficient reinforcement learning algorithms, building on the earlier AutoML-Zero work that demonstrated this approach for automating supervised learning algorithm discovery.
Neural architecture search (NAS) can automatically discover new ML architectures that are more efficient for a given problem domain. A primary advantage of NAS is that it can greatly reduce the effort needed for algorithm development, because NAS requires only a one-time effort per search space and problem domain combination. In addition, while the initial effort to perform NAS can be computationally expensive, the resulting models can greatly reduce computation in downstream research and production settings, resulting in greatly reduced resource requirements overall. For example, the one-time search to discover the Evolved Transformer generated only 3.2 tons of CO2e (much less than the 284t CO2e reported elsewhere; see Appendix C and D in this joint Google/UC Berkeley preprint), but yielded a model for use by anyone in the NLP community that is 15-20% more efficient than the plain Transformer model. A more recent use of NAS discovered an even more efficient architecture called Primer (that has also been open-sourced), which reduces training costs by 4x compared to a plain Transformer model. In this way, the discovery costs of NAS searches are often recouped from the use of the more-efficient model architectures that are discovered, even if they are applied to only a handful of downstream uses (and many NAS results are reused thousands of times).
NAS has also been used to discover more efficient models in the vision domain. The EfficientNetV2 model architecture is the result of a neural architecture search that jointly optimizes for model accuracy, model size, and training speed. On the ImageNet benchmark, EfficientNetV2 improves training speed by 5–11x while substantially reducing model size over previous state-of-the-art models. The CoAtNet model architecture was created with an architecture search that uses ideas from the Vision Transformer and convolutional networks to create a hybrid model architecture that trains 4x faster than the Vision Transformer and achieves a new ImageNet state of the art.
The broad use of search to help improve ML model architectures and algorithms, including the use of reinforcement learning and evolutionary techniques, has inspired other researchers to apply this approach to different domains. To aid others in creating their own model searches, we have open-sourced Model Search, a platform that enables others to explore model search for their domains of interest. In addition to model architectures, automated search can also be used to find new, more efficient reinforcement learning algorithms, building on the earlier AutoML-Zero work that demonstrated this approach for automating supervised learning algorithm discovery.
Use of Sparsity
Sparsity, where a model has a very large capacity, but only some parts of the model are activated for a given task, example or token, is another important algorithmic advance that can greatly improve efficiency. In 2017, we introduced the sparsely-gated mixture-of-experts layer, which demonstrated better results on a variety of translation benchmarks while using 10x less computation than previous state-of-the-art dense LSTM models. More recently, Switch Transformers, which pair a mixture-of-experts–style architecture with the Transformer model architecture, demonstrated a 7x speedup in training time and efficiency over the dense T5-Base Transformer model. The GLaM model showed that transformers and mixture-of-expert–style layers can be combined to produce a model that exceeds the accuracy of the GPT-3 model on average across 29 benchmarks using 3x less energy for training and 2x less computation for inference. The notion of sparsity can also be applied to reduce the cost of the attention mechanism in the core Transformer architecture. The BigBird sparse attention model consists of global tokens that attend to all parts of an input sequence, local tokens, and a set of random tokens. Theoretically, this can be interpreted as adding a few global tokens on a Watts-Strogatz graph. The use of sparsity in models is clearly an approach with very high potential payoff in terms of computational efficiency, and we are only scratching the surface in terms of research ideas to be tried in this direction. Each of these approaches for improved efficiency can be combined together so that equivalent-accuracy language models trained today in efficient data centers are ~100 times more energy efficient and produce ~650 times less CO2e emissions, compared to a baseline Transformer model trained using P100 GPUs in an average U.S. datacenter using an average U.S. energy mix. And this doesn’t even account for Google’s carbon-neutral, 100% renewable energy offsets. We’ll have a more detailed blog post analyzing the carbon emissions trends of NLP models soon.
Sparsity, where a model has a very large capacity, but only some parts of the model are activated for a given task, example or token, is another important algorithmic advance that can greatly improve efficiency. In 2017, we introduced the sparsely-gated mixture-of-experts layer, which demonstrated better results on a variety of translation benchmarks while using 10x less computation than previous state-of-the-art dense LSTM models. More recently, Switch Transformers, which pair a mixture-of-experts–style architecture with the Transformer model architecture, demonstrated a 7x speedup in training time and efficiency over the dense T5-Base Transformer model. The GLaM model showed that transformers and mixture-of-expert–style layers can be combined to produce a model that exceeds the accuracy of the GPT-3 model on average across 29 benchmarks using 3x less energy for training and 2x less computation for inference. The notion of sparsity can also be applied to reduce the cost of the attention mechanism in the core Transformer architecture.
The use of sparsity in models is clearly an approach with very high potential payoff in terms of computational efficiency, and we are only scratching the surface in terms of research ideas to be tried in this direction.
Each of these approaches for improved efficiency can be combined together so that equivalent-accuracy language models trained today in efficient data centers are ~100 times more energy efficient and produce ~650 times less CO2e emissions, compared to a baseline Transformer model trained using P100 GPUs in an average U.S. datacenter using an average U.S. energy mix. And this doesn’t even account for Google’s carbon-neutral, 100% renewable energy offsets. We’ll have a more detailed blog post analyzing the carbon emissions trends of NLP models soon.
Trend 3: ML Is Becoming More Personally and Communally Beneficial A host of new experiences are made possible as innovation in ML and silicon hardware (like the Google Tensor processor on the Pixel 6) enable mobile devices to be more capable of continuously and efficiently sensing their surrounding context and environment. These advances have improved accessibility and ease of use, while also boosting computational power, which is critical for popular features like mobile photography, live translation and more. Remarkably, recent technological advances also provide users with a more customized experience while strengthening privacy safeguards.
