Category: Offsites

Posted by Aurelien Boffy, Senior Staff Software Engineer, and Roberto Pieraccini, Engineering Director, Google Assistant

When people converse with one another, context and references play a critical role in driving their conversation more efficiently. For instance, if one asks the question “Who wrote Romeo and Juliet?” and, after receiving an answer, asks “Where was he born?”, it is clear that ‘he’ is referring to William Shakespeare without the need to explicitly mention him. Or if someone mentions “python” in a sentence, one can use the context from the conversation to determine whether they are referring to a type of snake or a computer language. If a virtual assistant cannot robustly handle context and references, users would be required to adapt to the limitation of the technology by repeating previously shared contextual information in their follow-up queries to ensure that the assistant understands their requests and can provide relevant answers.

In this post, we present a technology currently deployed on Google Assistant that allows users to speak in a natural manner when referencing context that was defined in previous queries and answers. The technology, based on the latest machine learning (ML) advances, rephrases a user’s follow-up query to explicitly mention the missing contextual information, thus enabling it to be answered as a stand-alone query. While Assistant considers many types of context for interpreting the user input, in this post we are focusing on short-term conversation history.

Context Handling by Rephrasing
One of the approaches taken by Assistant to understand contextual queries is to detect if an input utterance is referring to previous context and then rephrase it internally to explicitly include the missing information. Following on from the previous example in which the user asked who wrote Romeo and Juliet, one may ask follow-up questions like “When?”. Assistant recognizes that this question is referring to both the subject (Romeo and Juliet) and answer from the previous query (William Shakespeare) and can rephrase “When?” to “When did William Shakespeare write Romeo and Juliet?”

While there are other ways to handle context, for instance, by applying rules directly to symbolic representations of the meaning of queries, like intents and arguments, the advantage of the rephrasing approach is that it operates horizontally at the string level across any query answering, parsing, or action fulfillment module.

Conversation on a smart display device, where Assistant understands multiple contextual follow-up queries, allowing the user to have a more natural conversation. The phrases appearing at the bottom of the display are suggestions for follow-up questions that the user can select. However, the user can still ask different questions.

A Wide Variety of Contextual Queries
The natural language processing field, traditionally, has not put much emphasis on a general approach to context, focusing on the understanding of stand-alone queries that are fully specified. Accurately incorporating context is a challenging problem, especially when considering the large variety of contextual query types. The table below contains example conversations that illustrate query variability and some of the many contextual challenges that Assistant’s rephrasing method can resolve (e.g., differentiating between referential and non-referential cases or identifying what context a query is referencing). We demonstrate how Assistant is now able to rephrase follow-up queries, adding contextual information before providing an answer.

System Architecture
At a high level, the rephrasing system generates rephrasing candidates by using different types of candidate generators. Each rephrasing candidate is then scored based on a number of signals, and the one with the highest score is selected.

High level architecture of Google Assistant contextual rephraser.

Candidate Generation
To generate rephrasing candidates we use a hybrid approach that applies different techniques, which we classify into three categories:

1. Generators based on the analysis of the linguistic structure of the queries use grammatical and morphological rules to perform specific operations — for instance, the replacement of pronouns or other types of referential phrases with antecedents from the context.
2. Generators based on query statistics combine key terms from the current query and its context to create candidates that match popular queries from historical data or common query patterns.
3. Generators based on Transformer technologies, such as MUM, learn to generate sequences of words according to a number of training samples. LaserTagger and FELIX are technologies suitable for tasks with high overlap between the input and output texts, are very fast at inference time, and are not vulnerable to hallucination (i.e., generating text that is not related to the input texts). Once presented with a query and its context, they can generate a sequence of text edits to transform the input queries into a rephrasing candidate by indicating which portions of the context should be preserved and which words should be modified.

Candidate Scoring
We extract a number of signals for each rephrasing candidate and use an ML model to select the most promising candidate. Some of the signals depend only on the current query and its context. For example, is the topic of the current query similar to the topic of the previous query? Or, is the current query a good stand-alone query or does it look incomplete? Other signals depend on the candidate itself: How much of the information of the context does the candidate preserve? Is the candidate well-formed from a linguistic point of view? Etc.

Recently, new signals generated by BERT and MUM models have significantly improved the performance of the ranker, fixing about one-third of the recall headroom while minimizing false positives on query sequences that are not contextual (and therefore do not require a rephrasing).

Example conversation on a phone where Assistant understands a sequence of contextual queries.

Conclusion
The solution described here attempts to resolve contextual queries by rephrasing them in order to make them fully answerable in a stand-alone manner, i.e., without having to relate to other information during the fulfillment phase. The benefit of this approach is that it is agnostic to the mechanisms that would fulfill the query, thus making it usable as a horizontal layer to be deployed before any further processing.

Given the variety of contexts naturally used in human languages, we adopted a hybrid approach that combines linguistic rules, large amounts of historic data through logs, and ML models based on state-of-the-art Transformer approaches. By generating a number of rephrasing candidates for each query and its context, and then scoring and ranking them using a variety of signals, Assistant can rephrase and thus correctly interpret most contextual queries. As Assistant can handle most types of linguistic references, we are empowering users to have more natural conversations. To make such multi-turn conversations even less cumbersome, Assistant users can turn on Continued Conversation mode to enable asking follow-up queries without the need to repeat “Hey Google” between each query. We are also using this technology in other virtual assistant settings, for instance, interpreting context from something shown on a screen or playing on a speaker.

Acknowledgements
This post reflects the combined work of Aliaksei Severyn, André Farias, Cheng-Chun Lee, Florian Thöle, Gabriel Carvajal, Gyorgy Gyepesi, Julien Cretin, Liana Marinescu, Martin Bölle, Patrick Siegler, Sebastian Krause, Victor Ähdel, Victoria Fossum, Vincent Zhao. We also thank Amar Subramanya, Dave Orr, Yury Pinsky for helpful discussions and support.

Posted by Sara Ahmadian and Matthew Fahrbach, Research Scientists, Google Research, Large-Scale Optimization Team

Economics, combinatorics, physics, and signal processing conspire to make it difficult to design, build, and operate high-quality, cost-effective wireless networks. The radio transceivers that communicate with our mobile phones, the equipment that supports them (such as power and wired networking), and the physical space they occupy are all expensive, so it’s important to be judicious in choosing sites for new transceivers. Even when the set of available sites is limited, there are exponentially many possible networks that can be built. For example, given only 50 sites, there are 2⁵⁰ (over a million billion) possibilities!

Further complicating things, for every location where service is needed, one must know which transceiver provides the strongest signal and how strong it is. However, the physical characteristics of radio propagation in an environment containing buildings, hills, foliage, and other clutter are incredibly complex, so accurate predictions require sophisticated, computationally-intensive models. Building all possible sites would yield the best coverage and capacity, but even if this were not prohibitively expensive, it would create unacceptable interference among nearby transceivers. Balancing these trade-offs is a core mathematical difficulty.

The goal of wireless network planning is to decide where to place new transceivers to maximize coverage and capacity while minimizing cost and interference. Building an automatic network planning system (a.k.a., auto-planner) that quickly solves national-scale problems at fine-grained resolution without compromising solution quality has been among the most important and difficult open challenges in telecom research for decades.

To address these issues, we are piloting network planning tools built using detailed geometric models derived from high-resolution geographic data, that feed into radio propagation models powered by distributed computing. This system provides fast, high-accuracy predictions of signal strength. Our optimization algorithms then intelligently sift through the exponential space of possible networks to output a small menu of candidate networks that each achieve different desirable trade-offs among cost, coverage, and interference, while ensuring enough capacity to meet demand.