More people than ever rely on their phone cameras to record their daily lives and for artistic expression. The clever application of ML to computational photography has continued to advance the capabilities of phone cameras, making them easier to use, improving performance, and resulting in higher-quality images. Advances, such as improved HDR+, the ability to take pictures in very low light, better handling of portraits, and efforts to make cameras more inclusive so they work for all skin tones, yield better photos that are more true to the photographer’s vision and to their subjects. Such photos can be further improved using the powerful ML-based tools now available in Google Photos, like cinematic photos, noise and blur reduction, and the Magic Eraser.
In addition to using their phones for creative expression, many people rely on them to help communicate with others across languages and modalities in real-time using Live Translate in messaging apps and Live Caption for phone calls. Speech recognition accuracy has continued to make substantial improvements thanks to techniques like self-supervised learning and noisy student training, with marked improvements for accented speech, noisy conditions or environments with overlapping speech, and across many languages. Building on advances in text-to-speech synthesis, people can listen to web pages and articles using our Read Aloud technology on a growing number of platforms, making information more available across barriers of modality and languages. Live speech translations in the Google Translate app have become significantly better by stabilizing the translations that are generated on-the-fly, and high quality, robust and responsible direct speech-to-speech translation provides a much better user experience in communicating with people speaking a different language. New work on combining ML with traditional codec approaches in the Lyra speech codec and the more general SoundStream audio codec enables higher fidelity speech, music, and other sounds to be communicated reliably at much lower bitrate.
Everyday interactions are becoming much more natural with features like automatic call screening and ML agents that will wait on hold for you, thanks to advances in Duplex. Even short tasks that users may perform frequently have been improved with tools such as Smart Text Selection, which automatically selects entities like phone numbers or addresses for easy copy and pasting, and grammar correction as you type on Pixel 6 phones. In addition, Screen Attention prevents the phone screen from dimming when you are looking at it and improvements in gaze recognition are opening up new use cases for accessibility and for improved wellness and health. ML is also enabling new methods for ensuring the safety of people and communities. For example, Suspicious Message Alerts warn against possible phishing attacks and Safer Routing detects hard-braking events to suggest alternate routes.
Given the potentially sensitive nature of the data that underlies these new capabilities, it is essential that they are designed to be private by default. Many of them run inside of Android's Private Compute Core — an open source, secure environment isolated from the rest of the operating system. Android ensures that data processed in the Private Compute Core is not shared to any apps without the user taking an action. Android also prevents any feature inside the Private Compute Core from having direct access to the network. Instead, features communicate over a small set of open-source APIs to Private Compute Services, which strips out identifying information and makes use of privacy technologies, including federated learning, federated analytics, and private information retrieval, enabling learning while simultaneously ensuring privacy.
These technologies are critical to evolving next-generation computation and interaction paradigms, whereby personal or communal devices can both learn from and contribute to training a collective model of the world without compromising privacy. A federated unsupervised approach to privately learn the kinds of aforementioned general-purpose models with fine-tuning for a given task or context could unlock increasingly intelligent systems that are far more intuitive to interact with — more like a social entity than a machine. Broad and equitable access to these intelligent interfaces will only be possible with deep changes to our technology stacks, from the edge to the datacenter, so that they properly support neural computing.
Trend 4: Growing Impact of ML in Science, Health and Sustainability In recent years, we have seen an increasing impact of ML in the basic sciences, from physics to biology, with a number of exciting practical applications in related realms, such as renewable energy and medicine. Computer vision models have been deployed to address problems at both personal and global scales. They can assist physicians in their regular work, expand our understanding of neural physiology, and also provide better weather forecasts and streamline disaster relief efforts. Other types of ML models are proving critical in addressing climate change by discovering ways to reduce emissions and improving the output of alternative energy sources. Such models can even be leveraged as creative tools for artists! As ML becomes more robust, well-developed, and widely accessible, its potential for high-impact applications in a broad array of real-world domains continues to expand, helping to solve some of our most challenging problems.
Large-Scale Application of Computer Vision for New Insights
The advances in computer vision over the past decade have enabled computers to be used for a wide variety of tasks across different scientific domains. In neuroscience, automated reconstruction techniques can recover the neural connective structure of brain tissues from high resolution electron microscopy images of thin slices of brain tissue. In previous years, we have collaborated to create such resources for fruit fly, mouse, and songbird brains, but last year, we collaborated with the Lichtman Lab at Harvard University to analyze the largest sample of brain tissue imaged and reconstructed in this level of detail, in any species, and produced the first large-scale study of synaptic connectivity in the human cortex that spans multiple cell types across all layers of the cortex. The goal of this work is to produce a novel resource to assist neuroscientists in studying the stunning complexity of the human brain. The image below, for example, shows six neurons out of about 86 billion neurons in an adult human brain. A single human chandelier neuron from our human cortex reconstruction, along with some of the pyramidal neurons that make a connection with that cell. Here’s an interactive version and a gallery of other interactive examples. Computer vision technology also provides powerful tools to address challenges at much larger, even global, scales. A deep-learning–based approach to weather forecasting that uses satellite and radar imagery as inputs, combined with other atmospheric data, produces weather and precipitation forecasts that are more accurate than traditional physics-based models at forecasting times up to 12 hours. They can also produce updated forecasts much more quickly than traditional methods, which can be critical in times of extreme weather. Comparison of 0.2 mm/hr precipitation on March 30, 2020 over Denver, Colorado. Left: Ground truth, source MRMS. Center: Probability map as predicted by MetNet-2. Right: Probability map as predicted by the physics-based HREF model. MetNet-2 is able to predict the onset of the storm earlier in the forecast than HREF as well as the storm’s starting location, whereas HREF misses the initiation location, but captures its growth phase well. Having an accurate record of building footprints is essential for a range of applications, from population estimation and urban planning to humanitarian response and environmental science. In many parts of the world, including much of Africa, this information wasn’t previously available, but new work shows that using computer vision techniques applied to satellite imagery can help identify building boundaries at continental scales. The results of this approach have been released in the Open Buildings dataset, a new open-access data resource that contains the locations and footprints of 516 million buildings with coverage across most of the African continent. We’ve also been able to use this unique dataset in our collaboration with the World Food Programme to provide fast damage assessment after natural disasters through application of ML. Example of segmenting buildings in satellite imagery. Left: Source image; Center: Semantic segmentation, with each pixel assigned a confidence score that it is a building vs. non-building; Right: Instance segmentation, obtained by thresholding and grouping together connected components. A common theme across each of these cases is that ML models are able to perform specialized tasks efficiently and accurately based on analysis of available visual data, supporting high impact downstream tasks.
The advances in computer vision over the past decade have enabled computers to be used for a wide variety of tasks across different scientific domains. In neuroscience, automated reconstruction techniques can recover the neural connective structure of brain tissues from high resolution electron microscopy images of thin slices of brain tissue. In previous years, we have collaborated to create such resources for fruit fly, mouse, and songbird brains, but last year, we collaborated with the Lichtman Lab at Harvard University to analyze the largest sample of brain tissue imaged and reconstructed in this level of detail, in any species, and produced the first large-scale study of synaptic connectivity in the human cortex that spans multiple cell types across all layers of the cortex. The goal of this work is to produce a novel resource to assist neuroscientists in studying the stunning complexity of the human brain. The image below, for example, shows six neurons out of about 86 billion neurons in an adult human brain.
Computer vision technology also provides powerful tools to address challenges at much larger, even global, scales. A deep-learning–based approach to weather forecasting that uses satellite and radar imagery as inputs, combined with other atmospheric data, produces weather and precipitation forecasts that are more accurate than traditional physics-based models at forecasting times up to 12 hours. They can also produce updated forecasts much more quickly than traditional methods, which can be critical in times of extreme weather.
Having an accurate record of building footprints is essential for a range of applications, from population estimation and urban planning to humanitarian response and environmental science. In many parts of the world, including much of Africa, this information wasn’t previously available, but new work shows that using computer vision techniques applied to satellite imagery can help identify building boundaries at continental scales. The results of this approach have been released in the Open Buildings dataset, a new open-access data resource that contains the locations and footprints of 516 million buildings with coverage across most of the African continent. We’ve also been able to use this unique dataset in our collaboration with the World Food Programme to provide fast damage assessment after natural disasters through application of ML.
A common theme across each of these cases is that ML models are able to perform specialized tasks efficiently and accurately based on analysis of available visual data, supporting high impact downstream tasks.
Automated Design Space Exploration
Another approach that has yielded excellent results across many fields is to allow an ML algorithm to explore and evaluate a problem’s design space for possible solutions in an automated way. In one application, a Transformer-based variational autoencoder learns to create aesthetically-pleasing and useful document layouts, and the same approach can be extended to explore possible furniture layouts. Another ML-driven approach automates the exploration of the huge design space of tweaks for computer game rules to improve playability and other attributes of a game, enabling human game designers to create enjoyable games more quickly. A visualization of the Variational Transformer Network (VTN) model, which is able to extract meaningful relationships between the layout elements (paragraphs, tables, images, etc.) in order to generate realistic synthetic documents (e.g., with better alignment and margins). Other ML algorithms have been used to evaluate the design space of computer architectural decisions for ML accelerator chips themselves. We’ve also shown that ML can be used to quickly create chip placements for ASIC designs that are better than layouts generated by human experts and can be generated in a matter of hours instead of weeks. This reduces the fixed engineering costs of chips and lowers the barrier to quickly creating specialized hardware for different applications. We’ve successfully used this automated placement approach in the design of our upcoming TPU-v5 chip. Such exploratory ML approaches have also been applied to materials discovery. In a collaboration between Google Research and Caltech, several ML models, combined with a modified inkjet printer and a custom-built microscope, were able to rapidly search over hundreds of thousands of possible materials to hone in on 51 previously uncharacterized three-metal oxide materials with promising properties for applications in areas like battery technology and electrolysis of water. These automated design space exploration approaches can help accelerate many scientific fields, especially when the entire experimental loop of generating the experiment and evaluating the result can all be done in an automated or mostly-automated manner. I expect to see this approach applied to good effect in many more areas in the coming years.
Another approach that has yielded excellent results across many fields is to allow an ML algorithm to explore and evaluate a problem’s design space for possible solutions in an automated way. In one application, a Transformer-based variational autoencoder learns to create aesthetically-pleasing and useful document layouts, and the same approach can be extended to explore possible furniture layouts. Another ML-driven approach automates the exploration of the huge design space of tweaks for computer game rules to improve playability and other attributes of a game, enabling human game designers to create enjoyable games more quickly.
Other ML algorithms have been used to evaluate the design space of computer architectural decisions for ML accelerator chips themselves. We’ve also shown that ML can be used to quickly create chip placements for ASIC designs that are better than layouts generated by human experts and can be generated in a matter of hours instead of weeks. This reduces the fixed engineering costs of chips and lowers the barrier to quickly creating specialized hardware for different applications. We’ve successfully used this automated placement approach in the design of our upcoming TPU-v5 chip.
Such exploratory ML approaches have also been applied to materials discovery. In a collaboration between Google Research and Caltech, several ML models, combined with a modified inkjet printer and a custom-built microscope, were able to rapidly search over hundreds of thousands of possible materials to hone in on 51 previously uncharacterized three-metal oxide materials with promising properties for applications in areas like battery technology and electrolysis of water.
These automated design space exploration approaches can help accelerate many scientific fields, especially when the entire experimental loop of generating the experiment and evaluating the result can all be done in an automated or mostly-automated manner. I expect to see this approach applied to good effect in many more areas in the coming years.