Example auto-planning project in Charlotte, NC. Blue dots denote selected candidate sites. The heat map indicates signal strength from the propagation engine. The inset emphasizes the non-isotropic path loss in downtown.

<!–

Example auto-planning project in Charlotte, NC. Blue dots denote selected candidate sites. The heat map indicates signal strength from the propagation engine. The inset emphasizes the non-isotropic path loss in downtown.

–>

Radio Propagation
The propagation of radio waves near Earth’s surface is complicated. Like ripples in a pond, they decay with distance traveled, but they can also penetrate, bounce off, or bend around obstacles, further weakening the signal. Computing radio wave attenuation across a real-world landscape (called path loss) is a hybrid process combining traditional physics-based calculations with learned corrections accounting for obstruction, diffraction, reflection, and scattering of the signal by clutter (e.g., trees and buildings).

We have developed a radio propagation modeling engine that leverages the same high-res geodata that powers Google Earth, Maps and Street View to map the 3D distribution of vegetation and buildings. While accounting for signal origin, frequency, broadcast strength, etc., we train signal correction models using extensive real-world measurements, which account for diverse propagation environments — from flat to hilly terrain and from dense urban to sparse rural areas.

While such hybrid approaches are common, using detailed geodata enables accurate path loss predictions below one-meter resolution. Our propagation engine provides fast point-to-point path loss calculations and scales massively via distributed computation. For instance, computing coverage for 25,000 transceivers scattered across the continental United States can be done at 4 meter resolution in only 1.5 hours, using 1000 CPU cores.

Photorealistic 3D model in Google Earth (top-left) and corresponding clutter height model (top-right). Path profile through buildings and trees from a source to destination in the clutter model (bottom). Gray denotes buildings and green denotes trees.

Auto-Planning Inputs
Once accurate coverage estimates are available, we can use them to optimize network planning, for example, deciding where to place hundreds of new sites to maximize network quality. The auto-planning solver addresses large-scale combinatorial optimization problems such as these, using a fast, robust, scalable approach.

Formally, an auto-planning input instance contains a set of demand points (usually a square grid) where service is to be provided, a set of candidate transceiver sites, predicted signal strengths from candidate sites to demand points (supplied by the propagation model), and a cost budget. Each demand point includes a demand quantity (e.g., estimated from the population of wireless users), and each site includes a cost and capacity. Signal strengths below some threshold are omitted. Finally, the input may include an overall cost budget.

Data Summarization for Large Instances
Auto-planning inputs can be huge, not just because of the number of candidate sites (tens of thousands), and demand points (billions), but also because it requires signal strengths to all demand points from all nearby candidate sites. Simple downsampling is insufficient because population density may vary widely over a given region. Therefore, we apply methods like priority sampling to shrink the data. This technique produces a low-variance, unbiased estimate of the original data, preserving an accurate view of the network traffic and interference statistics, and shrinking the input data enough that a city-size instance fits into memory on one machine.

Multi-objective Optimization via Local Search
Combinatorial optimization remains a difficult task, so we created a domain-specific local search algorithm to optimize network quality. The local search algorithmic paradigm is widely applied to address computationally-hard optimization problems. Such algorithms move from one solution to another through a search space of candidate solutions by applying small local changes, stopping at a time limit or when the solution is locally optimal. To evaluate the quality of a candidate network, we combine the different objective functions into a single one, as described in the following section.

The number of local steps to reach a local optimum, number of candidate moves we evaluate per step, and time to evaluate each candidate can all be large when dealing with realistic networks. To achieve a high-quality algorithm that finishes within hours (rather than days), we must address each of these components. Fast candidate evaluation benefits greatly from dynamic data structures that maintain the mapping between each demand point and the site in the candidate solution that provides the strongest signal to it. We update this “strongest-signal” map efficiently as the candidate solution evolves during local search. The following observations help limit both the number of steps to convergence and evaluations per step.

Bipartite graph representing candidate sites (left) and demand points (right). Selected sites are circled in red, and each demand point is assigned to its strongest available connection. The topmost demand point has no service because the only site that can reach it was not selected. The third and fourth demand points from the top may have high interference if the signal strengths attached to their gray edges are only slightly lower than the ones on their red edges. The bottommost site has high congestion because many demand points get their service from that site, possibly exceeding its capacity.

Selecting two nearby sites is usually not ideal because they interfere. Our algorithm explicitly forbids such pairs of sites, thereby steering the search toward better solutions while greatly reducing the number of moves considered per step. We identify pairs of forbidden sites based on the demand points they cover, as measured by the weighted Jaccard index. This captures their functional proximity much better than simple geographic distance does, especially in urban or hilly areas where radio propagation is highly non-isotropic.

Breaking the local search into epochs also helps. The first epoch mostly adds sites to increase the coverage area while avoiding forbidden pairs. As we approach the cost budget, we begin a second epoch that includes swap moves between forbidden pairs to fine-tune the interference. This restriction limits the number of candidate moves per step, while focusing on those that improve interference with less change to coverage.

Three candidate local search moves. Red circles indicate selected sites and the orange edge indicates a forbidden pair.

Outputting a Diverse Set of Good Solutions
As mentioned before, auto-planning must balance three competing objectives: maximizing coverage, while minimizing interference and capacity violations, subject to a cost budget. There is no single correct tradeoff, so our algorithm delegates the final decision to the user by providing a small menu of candidate networks with different emphases. We apply a multiplier to each objective and optimize the sum. Raising the multiplier for a component guides the algorithm to emphasize it. We perform grid search over multipliers and budgets, generating a large number of solutions, filter out any that are worse than another solution along all four components (including cost), and finally select a small subset that represent different tradeoffs.

Menu of candidate solutions, one per row, displaying metrics. Clicking on a solution turns the selected sites pink and displays a plot of the interference distribution across covered area and demand. Sites not selected are blue.

Conclusion
We described our efforts to address the most vexing challenges facing telecom network operators. Using combinatorial optimization in concert with geospatial and radio propagation modeling, we built a scalable auto-planner for wireless telecommunication networks. We are actively exploring how to expand these capabilities to best meet the needs of our customers. Stay tuned!

For questions and other inquiries, please reach out to wireless-network-interest@google.com.

Acknowledgements
These technological advances were enabled by the tireless work of our collaborators: Aaron Archer, Serge Barbosa Da Torre, Imad Fattouch, Danny Liberty, Pishoy Maksy, Zifei Tong, and Mat Varghese. Special thanks to Corinna Cortes, Mazin Gilbert, Rob Katcher, Michael Purdy, Bea Sebastian, Dave Vadasz, Josh Williams, and Aaron Yonas, along with Serge and especially Aaron Archer for their assistance with this blog post.

Posted by Jason Wei and Denny Zhou, Research Scientists, Google Research, Brain team

In recent years, scaling up the size of language models has been shown to be a reliable way to improve performance on a range of natural language processing (NLP) tasks. Today’s language models at the scale of 100B or more parameters achieve strong performance on tasks like sentiment analysis and machine translation, even with little or no training examples. Even the largest language models, however, can still struggle with certain multi-step reasoning tasks, such as math word problems and commonsense reasoning. How might we enable language models to perform such reasoning tasks?