Application to Health
In addition to advancing basic science, ML can also drive advances in medicine and human health more broadly. The idea of leveraging advances in computer science in health is nothing new — in fact some of my own early experiences were in developing software to help analyze epidemiological data. But ML opens new doors, raises new opportunities, and yes, poses new challenges. Take for example the field of genomics. Computing has been important to genomics since its inception, but ML adds new capabilities and disrupts old paradigms. When Google researchers began working in this area, the idea of using deep learning to help infer genetic variants from sequencer output was considered far-fetched by many experts. Today, this ML approach is considered state-of-the-art. But the future holds an even more important role for ML — genomics companies are developing new sequencing instruments that are more accurate and faster, but also present new inference challenges. Our release of open-source software DeepConsensus and, in collaboration with UCSC, PEPPER-DeepVariant, supports these new instruments with cutting-edge informatics. We hope that more rapid sequencing can lead to near term applicability with impact for real patients. A schematic of the Transformer architecture for DeepConsensus, which corrects sequencing errors to improve yield and correctness. There are other opportunities to use ML to accelerate our use of genomic information for personalized health outside of processing the sequencer data. Large biobanks of extensively phenotyped and sequenced individuals can revolutionize how we understand and manage genetic predisposition to disease. Our ML-based phenotyping method improves the scalability of converting large imaging and text datasets into phenotypes usable for genetic association studies, and our DeepNull method better leverages large phenotypic data for genetic discovery. We are happy to release both as open-source methods for the scientific community. The process for generating large-scale quantification of anatomical and disease traits for combination with genomic data in Biobanks. Just as ML helps us see hidden characteristics of genomics data, it can help us discover new information and glean new insights from other health data types as well. Diagnosis of disease is often about identifying a pattern, quantifying a correlation, or recognizing a new instance of a larger class — all tasks at which ML excels. Google researchers have used ML to tackle a wide range of such problems, but perhaps none of these has progressed farther than the applications of ML to medical imaging. In fact, Google’s 2016 paper describing the application of deep learning to the screening for diabetic retinopathy, was selected by the editors of the Journal of the American Medical Association (JAMA) as one of the top 10 most influential papers of the decade — not just the most influential papers on ML and health, the most influential JAMA papers of the decade overall. But the strength of our research doesn’t end at contributions to the literature, but extends to our ability to build systems operating in the real world. Through our global network of deployment partners, this same program has helped screen tens of thousands of patients in India, Thailand, Germany and France who might otherwise have been untested for this vision-threatening disease. We expect to see this same pattern of assistive ML systems deployed to improve breast cancer screening, detect lung cancer, accelerate radiotherapy treatments for cancer, flag abnormal X-rays, and stage prostate cancer biopsies. Each domain presents new opportunities to be helpful. ML-assisted colonoscopy procedures are a particularly interesting example of going beyond the basics. Colonoscopies are not just used to diagnose colon cancer — the removal of polyps during the procedure are the front line of halting disease progression and preventing serious illness. In this domain we’ve demonstrated that ML can help ensure doctors don’t miss polyps, can help detect elusive polyps, and can add new dimensions of quality assurance, like coverage mapping through the application of simultaneous localization and mapping techniques. In collaboration with Shaare Zedek Medical Center in Jerusalem, we’ve shown these systems can work in real time, detecting an average of one polyp per procedure that would have otherwise been missed, with fewer than four false alarms per procedure. Sample chest X-rays (CXR) of true and false positives, and true and false negatives for (A) general abnormalities, (B) tuberculosis, and (C) COVID-19. On each CXR, red outlines indicate areas on which the model focused to identify abnormalities (i.e., the class activation map), and yellow outlines refer to regions of interest identified by a radiologist. Another ambitious healthcare initiative, Care Studio, uses state-of-the-art ML and advanced NLP techniques to analyze structured data and medical notes, presenting clinicians with the most relevant information at the right time — ultimately helping them deliver more proactive and accurate care. As important as ML may be to expanding access and improving accuracy in the clinical setting, we see a new equally important trend emerging: ML applied to help people in their daily health and well-being. Our everyday devices have powerful sensors that can help democratize health metrics and information so people can make more informed decisions about their health. We’ve already seen launches that enable a smartphone camera to assess heart rate and respiratory rate to help users without additional hardware, and Nest Hub devices that support contactless sleep sensing and allow users to better understand their nighttime wellness. We’ve seen that we can, on the one hand, significantly improve speech recognition quality for disordered speech in our own ASR systems, and on the other, use ML to help recreate the voice of those with speech impairments, empowering them to communicate in their own voice. ML enabled smartphones that help people better research emerging skin conditions or help those with limited vision go for a jog, seem to be just around the corner. These opportunities offer a future too bright to ignore. The custom ML model for contactless sleep sensing efficiently processes a continuous stream of 3D radar tensors (summarizing activity over a range of distances, frequencies, and time) to automatically compute probabilities for the likelihood of user presence and wakefulness (awake or asleep).
In addition to advancing basic science, ML can also drive advances in medicine and human health more broadly. The idea of leveraging advances in computer science in health is nothing new — in fact some of my own early experiences were in developing software to help analyze epidemiological data. But ML opens new doors, raises new opportunities, and yes, poses new challenges.
Take for example the field of genomics. Computing has been important to genomics since its inception, but ML adds new capabilities and disrupts old paradigms. When Google researchers began working in this area, the idea of using deep learning to help infer genetic variants from sequencer output was considered far-fetched by many experts. Today, this ML approach is considered state-of-the-art. But the future holds an even more important role for ML — genomics companies are developing new sequencing instruments that are more accurate and faster, but also present new inference challenges. Our release of open-source software DeepConsensus and, in collaboration with UCSC, PEPPER-DeepVariant, supports these new instruments with cutting-edge informatics. We hope that more rapid sequencing can lead to near term applicability with impact for real patients.
There are other opportunities to use ML to accelerate our use of genomic information for personalized health outside of processing the sequencer data. Large biobanks of extensively phenotyped and sequenced individuals can revolutionize how we understand and manage genetic predisposition to disease. Our ML-based phenotyping method improves the scalability of converting large imaging and text datasets into phenotypes usable for genetic association studies, and our DeepNull method better leverages large phenotypic data for genetic discovery. We are happy to release both as open-source methods for the scientific community.