In “Chain of Thought Prompting Elicits Reasoning in Large Language Models,” we explore a prompting method for improving the reasoning abilities of language models. Called chain of thought prompting, this method enables models to decompose multi-step problems into intermediate steps. With chain of thought prompting, language models of sufficient scale (~100B parameters) can solve complex reasoning problems that are not solvable with standard prompting methods.

Comparison to Standard Prompting
With standard prompting (popularized by GPT-3) the model is given examples of input–output pairs (formatted as questions and answers) before being asked to predict the answer for a test-time example (shown below on the left). In chain of thought prompting (below, right), the model is prompted to produce intermediate reasoning steps before giving the final answer to a multi-step problem. The idea is that a model-generated chain of thought would mimic an intuitive thought process when working through a multi-step reasoning problem. While producing a thought process has been previously accomplished via fine-tuning, we show that such thought processes can be elicited by including a few examples of chain of thought via prompting only, which does not require a large training dataset or modifying the language model’s weights.

Whereas standard prompting asks the model to directly give the answer to a multi-step reasoning problem, chain of thought prompting induces the model to decompose the problem into intermediate reasoning steps, in this case leading to a correct final answer.

Chain of thought reasoning allows models to decompose complex problems into intermediate steps that are solved individually. Moreover, the language-based nature of chain of thought makes it applicable to any task that a person could solve via language. We find through empirical experiments that chain of thought prompting can improve performance on various reasoning tasks, and that successful chain of thought reasoning is an emergent property of model scale — that is, the benefits of chain of thought prompting only materialize with a sufficient number of model parameters (around 100B).

Arithmetic Reasoning
One class of tasks where language models typically struggle is arithmetic reasoning (i.e., solving math word problems). Two benchmarks in arithmetic reasoning are MultiArith and GSM8K, which test the ability of language models to solve multi-step math problems similar to the one shown in the figure above. We evaluate both the LaMDA collection of language models ranging from 422M to 137B parameters, as well as the PaLM collection of language models ranging from 8B to 540B parameters. We manually compose chains of thought to include in the examples for chain of thought prompting.

For these two benchmarks, using standard prompting leads to relatively flat scaling curves: increasing the scale of the model does not substantially improve performance (shown below). However, we find that when using chain of thought prompting, increasing model scale leads to improved performance that substantially outperforms standard prompting for large model sizes.

Employing chain of thought prompting enables language models to solve arithmetic reasoning problems for which standard prompting has a mostly flat scaling curve.

On the GSM8K dataset of math word problems, PaLM shows remarkable performance when scaled to 540B parameters. As shown in the table below, combining chain of thought prompting with the 540B parameter PaLM model leads to new state-of-the-art performance of 58%, surpassing the prior state of the art of 55% achieved by fine-tuning GPT-3 175B on a large training set and then ranking potential solutions via a specially trained verifier. Moreover, follow-up work on self-consistency shows that the performance of chain of thought prompting can be improved further by taking the majority vote of a broad set of generated reasoning processes, which results in 74% accuracy on GSM8K.

Chain of thought prompting with PaLM achieves a new state of the art on the GSM8K benchmark of math word problems. For a fair comparison against fine-tuned GPT-3 baselines, the chain of thought prompting results shown here also use an external calculator to compute basic arithmetic functions (i.e., addition, subtraction, multiplication and division).

Commonsense Reasoning
In addition to arithmetic reasoning, we consider whether the language-based nature of chain of thought prompting also makes it applicable to commonsense reasoning, which involves reasoning about physical and human interactions under the presumption of general background knowledge. For these evaluations, we use the CommonsenseQA and StrategyQA benchmarks, as well as two domain-specific tasks from BIG-Bench collaboration regarding date understanding and sports understanding. Example questions are below:

As shown below, for CommonsenseQA, StrategyQA, and Date Understanding, performance improved with model scale, and employing chain of thought prompting led to additional small improvements. Chain of thought prompting had the biggest improvement on sports understanding, for which PaLM 540B’s chain of thought performance surpassed that of an unaided sports enthusiast (95% vs 84%).

Chain of thought prompting also improves performance on various types of commonsense reasoning tasks.

Conclusions
Chain of thought prompting is a simple and broadly applicable method for improving the ability of language models to perform various reasoning tasks. Through experiments on arithmetic and commonsense reasoning, we find that chain of thought prompting is an emergent property of model scale. Broadening the range of reasoning tasks that language models can perform will hopefully inspire further work on language-based approaches to reasoning.

Acknowledgements
It was an honor and privilege to work with Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Quoc Le on this project.

Posted by Isaac Caswell and Ankur Bapna, Research Scientists, Google Translate

Machine translation (MT) technology has made significant advances in recent years, as deep learning has been integrated with natural language processing (NLP). Performance on research benchmarks like WMT have soared, and translation services have improved in quality and expanded to include new languages. Nevertheless, while existing translation services cover languages spoken by the majority of people world wide, they only include around 100 languages in total, just over 1% of those actively spoken globally. Moreover, the languages that are currently represented are overwhelmingly European, largely overlooking regions of high linguistic diversity, like Africa and the Americas.

There are two key bottlenecks towards building functioning translation models for the long tail of languages. The first arises from data scarcity; digitized data for many languages is limited and can be difficult to find on the web due to quality issues with Language Identification (LangID) models. The second challenge arises from modeling limitations. MT models usually train on large amounts of parallel (translated) text, but without such data, models must learn to translate from limited amounts of monolingual text, which is a novel area of research. Both of these challenges need to be addressed for translation models to reach sufficient quality.

In “Building Machine Translation Systems for the Next Thousand Languages”, we describe how to build high-quality monolingual datasets for over a thousand languages that do not have translation datasets available and demonstrate how one can use monolingual data alone to train MT models. As part of this effort, we are expanding Google Translate to include 24 under-resourced languages. For these languages, we created monolingual datasets by developing and using specialized neural language identification models combined with novel filtering approaches. The techniques we introduce supplement massively multilingual models with a self supervised task to enable zero-resource translation. Finally, we highlight how native speakers have helped us realize this accomplishment.

Meet the Data
Automatically gathering usable textual data for under-resourced languages is much more difficult than it may seem. Tasks like LangID, which work well for high-resource languages, are unsuccessful for under-resourced languages, and many publicly available datasets crawled from the web often contain more noise than usable data for the languages they attempt to support. In our early attempts to identify under-resourced languages on the web by training a standard Compact Language Detector v3 (CLD3) LangID model, we too found that the dataset was too noisy to be usable.

As an alternative, we trained a Transformer-based, semi-supervised LangID model on over 1000 languages. This model supplements the LangID task with the MAsked Sequence-to-Sequence (MASS) task to better generalize over noisy web data. MASS simply garbles the input by randomly removing sequences of tokens from it, and trains the model to predict these sequences. We applied the Transformer-based model to a dataset that had been filtered with a CLD3 model and trained to recognize clusters of similar languages.

We then applied the open sourced Term Frequency-Inverse Internet Frequency (TF-IIF) filtering to the resulting dataset to find and discard sentences that were actually in related high-resource languages, and developed a variety of language-specific filters to eliminate specific pathologies. The result of this effort was a dataset with monolingual text in over 1000 languages, of which 400 had over 100,000 sentences. We performed human evaluations on samples of 68 of these languages and found that the majority (>70%) reflected high-quality, in-language content.

The amount of monolingual data per language versus the amount of parallel (translated) data per language. A small number of languages have large amounts of parallel data, but there is a long tail of languages with only monolingual data.