Just as ML helps us see hidden characteristics of genomics data, it can help us discover new information and glean new insights from other health data types as well. Diagnosis of disease is often about identifying a pattern, quantifying a correlation, or recognizing a new instance of a larger class — all tasks at which ML excels. Google researchers have used ML to tackle a wide range of such problems, but perhaps none of these has progressed farther than the applications of ML to medical imaging.
In fact, Google’s 2016 paper describing the application of deep learning to the screening for diabetic retinopathy, was selected by the editors of the Journal of the American Medical Association (JAMA) as one of the top 10 most influential papers of the decade — not just the most influential papers on ML and health, the most influential JAMA papers of the decade overall. But the strength of our research doesn’t end at contributions to the literature, but extends to our ability to build systems operating in the real world. Through our global network of deployment partners, this same program has helped screen tens of thousands of patients in India, Thailand, Germany and France who might otherwise have been untested for this vision-threatening disease.
We expect to see this same pattern of assistive ML systems deployed to improve breast cancer screening, detect lung cancer, accelerate radiotherapy treatments for cancer, flag abnormal X-rays, and stage prostate cancer biopsies. Each domain presents new opportunities to be helpful. ML-assisted colonoscopy procedures are a particularly interesting example of going beyond the basics. Colonoscopies are not just used to diagnose colon cancer — the removal of polyps during the procedure are the front line of halting disease progression and preventing serious illness. In this domain we’ve demonstrated that ML can help ensure doctors don’t miss polyps, can help detect elusive polyps, and can add new dimensions of quality assurance, like coverage mapping through the application of simultaneous localization and mapping techniques. In collaboration with Shaare Zedek Medical Center in Jerusalem, we’ve shown these systems can work in real time, detecting an average of one polyp per procedure that would have otherwise been missed, with fewer than four false alarms per procedure.
Another ambitious healthcare initiative, Care Studio, uses state-of-the-art ML and advanced NLP techniques to analyze structured data and medical notes, presenting clinicians with the most relevant information at the right time — ultimately helping them deliver more proactive and accurate care.
As important as ML may be to expanding access and improving accuracy in the clinical setting, we see a new equally important trend emerging: ML applied to help people in their daily health and well-being. Our everyday devices have powerful sensors that can help democratize health metrics and information so people can make more informed decisions about their health. We’ve already seen launches that enable a smartphone camera to assess heart rate and respiratory rate to help users without additional hardware, and Nest Hub devices that support contactless sleep sensing and allow users to better understand their nighttime wellness. We’ve seen that we can, on the one hand, significantly improve speech recognition quality for disordered speech in our own ASR systems, and on the other, use ML to help recreate the voice of those with speech impairments, empowering them to communicate in their own voice. ML enabled smartphones that help people better research emerging skin conditions or help those with limited vision go for a jog, seem to be just around the corner. These opportunities offer a future too bright to ignore.
Another realm of paramount importance is climate change, which is an incredibly urgent threat for humanity. We need to all work together to bend the curve of harmful emissions to ensure a safe and prosperous future. Better information about the climate impact of different choices can help us tackle this challenge in a number of different ways. To this end, we recently rolled out eco-friendly routing in Google Maps, which we estimate will save about 1 million tons of CO2 emissions per year (the equivalent of removing more than 200,000 cars from the road). A recent case study shows that using Google Maps directions in Salt Lake City results in both faster and more emissions-friendly routing, which saves 1.7% of CO2 emissions and 6.5% travel time. In addition, making our Maps products smarter about electric vehicles can help alleviate range anxiety, encouraging people to switch to emissions-free vehicles. We are also working with multiple municipalities around the world to use aggregated historical traffic data to help suggest improved traffic light timing settings, with an early pilot study in Israel and Brazil showing a 10-20% reduction in fuel consumption and delay time at the examined intersections. With eco-friendly routing, Google Maps will show you the fastest route and the one that’s most fuel-efficient — so you can choose whichever one works best for you. On a longer time scale, fusion holds promise as a game-changing renewable energy source. In a long-standing collaboration with TAE Technologies, we have used ML to help maintain stable plasmas in their fusion reactor by suggesting settings of the more than 1000 relevant control parameters. With our collaboration, TAE achieved their major goals for their Norman reactor, which brings us a step closer to the goal of breakeven fusion. The machine maintains a stable plasma at 30 million Kelvin (don’t touch!) for 30 milliseconds, which is the extent of available power to its systems. They have completed a design for an even more powerful machine, which they hope will demonstrate the conditions necessary for breakeven fusion before the end of the decade. We’re also expanding our efforts to address wildfires and floods, which are becoming more common (like millions of Californians, I’m having to adapt to having a regular “fire season”). Last year, we launched a wildfire boundary map powered by satellite data to help people in the U.S. easily understand the approximate size and location of a fire — right from their device. Building on this, we’re now bringing all of Google’s wildfire information together and launching it globally with a new layer on Google Maps. We have been applying graph optimization algorithms to help optimize fire evacuation routes to help keep people safe in the presence of rapidly advancing fires. In 2021, our Flood Forecasting Initiative expanded its operational warning systems to cover 360 million people, and sent more than 115 million notifications directly to the mobile devices of people at risk from flooding, more than triple our outreach in the previous year. We also deployed our LSTM-based forecast models and the new Manifold inundation model in real-world systems for the first time, and shared a detailed description of all components of our systems.The wildfire layer in Google Maps provides people with critical, up-to-date information in an emergency. We’re also working hard on our own set of sustainability initiatives. Google was the first major company to become carbon neutral in 2007. We were also the first major company to match our energy use with 100 percent renewable energy in 2017. We operate the cleanest global cloud in the industry, and we’re the world’s largest corporate purchaser of renewable energy. Further, in 2020 we became the first major company to make a commitment to operate on 24/7 carbon-free energy in all our data centers and campuses worldwide. This is far more challenging than the traditional approach of matching energy usage with renewable energy, but we’re working to get this done by 2030. Carbon emission from ML model training is a concern for the ML community, and we have shown that making good choices about model architecture, datacenter, and ML accelerator type can reduce the carbon footprint of training by ~100-1000x.