Meet the Models
Once we had a dataset of monolingual text in over 1000 languages, we then developed a simple yet practical approach for zero-resource translation, i.e., translation for languages with no in-language parallel text and no language-specific translation examples. Rather than limiting our model to an artificial scenario with only monolingual text, we also include all available parallel text data with millions of examples for higher resource languages to enable the model to learn the translation task. Simultaneously, we train the model to learn representations of under-resourced languages directly from monolingual text using the MASS task. In order to solve this task, the model is forced to develop a sophisticated representation of the language in question, developing a complex understanding of how words relate to other words in a sentence.

Relying on the benefits of transfer learning in massively multilingual models, we train a single giant translation model on all available data for over 1000 languages. The model trains on monolingual text for all 1138 languages and on parallel text for a subset of 112 of the higher-resourced languages.

At training time, any input the model sees has a special token indicating which language the output should be in, exactly like the standard formulation for multilingual translation. Our additional innovation is to use the same special tokens for both the monolingual MASS task and the translation task. Therefore, the token translate_to_french may indicate that the source is in English and needs to be translated to French (the translation task), or it may mean that the source is in garbled French and needs to be translated to fluent French (the MASS task). By using the same tags for both tasks, a translate_to_french tag takes on the meaning, “Produce a fluent output in French that is semantically close to the input,” regardless of whether the input is garbled in the same language or in another language entirely. From the model’s perspective, there is not much difference between the two.

Surprisingly, this simple procedure produces high quality zero-shot translations. The BLEU and ChrF scores for the resulting model are in the 10–40 and 20–60 ranges respectively, indicating mid- to high-quality translation. We observed meaningful translations even for highly inflected languages like Quechua and Kalaallisut, despite these languages being linguistically dissimilar to all other languages in the model. However, we only computed these metrics on the small subset of languages with human-translated evaluation sets. In order to understand the quality of translation for the remaining languages, we developed an evaluation metric based on round-trip translation, which allowed us to see that several hundred languages are reaching high translation quality.

To further improve quality, we use the model to generate large amounts of synthetic parallel data, filter the data based on round-trip translation (comparing a sentence translated into another language and back again), and continue training the model on this filtered synthetic data via back-translation and self-training. Finally, we fine-tune the model on a smaller subset of 30 languages and distill it into a model small enough to be served.

Translation accuracy scores for 638 of the languages supported in our model, using the metric we developed (RTTLangIDChrF), for both the higher-resource supervised languages and the low-resource zero-resource languages.

Contributions from Native Speakers
Regular communication with native speakers of these languages was critical for our research. We collaborated with over 100 people at Google and other institutions who spoke these languages. Some volunteers helped develop specialized filters to remove out-of-language content overlooked by automatic methods, for instance Hindi mixed with Sanskrit. Others helped with transliterating between different scripts used by the languages, for instance between Meetei Mayek and Bengali, for which sufficient tools didn’t exist; and yet others helped with a gamut of tasks related to evaluation. Native speakers were also key for advising in matters of political sensitivity, like the appropriate name for the language, and the appropriate writing system to use for it. And only native speakers could answer the ultimate question: given the current quality of translation, would it be valuable to the community for Google Translate to support this language?

Closing Notes
This advance is an exciting first step toward supporting more language technologies in under-resourced languages. Most importantly, we want to stress that the quality of translations produced by these models still lags far behind that of the higher-resource languages supported by Google Translate. These models are certainly a useful first tool for understanding content in under-resourced languages, but they will make mistakes and exhibit their own biases. As with any ML-driven tool, one should consider the output carefully.

The complete list of new languages added to Google Translate in this update:

Acknowledgements
We would like to thank Julia Kreutzer, Orhan Firat, Daan van Esch, Aditya Siddhant, Mengmeng Niu, Pallavi Baljekar, Xavier Garcia, Wolfgang Macherey, Theresa Breiner, Vera Axelrod, Jason Riesa, Yuan Cao, Mia Xu Chen, Klaus Macherey, Maxim Krikun, Pidong Wang, Alexander Gutkin, Apurva Shah, Yanping Huang, Zhifeng Chen, Yonghui Wu, and Macduff Hughes for their contributions to the research, engineering, and leadership of this project.

We would also like to extend our deepest gratitude to the following native speakers and members of affected communities, who helped us in a wide variety of ways: Yasser Salah Eddine Bouchareb (Algerian Arabic); Mfoniso Ukwak (Anaang); Bhaskar Borthakur, Kishor Barman, Rasika Saikia, Suraj Bharech (Assamese); Ruben Hilare Quispe (Aymara); Devina Suyanto (Balinese); Allahserix Auguste Tapo, Bakary Diarrassouba, Maimouna Siby (Bambara); Mohammad Jahangir (Baluchi); Subhajit Naskar (Bengali); Animesh Pathak, Ankur Bapna, Anup Mohan, Chaitanya Joshi, Chandan Dubey, Kapil Kumar, Manish Katiyar, Mayank Srivastava, Neeharika, Saumya Pathak, Tanya Sinha, Vikas Singh (Bhojpuri); Bowen Liang, Ellie Chio, Eric Dong, Frank Tang, Jeff Pitman, John Wong, Kenneth Chang, Manish Goregaokar, Mingfei Lau, Ryan Li, Yiwen Luo (Cantonese); Monang Setyawan (Caribbean Javanese); Craig Cornelius (Cherokee); Anton Prokopyev (Chuvash); Rajat Dogra, Sid Dogra (Dogri); Mohamed Kamagate (Dyula); Chris Assigbe, Dan Ameme, Emeafa Doe, Irene Nyavor, Thierry Gnanih, Yvonne Dumor (Ewe); Abdoulaye Barry, Adama Diallo, Fauzia van der Leeuw, Ibrahima Barry (Fulfulde); Isabel Papadimitriou (Greek); Alex Rudnick (Guarani); Mohammad Khdeir (Gulf Arabic); Paul Remollata (Hiligaynon); Ankur Bapna (Hindi); Mfoniso Ukwak (Ibibio); Nze Lawson (Igbo); D.J. Abuy, Miami Cabansay (Ilocano); Archana Koul, Shashwat Razdan, Sujeet Akula (Kashmiri); Jatin Kulkarni, Salil Rajadhyaksha, Sanjeet Hegde Desai, Sharayu Shenoy, Shashank Shanbhag, Shashi Shenoy (Konkani); Ryan Michael, Terrence Taylor (Krio); Bokan Jaff, Medya Ghazizadeh, Roshna Omer Abdulrahman, Saman Vaisipour, Sarchia Khursheed (Kurdish (Sorani));Suphian Tweel (Libyan Arabic); Doudou Kisabaka (Lingala); Colleen Mallahan, John Quinn (Luganda); Cynthia Mboli (Luyia); Abhishek Kumar, Neeraj Mishra, Priyaranjan Jha, Saket Kumar, Snehal Bhilare (Maithili); Lisa Wang (Mandarin Chinese); Cibu Johny (Malayalam); Viresh Ratnakar (Marathi); Abhi Sanoujam, Gautam Thockchom, Pritam Pebam, Sam Chaomai, Shangkar Mayanglambam, Thangjam Hindustani Devi (Meiteilon (Manipuri)); Hala Ajil (Mesopotamian Arabic); Hamdanil Rasyid (Minangkabau); Elizabeth John, Remi Ralte, S Lallienkawl Gangte,Vaiphei Thatsing, Vanlalzami Vanlalzami (Mizo); George Ouais (MSA); Ahmed Kachkach, Hanaa El Azizi (Morrocan Arabic); Ujjwal Rajbhandari (Newari); Ebuka Ufere, Gabriel Fynecontry, Onome Ofoman, Titi Akinsanmi (Nigerian Pidgin); Marwa Khost Jarkas (North Levantine Arabic); Abduselam Shaltu, Ace Patterson, Adel Kassem, Mo Ali, Yonas Hambissa (Oromo); Helvia Taina, Marisol Necochea (Quechua); AbdelKarim Mardini (Saidi Arabic); Ishank Saxena, Manasa Harish, Manish Godara, Mayank Agrawal, Nitin Kashyap, Ranjani Padmanabhan, Ruchi Lohani, Shilpa Jindal, Shreevatsa Rajagopalan, Vaibhav Agarwal, Vinod Krishnan (Sanskrit); Nabil Shahid (Saraiki); Ayanda Mnyakeni (Sesotho, Sepedi); Landis Baker (Seychellois Creole); Taps Matangira (Shona); Ashraf Elsharif (Sudanese Arabic); Sakhile Dlamini (Swati); Hakim Sidahmed (Tamazight); Melvin Johnson (Tamil); Sneha Kudugunta (Telugu); Alexander Tekle, Bserat Ghebremicael, Nami Russom, Naud Ghebre (Tigrinya); Abigail Annkah, Diana Akron, Maame Ofori, Monica Opoku-Geren, Seth Duodu-baah, Yvonne Dumor (Twi); Ousmane Loum (Wolof); and Daniel Virtheim (Yiddish).

Posted by Jimmy (Tsung-Yen) Yang, Student Researcher, Robotics at Google

The promise of deep reinforcement learning (RL) in solving complex, high-dimensional problems autonomously has attracted much interest in areas such as robotics, game playing, and self-driving cars. However, effectively training an RL policy requires exploring a large set of robot states and actions, including many that are not safe for the robot. This is a considerable risk, for example, when training a legged robot. Because such robots are inherently unstable, there is a high likelihood of the robot falling during learning, which could cause damage.

The risk of damage can be mitigated to some extent by learning the control policy in computer simulation and then deploying it in the real world. However, this approach usually requires addressing the difficult sim-to-real gap, i.e., the policy trained in simulation can not be readily deployed in the real world for various reasons, such as sensor noise in deployment or the simulator not being realistic enough during training. Another approach to solve this issue is to directly learn or fine-tune a control policy in the real world. But again, the main challenge is to assure safety during learning.

In “Safe Reinforcement Learning for Legged Locomotion”, we introduce a safe RL framework for learning legged locomotion while satisfying safety constraints during training. Our goal is to learn locomotion skills autonomously in the real world without the robot falling during the entire learning process. Our learning framework adopts a two-policy safe RL framework: a “safe recovery policy” that recovers robots from near-unsafe states, and a “learner policy” that is optimized to perform the desired control task. The safe learning framework switches between the safe recovery policy and the learner policy to enable robots to safely acquire novel and agile motor skills.

The Proposed Framework
Our goal is to ensure that during the entire learning process, the robot never falls, regardless of the learner policy being used. Similar to how a child learns to ride a bike, our approach teaches an agent a policy while using “training wheels”, i.e., a safe recovery policy. We first define a set of states, which we call a “safety trigger set”, where the robot is close to violating safety constraints but can still be saved by a safe recovery policy. For example, the safety trigger set can be defined as a set of states with the height of the robots being below a certain threshold and the roll, pitch, yaw angles being too large, which is an indication of falls. When the learner policy results in the robot being within the safety trigger set (i.e., where it is likely to fall), we switch to the safe recovery policy, which drives the robot back to a safe state. We determine when to switch back to the learner policy by leveraging an approximate dynamics model of the robot to predict the future robot trajectory. For example, based on the position of the robot’s legs and the current angle of the robot based on sensors for roll, pitch, and yaw, is it likely to fall in the future? If the predicted future states are all safe, we hand the control back to the learner policy, otherwise, we keep using the safe recovery policy.

The state diagram of the proposed approach. (1) If the learner policy violates the safety constraint, we switch to the safe recovery policy. (2) If the learner policy cannot ensure safety in the near future after switching to the safe recovery policy, we keep using the safe recovery policy. This allows the robot to explore more while ensuring safety.

This approach ensures safety in complex systems without resorting to opaque neural networks that may be sensitive to distribution shifts in application. In addition, the learner policy is able to explore states that are near safety violations, which is useful for learning a robust policy.

Because we use “approximated” dynamics to predict the future trajectory, we also examine how much safer a robot would be if we used a much more accurate model for its dynamics. We provide a theoretical analysis of this problem and show that our approach can achieve minimal safety performance loss compared to one with a full knowledge about the system dynamics.

Legged Locomotion Tasks
To demonstrate the effectiveness of the algorithm, we consider learning three different legged locomotion skills:

1. Efficient Gait: The robot learns how to walk with low energy consumption and is rewarded for consuming less energy.
2. Catwalk: The robot learns a catwalk gait pattern, in which the left and right two feet are close to each other. This is challenging because by narrowing the support polygon, the robot becomes less stable.
3. Two-leg Balance: The robot learns a two-leg balance policy, in which the front-right and rear-left feet are in stance, and the other two are lifted. The robot can easily fall without delicate balance control because the contact polygon degenerates into a line segment.

Locomotion tasks considered in the paper. Top: efficient gait. Middle: catwalk. Bottom: two-leg balance.

Implementation Details
We use a hierarchical policy framework that combines RL and a traditional control approach for the learner and safe recovery policies. This framework consists of a high-level RL policy, which produces gait parameters (e.g., stepping frequency) and feet placements, and pairs it with a low-level process controller called model predictive control (MPC) that takes in these parameters and computes the desired torque for each motor in the robot. Because we do not directly command the motors’ angles, this approach provides more stable operation, streamlines the policy training due to a smaller action space, and results in a more robust policy. The input of the RL policy network includes the previous gait parameters, the height of the robot, base orientation, linear, angular velocities, and feedback to indicate whether the robot is approaching the safety trigger set. We use the same setup for each task.

We train a safe recovery policy with a reward for reaching stability as soon as possible. Furthermore, we design the safety trigger set with inspiration from capturability theory. In particular, the initial safety trigger set is defined to ensure that the robot’s feet can not fall outside of the positions from which the robot can safely recover using the safe recovery policy. We then fine-tune this set on the real robot with a random policy to prevent the robot from falling.

Real-World Experiment Results
We report the real-world experimental results showing the reward learning curves and the percentage of safe recovery policy activations on the efficient gait, catwalk, and two-leg balance tasks. To ensure that the robot can learn to be safe, we add a penalty when triggering the safe recovery policy. Here, all the policies are trained from scratch, except for the two-leg balance task, which was pre-trained in simulation because it requires more training steps.

Overall, we see that on these tasks, the reward increases, and the percentage of uses of the safe recovery policy decreases over policy updates. For instance, the percentage of uses of the safe recovery policy decreases from 20% to near 0% in the efficient gait task. For the two-leg balance task, the percentage drops from near 82.5% to 67.5%, suggesting that the two-leg balance is substantially harder than the previous two tasks. Still, the policy does improve the reward. This observation implies that the learner can gradually learn the task while avoiding the need to trigger the safe recovery policy. In addition, this suggests that it is possible to design a safe trigger set and a safe recovery policy that does not impede the exploration of the policy as the performance increases.