Another realm of paramount importance is climate change, which is an incredibly urgent threat for humanity. We need to all work together to bend the curve of harmful emissions to ensure a safe and prosperous future. Better information about the climate impact of different choices can help us tackle this challenge in a number of different ways.
To this end, we recently rolled out eco-friendly routing in Google Maps, which we estimate will save about 1 million tons of CO2 emissions per year (the equivalent of removing more than 200,000 cars from the road). A recent case study shows that using Google Maps directions in Salt Lake City results in both faster and more emissions-friendly routing, which saves 1.7% of CO2 emissions and 6.5% travel time. In addition, making our Maps products smarter about electric vehicles can help alleviate range anxiety, encouraging people to switch to emissions-free vehicles. We are also working with multiple municipalities around the world to use aggregated historical traffic data to help suggest improved traffic light timing settings, with an early pilot study in Israel and Brazil showing a 10-20% reduction in fuel consumption and delay time at the examined intersections.
On a longer time scale, fusion holds promise as a game-changing renewable energy source. In a long-standing collaboration with TAE Technologies, we have used ML to help maintain stable plasmas in their fusion reactor by suggesting settings of the more than 1000 relevant control parameters. With our collaboration, TAE achieved their major goals for their Norman reactor, which brings us a step closer to the goal of breakeven fusion. The machine maintains a stable plasma at 30 million Kelvin (don’t touch!) for 30 milliseconds, which is the extent of available power to its systems. They have completed a design for an even more powerful machine, which they hope will demonstrate the conditions necessary for breakeven fusion before the end of the decade.
We’re also expanding our efforts to address wildfires and floods, which are becoming more common (like millions of Californians, I’m having to adapt to having a regular “fire season”). Last year, we launched a wildfire boundary map powered by satellite data to help people in the U.S. easily understand the approximate size and location of a fire — right from their device. Building on this, we’re now bringing all of Google’s wildfire information together and launching it globally with a new layer on Google Maps. We have been applying graph optimization algorithms to help optimize fire evacuation routes to help keep people safe in the presence of rapidly advancing fires. In 2021, our Flood Forecasting Initiative expanded its operational warning systems to cover 360 million people, and sent more than 115 million notifications directly to the mobile devices of people at risk from flooding, more than triple our outreach in the previous year. We also deployed our LSTM-based forecast models and the new Manifold inundation model in real-world systems for the first time, and shared a detailed description of all components of our systems.
We’re also working hard on our own set of sustainability initiatives. Google was the first major company to become carbon neutral in 2007. We were also the first major company to match our energy use with 100 percent renewable energy in 2017. We operate the cleanest global cloud in the industry, and we’re the world’s largest corporate purchaser of renewable energy. Further, in 2020 we became the first major company to make a commitment to operate on 24/7 carbon-free energy in all our data centers and campuses worldwide. This is far more challenging than the traditional approach of matching energy usage with renewable energy, but we’re working to get this done by 2030. Carbon emission from ML model training is a concern for the ML community, and we have shown that making good choices about model architecture, datacenter, and ML accelerator type can reduce the carbon footprint of training by ~100-1000x.
Trend 5: Deeper and Broader Understanding of ML As ML is used more broadly across technology products and society more generally, it is imperative that we continue to develop new techniques to ensure that it is applied fairly and equitably, and that it benefits all people and not just select subsets. This is a major focus for our Responsible AI and Human-Centered Technology research group and an area in which we conduct research on a variety of responsibility-related topics.
One area of focus is recommendation systems that are based on user activity in online products. Because these recommendation systems are often composed of multiple distinct components, understanding their fairness properties often requires insight into individual components as well as how the individual components behave when combined together. Recent work has helped to better understand these relationships, revealing ways to improve the fairness of both individual components and the overall recommendation system. In addition, when learning from implicit user activity, it is also important for recommendation systems to learn in an unbiased manner, since the straightforward approach of learning from items that were shown to previous users exhibits well-known forms of bias. Without correcting for such biases, for example, items that were shown in more prominent positions to users tend to get recommended to future users more often.
As in recommendation systems, surrounding context is important in machine translation. Because most machine translation systems translate individual sentences in isolation, without additional surrounding context, they can often reinforce biases related to gender, age or other areas. In an effort to address some of these issues, we have a long-standing line of research on reducing gender bias in our translation systems, and to help the entire translation community, last year we released a dataset to study gender bias in translation based on translations of Wikipedia biographies.
Another common problem in deploying machine learning models is distributional shift: if the statistical distribution of data on which the model was trained is not the same as that of the data the model is given as input, the model’s behavior can sometimes be unpredictable. In recent work, we employ the Deep Bootstrap framework to compare the real world, where there is finite training data, to an "ideal world", where there is infinite data. Better understanding of how a model behaves in these two regimes (real vs. ideal) can help us develop models that generalize better to new settings and exhibit less bias towards fixed training datasets.
Although work on ML algorithms and model development gets significant attention, data collection and dataset curation often gets less. But this is an important area, because the data on which an ML model is trained can be a potential source of bias and fairness issues in downstream applications. Analyzing such data cascades in ML can help identify the many places in the lifecycle of an ML project that can have substantial influence on the outcomes. This research on data cascades has led to evidence-backed guidelines for data collection and evaluation in the revised PAIR Guidebook, aimed at ML developers and designers.