The reward learning curve (blue) and the percentage of safe recovery policy activations (red) using our safe RL algorithm in the real world.

In addition, the following video shows the learning process for the two-leg balance task, including the interplay between the learner policy and the safe recovery policy, and the reset to the initial position when an episode ends. We can see that the robot tries to catch itself when falling by putting down the lifted legs (front left and rear right) outward, creating a support polygon. After the learning episode ends, the robot walks back to the reset position automatically. This allows us to train policy autonomously and safely without human supervision.

Early training stage.

Late training stage.

Without a safe recovery policy.

Finally, we show the clips of learned policies. First, in the catwalk task, the distance between two sides of the legs is 0.09m, which is 40.9% smaller than the nominal distance. Second, in the two-leg balance task, the robot can maintain balance by jumping up to four times via two legs, compared to one jump from the policy pre-trained from simulation.

Final learned two-leg balance.

Conclusion
We presented a safe RL framework and demonstrated how it can be used to train a robotic policy with no falls and without the need for a manual reset during the entire learning process for the efficient gait and catwalk tasks. This approach even enables training of a two-leg balance task with only four falls. The safe recovery policy is triggered only when needed, allowing the robot to more fully explore the environment. Our results suggest that learning legged locomotion skills autonomously and safely is possible in the real world, which could unlock new opportunities including offline dataset collection for robot learning.

No model is without limitation. We currently ignore the model uncertainty from the environment and non-linear dynamics in our theoretical analysis. Including these would further improve the generality of our approach. In addition, some hyper-parameters of the switching criteria are currently being heuristically tuned. It would be more efficient to automatically determine when to switch based on the learning progress. Furthermore, it would be interesting to extend this safe RL framework to other robot applications, such as robot manipulation. Finally, designing an appropriate reward when incorporating the safe recovery policy can impact learning performance. We use a penalty-based approach that obtained reasonable results in these experiments, but we plan to investigate this in future work to make further performance improvements.

Acknowledgements
We would like to thank our paper co-authors: Tingnan Zhang, Linda Luu, Sehoon Ha, Jie Tan, and Wenhao Yu. We would also like to thank the team members of Robotics at Google for discussions and feedback.

John Palowitch and Anton Tsitsulin, Research Scientists, Google Research, Graph Mining team

Graphs are very common representations of natural systems that have connected relational components, such as social networks, traffic infrastructure, molecules, and the internet. Graph neural networks (GNNs) are powerful machine learning (ML) models for graphs that leverage their inherent connections to incorporate context into predictions about items within the graph or the graph as a whole. GNNs have been effectively used to discover new drugs, help mathematicians prove theorems, detect misinformation, and improve the accuracy of arrival time predictions in Google Maps.

A surge of interest in GNNs during the last decade has produced thousands of GNN variants, with hundreds introduced each year. In contrast, methods and datasets for evaluating GNNs have received far less attention. Many GNN papers re-use the same 5–10 benchmark datasets, most of which are constructed from easily labeled academic citation networks and molecular datasets. This means that the empirical performance of new GNN variants can be claimed only for a limited class of graphs. Confounding this issue are recently published works with rigorous experimental designs that cast doubt on the performance rankings of popular GNN models reported in seminal papers.

Recent workshops and conference tracks devoted to GNN benchmarking have begun addressing these issues. The recently-introduced Open Graph Benchmark (OGB) is an open-source package for benchmarking GNNs on a handful of massive-scale graph datasets across a variety of tasks, facilitating consistent GNN experimental design. However, the OGB datasets are sourced from many of the same domains as existing datasets, such as citation and molecular networks. This means that OGB does not solve the dataset variety problem we mention above. Therefore, we ask: how can the GNN research community keep up with innovation by experimenting on graphs with the large statistical variance seen in the real-world?

To match the scale and pace of GNN research, in “GraphWorld: Fake Graphs Bring Real Insights for GNNs”, we introduce a methodology for analyzing the performance of GNN architectures on millions of synthetic benchmark datasets. Whereas GNN benchmark datasets featured in academic literature are just individual “locations” on a fully-diverse “world” of potential graphs, GraphWorld directly generates this world using probability models, tests GNN models at every location on it, and extracts generalizable insights from the results. We propose GraphWorld as a complementary GNN benchmark that allows researchers to explore GNN performance on regions of graph space that are not covered by popular academic datasets. Furthermore, GraphWorld is cost-effective, running hundreds-of-thousands of GNN experiments on synthetic data with less computational cost than one experiment on a large OGB dataset.

Illustration of the GraphWorld pipeline. The user provides configurations for the graph generator and the GNN models to test. GraphWorld spawns workers, each one simulating a new graph with diverse properties and testing all specified GNN models. The test metrics from the workers are then aggregated and stored for the user.

The Limited Variety of GNN Benchmark Datasets
To illustrate the motivation for GraphWorld, we compare OGB graphs to a much larger collection (5,000+) of graphs from the Network Repository. While the vast majority of Network Repository graphs are unlabelled, and therefore cannot be used in common GNN experiments, they represent a large space of graphs that are available in the real world. We computed two properties of the OGB and Network Repository graphs: the clustering coefficient (how interconnected nodes are to nearby neighbors) and the degree distribution gini coefficient (the inequality among the nodes’ connection counts). We found that OGB datasets exist in a limited and sparsely-populated region of this metric space.

The distribution of graphs from the Open Graph Benchmark does not match the larger population of graphs from the Network Repository.

Dataset Generators in GraphWorld
A researcher using GraphWorld to investigate GNN performance on a given task first chooses a parameterized generator (example below) that can produce graph datasets for stress-testing GNN models on the task. A generator parameter is an input that controls high-level features of the output dataset. GraphWorld uses parameterized generators to produce populations of graph datasets that are varied enough to test the limits of state-of-the-art GNN models.

For instance, a popular task for GNNs is node classification, in which a GNN is trained to infer node labels that represent some unknown property of each node, such as user interests in a social network. In our paper, we chose the well-known stochastic block model (SBM) to generate datasets for this task. The SBM first organizes a pre-set number of nodes into groups or “clusters“, which serve as node labels to be classified. It then generates connections between nodes according to various parameters that (each) control a different property of the resulting graph.

One SBM parameter that we expose to GraphWorld is the “homophily” of the clusters, which controls the likelihood that two nodes from the same cluster are connected (relative to two nodes from different clusters). Homophily is a common phenomenon in social networks in which users with similar interests (e.g., the SBM clusters) are more likely to connect. However, not all social networks have the same level of homophily. GraphWorld uses the SBM to generate graphs with high homophily (below on the left), graphs with low homophily (below on the right), and millions more graphs with any level of homophily in-between. This allows a user to analyze GNN performance on graphs with all levels of homophily without depending on the availability of real-world datasets curated by other researchers.

Examples of graphs produced by GraphWorld using the stochastic block model. The left graph has high homophily among node classes (represented by different colors); the right graph has low homophily.

GraphWorld Experiments and Insights
Given a task and parameterized generator for that task, GraphWorld uses parallel computing (e.g., Google Cloud Platform Dataflow) to produce a world of GNN benchmark datasets by sampling the generator parameter values. Simultaneously, GraphWorld tests an arbitrary list of GNN models (chosen by the user, e.g., GCN, GAT, GraphSAGE) on each dataset, and then outputs a massive tabular dataset joining graph properties with the GNN performance results.