The general goal of better understanding data is an important part of ML research. One thing that can help is finding and investigating anomalous data. We have developed methods to better understand the influence that particular training examples can have on an ML model, since mislabeled data or other similar issues can have outsized impact on the overall model behavior. We have also built the Know Your Data tool to help ML researchers and practitioners better understand properties of their datasets, and last year we created a case study of how to use the Know Your Data tool to explore issues like gender bias and age bias in a dataset.
Understanding dynamics of benchmark dataset usage is also important, given the central role they play in the organization of ML as a field. Although studies of individual datasets have become increasingly common, the dynamics of dataset usage across the field have remained underexplored. In recent work, we published the first large scale empirical analysis of dynamics of dataset creation, adoption, and reuse. This work offers insights into pathways to enable more rigorous evaluations, as well as more equitable and socially informed research.
Creating public datasets that are more inclusive and less biased is an important way to help improve the field of ML for everyone. In 2016, we released the Open Images dataset, a collection of ~9 million images annotated with image labels spanning thousands of object categories and bounding box annotations for 600 classes. Last year, we introduced the More Inclusive Annotations for People (MIAP) dataset in the Open Images Extended collection. The collection contains more complete bounding box annotations for the person class hierarchy, and each annotation is labeled with fairness-related attributes, including perceived gender presentation and perceived age range. With the increasing focus on reducing unfair bias as part of responsible AI research, we hope these annotations will encourage researchers already leveraging the Open Images dataset to incorporate fairness analysis in their research.
Because we also know that our teams are not the only ones creating datasets that can improve machine learning, we have built Dataset Search to help users discover new and useful datasets, wherever they might be on the Web.
Tackling various forms of abusive behavior online, such as toxic language, hate speech, and misinformation, is a core priority for Google. Being able to detect such forms of abuse reliably, efficiently, and at scale is of critical importance both to ensure that our platforms are safe and also to avoid the risk of reproducing such negative traits through language technologies that learn from online discourse in an unsupervised fashion. Google has pioneered work in this space through the Perspective API tool, but the nuances involved in detecting toxicity at scale remains a complex problem. In recent work, in collaboration with various academic partners, we introduced a comprehensive taxonomy to reason about the changing landscape of online hate and harassment. We also investigated how to detect covert forms of toxicity, such as microaggressions, that are often ignored in online abuse interventions, studied how conventional approaches to deal with disagreements in data annotations of such subjective concepts might marginalize minority perspectives, and proposed a new disaggregated modeling approach that uses a multi-task framework to tackle this issue. Furthermore, through qualitative research and network-level content analysis, Google’s Jigsaw team, in collaboration with researchers at George Washington University, studied how hate clusters spread disinformation across social media platforms.
Another potential concern is that ML language understanding and generation models can sometimes also produce results that are not properly supported by evidence. To confront this problem in question answering, summarization, and dialog, we developed a new framework for measuring whether results can be attributed to specific sources. We released annotation guidelines and demonstrated that they can be reliably used in evaluating candidate models.
Interactive analysis and debugging of models remains key to responsible use of ML. We have updated our Language Interpretability Tool with new capabilities and techniques to advance this line of work, including support for image and tabular data, a variety of features carried over from our previous work on the What-If Tool, and built-in support for fairness analysis through the technique of Testing with Concept Activation Vectors. Interpretability and explainability of ML systems more generally is also a key part of our Responsible AI vision; in collaboration with DeepMind, we made headway in understanding the acquisition of human chess concepts in the self-trained AlphaZero chess system.
We are also working hard to broaden the perspective of Responsible AI beyond western contexts. Our recent research examines how various assumptions of conventional algorithmic fairness frameworks based on Western institutions and infrastructures may fail in non-Western contexts and offers a pathway for recontextualizing fairness research in India along several directions. We are actively conducting survey research across several continents to better understand perceptions of and preferences regarding AI. Western framing of algorithmic fairness research tends to focus on only a handful of attributes, thus biases concerning non-Western contexts are largely ignored and empirically under-studied. To address this gap, in collaboration with the University of Michigan, we developed a weakly supervised method to robustly detect lexical biases in broader geo-cultural contexts in NLP models that reflect human judgments of offensive and inoffensive language in those geographic contexts.
Furthermore, we have explored applications of ML to contexts valued in the Global South, including developing a proposal for farmer-centered ML research. Through this work, we hope to encourage the field to be thoughtful about how to bring ML-enabled solutions to smallholder farmers in ways that will improve their lives and their communities.
Involving community stakeholders at all stages of the ML pipeline is key to our efforts to develop and deploy ML responsibly and keep us focused on tackling the problems that matter most. In this vein, we held a Health Equity Research Summit among external faculty, non-profit organization leads, government and NGO representatives, and other subject matter experts to discuss how to bring more equity into the entire ML ecosystem, from the way we approach problem-solving to how we assess the impact of our efforts.
Community-based research methods have also informed our approach to designing for digital wellbeing and addressing racial equity issues in ML systems, including improving our understanding of the experience of Black Americans using ASR systems. We are also listening to the public more broadly to learn how sociotechnical ML systems could help during major life events, such as by supporting family caregiving.
As ML models become more capable and have impact in many domains, the protection of the private information used in ML continues to be an important focus for research. Along these lines, some of our recent work addresses privacy in large models, both highlighting that training data can sometimes be extracted from large models and pointing to how privacy can be achieved in large models, e.g., as in differentially private BERT. In addition to the work on federated learning and analytics, mentioned above, we have also been enhancing our toolbox with other principled and practical ML techniques for ensuring differential privacy, for example private clustering, private personalization, private matrix completion, private weighted sampling, private quantiles, private robust learning of halfspaces, and in general, sample-efficient private PAC learning. Moreover, we have been expanding the set of privacy notions that can be tailored to different applications and threat models, including label privacy and user versus item level privacy.