In our paper, we describe GraphWorld pipelines for node classification, link prediction, and graph classification tasks, each featuring different dataset generators. We found that each pipeline took less time and computational resources than state-of-the-art experiments on OGB graphs, which means that GraphWorld is accessible to researchers with low budgets.

The animation below visualizes GNN performance data from the GraphWorld node classification pipeline (using the SBM as the dataset generator). To illustrate the impact of GraphWorld, we first map classic academic graph datasets to an x–y plane that measures the cluster homophily (x-axis) and the average of the node degrees (y-axis) within each graph (similar to the scatterplot above that includes the OGB datasets, but with different measurements). Then, we map each simulated graph dataset from GraphWorld to the same plane, and add a third z-axis that measures GNN model performance over each dataset. Specifically, for a particular GNN model (like GCN or GAT), the z-axis measures the mean reciprocal rank of the model against the 13 other GNN models evaluated in our paper, where a value closer to 1 means the model is closer to being the top performer in terms of node classification accuracy.

The animation illustrates two related conclusions. First, GraphWorld generates regions of graph datasets that extend well-beyond the regions covered by the standard datasets. Second, and most importantly, the rankings of GNN models change when graphs become dissimilar from academic benchmark graphs. Specifically, the homophily of classic datasets like Cora and CiteSeer are high, meaning that nodes are well-separated in the graph according to their classes. We find that as GNNs traverse toward the space of less-homophilous graphs, their rankings change quickly. For example, the comparative mean reciprocal rank of GCN moves from higher (green) values in the academic benchmark region to lower (red) values away from that region. This shows that GraphWorld has the potential to reveal critical headroom in GNN architecture development that would be invisible with only the handful of individual datasets that academic benchmarks provide.

Relative performance results of three GNN variants (GCN, APPNP, FiLM) across 50,000 distinct node classification datasets. We find that academic GNN benchmark datasets exist in GraphWorld regions where model rankings do not change. GraphWorld can discover previously unexplored graphs that reveal new insights about GNN architectures.

Conclusion
GraphWorld breaks new ground in GNN experimentation by allowing researchers to scalably test new models on a high-dimensional surface of graph datasets. This allows fine-grained analysis of GNN architectures against graph properties on entire subspaces of graphs that are distal from Cora-like graphs and those in the OGB, which appear only as individual points in a GraphWorld dataset. A key feature of GraphWorld is its low cost, which enables individual researchers without access to institutional resources to quickly understand the empirical performance of new models.

With GraphWorld, researchers can also investigate novel random/generative graph models for more-nuanced GNN experimentation, and potentially use GraphWorld datasets for GNN pre-training. We look forward to supporting these lines of inquiry with our open-source GraphWorld repository and follow-up projects.

Acknowledgements
GraphWorld is joint work with Brandon Mayer and Bryan Perozzi from Google Research. Thanks to Tom Small for visualizations.

Posted by Zhuohan Li, Student Researcher, Google Research, and Yu Emma Wang, Senior Software Engineer, Google Core

Over the last several years, the rapidly growing size of deep learning models has quickly exceeded the memory capacity of single accelerators. Earlier models like BERT (with a parameter size of < 1GB) can efficiently scale across accelerators by leveraging data parallelism in which model weights are duplicated across accelerators while only partitioning and distributing the training data. However, recent large models like GPT-3 (with a parameter size of 175GB) can only scale using model parallel training, where a single model is partitioned across different devices.

While model parallelism strategies make it possible to train large models, they are more complex in that they need to be specifically designed for target neural networks and compute clusters. For example, Megatron-LM uses a model parallelism strategy to split the weight matrices by rows or columns and then synchronizes results among devices. Device placement or pipeline parallelism partitions different operators in a neural network into multiple groups and the input data into micro-batches that are executed in a pipelined fashion. Model parallelism often requires significant effort from system experts to identify an optimal parallelism plan for a specific model. But doing so is too onerous for most machine learning (ML) researchers whose primary focus is to run a model and for whom the model’s performance becomes a secondary priority. As such, there remains an opportunity to automate model parallelism so that it can easily be applied to large models.

In “Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning”, published at OSDI 2022, we describe a method for automating the complex model parallelism process. We demonstrate that with only one line of code Alpa can transform any JAX neural network into a distributed version with an optimal parallelization strategy that can be executed on a user-provided device cluster. We are also excited to release Alpa’s code to the broader research community.

Alpa Design
We begin by grouping existing ML parallelization strategies into two categories, inter-operator parallelism and intra-operator parallelism. Inter-operator parallelism assigns distinct operators to different devices (e.g., device placement) that are often accelerated with a pipeline execution schedule (e.g., pipeline parallelism). With intra-operator parallelism, which includes data parallelism (e.g., Deepspeed-Zero), operator parallelism (e.g., Megatron-LM), and expert parallelism (e.g., GShard-MoE), individual operators are split and executed on multiple devices, and often collective communication is used to synchronize the results across devices.

The difference between these two approaches maps naturally to the heterogeneity of a typical compute cluster. Inter-operator parallelism has lower communication bandwidth requirements because it is only transmitting activations between operators on different accelerators. But, it suffers from device underutilization because of its pipeline data dependency, i.e., some operators are inactive while waiting on the outputs from other operators. In contrast, intra-operator parallelism doesn’t have the data dependency issue, but requires heavier communication across devices. In a GPU cluster, the GPUs within a node have higher communication bandwidth that can accommodate intra-operator parallelism. However, GPUs across different nodes are often connected with much lower bandwidth (e.g., ethernet) so inter-operator parallelism is preferred.

By leveraging heterogeneous mapping, we design Alpa as a compiler that conducts various passes when given a computational graph and a device cluster from a user. First, the inter-operator pass slices the computational graph into subgraphs and the device cluster into submeshes (i.e., a partitioned device cluster) and identifies the best way to assign a subgraph to a submesh. Then, the intra-operator pass finds the best intra-operator parallelism plan for each pipeline stage from the inter-operator pass. Finally, the runtime orchestration pass generates a static plan that orders the computation and communication and executes the distributed computational graph on the actual device cluster.

An overview of Alpa. In the sliced subgraphs, red and blue represent the way the operators are partitioned and gray represents operators that are replicated. Green represents the actual devices (e.g., GPUs).

Intra-Operator Pass
Similar to previous research (e.g., Mesh-TensorFlow and GSPMD), intra-operator parallelism partitions a tensor on a device mesh. This is shown below for a typical 3D tensor in a Transformer model with a given batch, sequence, and hidden dimensions. The batch dimension is partitioned along device mesh dimension 0 (mesh0), the hidden dimension is partitioned along mesh dimension 1 (mesh1), and the sequence dimension is replicated to each processor.

A 3D tensor that is partitioned on a 2D device mesh.

With the partitions of tensors in Alpa, we further define a set of parallelization strategies for each individual operator in a computational graph. We show example parallelization strategies for matrix multiplication in the figure below. Defining parallelization strategies on operators leads to possible conflicts on the partitions of tensors because one tensor can be both the output of one operator and the input of another. In this case, re-partition is needed between the two operators, which incurs additional communication costs.

The parallelization strategies for matrix multiplication.

Given the partitions of each operator and re-partition costs, we formulate the intra-operator pass as a Integer-Linear Programming (ILP) problem. For each operator, we define a one-hot variable vector to enumerate the partition strategies. The ILP objective is to minimize the sum of compute and communication cost (node cost) and re-partition communication cost (edge cost). The solution of the ILP translates to one specific way to partition the original computational graph.