Datasets Recognizing the value of open datasets to the general advancement of ML and related fields of research, we continue to grow our collection of open source datasets and resources and expand our global index of open datasets in Google Dataset Search. This year, we have released a number of datasets and tools across a range of research areas:
Research Community Interaction To realize our goal for a more robust and comprehensive understanding of ML and related technologies, we actively engage with the broader research community. In 2021, we published over 750 papers, nearly 600 of which were presented at leading research conferences. Google Research sponsored over 150 conferences, and Google researchers contributed directly by serving on program committees and organizing workshops, tutorials and numerous other activities aimed at collectively advancing the field. To learn more about our contributions to some of the larger research conferences this year, please see our recent conference blog posts. In addition, we hosted 19 virtual workshops (like the 2021 Quantum Summer Symposium), which allowed us to further engage with the academic community by generating new ideas and directions for the research field and advancing research initiatives.
In 2021, Google Research also directly supported external research with $59M in funding, including $23M through Research programs to faculty and students, and $20M in university partnerships and outreach. This past year, we introduced new funding and collaboration programs that support academics all over the world who are doing high impact research. We funded 86 early career faculty through our Research Scholar Program to support general advancements in science, and funded 34 faculty through our Award for Inclusion Research Program who are doing research in areas like accessibility, algorithmic fairness, higher education and collaboration, and participatory ML. In addition to the research we are funding, we welcomed 85 faculty and post-docs, globally, through our Visiting Researcher program, to come to Google and partner with us on exciting ideas and shared research challenges. We also selected a group of 74 incredibly talented PhD student researchers to receive Google PhD Fellowships and mentorship as they conduct their research.
As part of our ongoing racial equity commitments, making computer science (CS) research more inclusive continues to be a top priority for us. In 2021, we continued expanding our efforts to increase the diversity of Ph.D. graduates in computing. For example, the CS Research Mentorship Program (CSRMP), an initiative by Google Research to support students from historically marginalized groups (HMGs) in computing research pathways, graduated 590 mentees, 83% of whom self-identified as part of an HMG, who were supported by 194 Google mentors — our largest group to date! In October, we welcomed 35 institutions globally leading the way to engage 3,400+ students in computing research as part of the 2021 exploreCSR cohort. Since 2018, this program has provided faculty with funding, community, evaluation and connections to Google researchers in order to introduce students from HMGs to the world of CS research. We are excited to expand this program to more international locations in 2022.
We also continued our efforts to fund and partner with organizations to develop and support new pathways and approaches to broadening participation in computing research at scale. From working with alliances like the Computing Alliance of Hispanic-Serving Institutions (CAHSI) and CMD-IT Diversifying LEAdership in the Professoriate (LEAP) Alliance to partnering with university initiatives like UMBC’s Meyerhoff Scholars, Cornell University’s CSMore, Northeastern University’s Center for Inclusive Computing, and MIT’s MEnTorEd Opportunities in Research (METEOR), we are taking a community-based approach to materially increase the representation of marginalized groups in computing research.
Other Work In writing these retrospectives, I try to focus on new research work that has happened (mostly) in the past year while also looking ahead. In past years’ retrospectives, I’ve tried to be more comprehensive, but this time I thought it could be more interesting to focus on just a few themes. We’ve also done great work in many other research areas that don’t fit neatly into these themes. If you’re interested, I encourage you to check out our research publications by area below or by year (and if you’re interested in quantum computing, our Quantum team recently wrote a retrospective of their work in 2021):
Conclusion Research is often a multi-year journey to real-world impact. Early stage research work that happened a few years ago is now having a dramatic impact on Google’s products and across the world. Investments in ML hardware accelerators like TPUs and in software frameworks like TensorFlow and JAX have borne fruit. ML models are increasingly prevalent in many different products and features at Google because their power and ease of expression streamline experimentation and productionization of ML models in performance-critical environments. Research into model architectures to create Seq2Seq, Inception, EfficientNet, and Transformer or algorithmic research like batch normalization and distillation is driving progress in the fields of language understanding, vision, speech, and others. Basic capabilities like better language and visual understanding and speech recognition can be transformational, and as a result, these sorts of models are widely deployed for a wide variety of problems in many of our products including Search, Assistant, Ads, Cloud, Gmail, Maps, YouTube, Workspace, Android, Pixel, Nest, and Translate.
These are truly exciting times in machine learning and computer science. Continued improvement in computers’ ability to understand and interact with the world around them through language, vision, and sound opens up entire new frontiers of how computers can help people accomplish things in the world. The many examples of progress along the five themes outlined in this post are waypoints in a long-term journey!
Acknowledgements Thanks to Alison Carroll, Alison Lentz, Andrew Carroll, Andrew Tomkins, Avinatan Hassidim, Azalia Mirhoseini, Barak Turovsky, Been Kim, Blaise Aguera y Arcas, Brennan Saeta, Brian Rakowski, Charina Chou, Christian Howard, Claire Cui, Corinna Cortes, Courtney Heldreth, David Patterson, Dipanjan Das, Ed Chi, Eli Collins, Emily Denton, Fernando Pereira, Genevieve Park, Greg Corrado, Ian Tenney, Iz Conroy, James Wexler, Jason Freidenfelds, John Platt, Katherine Chou, Kathy Meier-Hellstern, Kyle Vandenberg, Lauren Wilcox, Lizzie Dorfman, Marian Croak, Martin Abadi, Matthew Flegal, Meredith Morris, Natasha Noy, Negar Saei, Neha Arora, Paul Muret, Paul Natsev, Quoc Le, Ravi Kumar, Rina Panigrahy, Sanjiv Kumar, Sella Nevo, Slav Petrov, Sreenivas Gollapudi, Tom Duerig, Tom Small, Vidhya Navalpakkam, Vincent Vanhoucke, Vinodkumar Prabhakaran, Viren Jain, Yonghui Wu, Yossi Matias, and Zoubin Ghahramani for helpful feedback and contributions to this post, and to the entire Research and Health communities at Google for everyone’s contributions towards this work.