Inter-Operator Pass
The inter-operator pass slices the computational graph and device cluster for pipeline parallelism. As shown below, the boxes represent micro-batches of input and the pipeline stages represent a submesh executing a subgraph. The horizontal dimension represents time and shows the pipeline stage at which a micro-batch is executed. The goal of the inter-operator pass is to minimize the total execution latency, which is the sum of the entire workload execution on the device as illustrated in the figure below. Alpa uses a Dynamic Programming (DP) algorithm to minimize the total latency. The computational graph is first flattened, and then fed to the intra-operator pass where the performance of all possible partitions of the device cluster into submeshes are profiled.

Pipeline parallelism. For a given time, this figure shows the micro-batches (colored boxes) that a partitioned device cluster and a sliced computational graph (e.g., stage 1, 2, 3) is processing.

Runtime Orchestration
After the inter- and intra-operator parallelization strategies are complete, the runtime generates and dispatches a static sequence of execution instructions for each device submesh. These instructions include RUN a specific subgraph, SEND/RECEIVE tensors from other meshes, or DELETE a specific tensor to free the memory. The devices can execute the computational graph without other coordination by following the instructions.

Evaluation
We test Alpa with eight AWS p3.16xlarge instances, each of which has eight 16 GB V100 GPUs, for 64 total GPUs. We examine weak scaling results of growing the model size while increasing the number of GPUs. We evaluate three models: (1) the standard Transformer model (GPT); (2) the GShard-MoE model, a transformer with mixture-of-expert layers; and (3) Wide-ResNet, a significantly different model with no existing expert-designed model parallelization strategy. The performance is measured by peta-floating point operations per second (PFLOPS) achieved on the cluster.

We demonstrate that for GPT, Alpa outputs a parallelization strategy very similar to the one computed by the best existing framework, Megatron-ML, and matches its performance. For GShard-MoE, Alpa outperforms the best expert-designed baseline on GPU (i.e., Deepspeed) by up to 8x. Results for Wide-ResNet show that Alpa can generate the optimal parallelization strategy for models that have not been studied by experts. We also show the linear scaling numbers for reference.

GPT: Alpa matches the performance of Megatron-ML, the best expert-designed framework.

GShard MoE: Alpa outperforms Deepspeed (the best expert-designed framework on GPU) by up to 8x.

Wide-ResNet: Alpa generalizes to models without manual plans. Pipeline and Data Parallelism (PP-DP) is a baseline model that uses only pipeline and data parallelism but no other intra-operator parallelism.

The parallelization strategy for Wide-ResNet on 16 GPUs consists of three pipeline stages and is a complicated strategy even for an expert to design. Stages 1 and 2 are on 4 GPUs performing data parallelism, and stage 3 is on 8 GPUs performing operator parallelism.

Conclusion
The process of designing an effective parallelization plan for distributed model-parallel deep learning has historically been a difficult and labor-intensive task. Alpa is a new framework that leverages intra- and inter-operator parallelism for automated model-parallel distributed training. We believe that Alpa will democratize distributed model-parallel learning and accelerate the development of large deep learning models. Explore the open-source code and learn more about Alpa in our paper.

Acknowledgements
Thanks to the co-authors of the paper: Lianmin Zheng, Hao Zhang, Yonghao Zhuang, Yida Wang, Danyang Zhuo, Joseph E. Gonzalez, and Ion Stoica. We would also like to thank Shibo Wang, Jinliang Wei, Yanping Huang, Yuanzhong Xu, Zhifeng Chen, Claire Cui, Naveen Kumar, Yash Katariya, Laurent El Shafey, Qiao Zhang, Yonghui Wu, Marcello Maggioni, Mingyao Yang, Michael Isard, Skye Wanderman-Milne, and David Majnemer for their collaborations to this research.

Posted by Dhruv Shah, Intern, and Brian Ichter, Research Scientist, Robotics at Google

Advances in reinforcement learning (RL) for robotics have enabled robotic agents to perform increasingly complex tasks in challenging environments. Recent results show that robots can learn to fold clothes, dexterously manipulate a rubik’s cube, sort objects by color, navigate complex environments and walk on difficult, uneven terrain. But “short-horizon” tasks such as these, which require very little long-term planning and provide immediate failure feedback, are relatively easy to train compared to many tasks that may confront a robot in a real-world setting. Unfortunately, scaling such short-horizon skills to the abstract, long horizons of real-world tasks is difficult. For example, how would one train a robot capable of picking up objects to rearrange a room?

Hierarchical reinforcement learning (HRL), a popular way of solving this problem, has achieved some success in a variety of long-horizon RL tasks. HRL aims to solve such problems by reasoning over a bank of low-level skills, thus providing an abstraction for actions. However, the high-level planning problem can be further simplified by abstracting both states and actions. For example, consider a tabletop rearrangement task, where a robot is tasked with interacting with objects on a desk. Using recent advances in RL, imitation learning, and unsupervised skill discovery, it is possible to obtain a set of primitive manipulation skills such as opening or closing drawers, picking or placing objects, etc. However, even for the simple task of putting a block into the drawer, chaining these skills together is not straightforward. This may be attributed to a combination of (i) challenges with planning and reasoning over long horizons, and (ii) dealing with high dimensional observations while parsing the semantics and affordances of the scene, i.e., where and when the skill can be used.

In “Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning”, presented at ICLR 2022, we address the task of learning suitable state and action abstractions for long-range problems. We posit that a minimal, but complete, representation for a higher-level policy in HRL must depend on the capabilities of the skills available to it. We present a simple mechanism to obtain such a representation using skill value functions and show that such an approach improves long-horizon performance in both model-based and model-free RL and enables better zero-shot generalization.

Our method, VFS, can compose low-level primitives (left) to learn complex long-horizon behaviors (right).

Building a Value Function Space
The key insight motivating this work is that the abstract representation of actions and states is readily available from trained policies via their value functions. The notion of “value” in RL is intrinsically linked to affordances, in that the value of a state for skill reflects the probability of receiving a reward for successfully executing the skill. For any skill, its value function captures two key properties: 1) the preconditions and affordances of the scene, i.e., where and when the skill can be used, and 2) the outcome, which indicates whether the skill executed successfully when it was used.

Given a decision process with a finite set of k skills trained with sparse outcome rewards and their corresponding value functions, we construct an embedding space by stacking these skill value functions. This gives us an abstract representation that maps a state to a k-dimensional representation that we call the Value Function Space, or VFS for short. This representation captures functional information about the exhaustive set of interactions that the agent can have with the environment, and is thus a suitable state abstraction for downstream tasks.

Consider a toy example of the tabletop rearrangement setup discussed earlier, with the task of placing the blue object in the drawer. There are eight elementary actions in this environment. The bar plot on the right shows the values of each skill at any given time, and the graph at the bottom shows the evolution of these values over the course of the task.

Value functions corresponding to each skill (top-right; aggregated in bottom) capture functional information about the scene (top-left) and aid decision-making.

At the beginning, the values corresponding to the “Place on Counter” skill are high since the objects are already on the counter; likewise, the values corresponding to “Close Drawer” are high. Through the trajectory, when the robot picks up the blue cube, the corresponding skill value peaks. Similarly, the values corresponding to placing the objects in the drawer increase when the drawer is open and peak when the blue cube is placed inside it. All the functional information required to affect each transition and predict its outcome (success or failure) is captured by the VFS representation, and in principle, allows a high-level agent to reason over all the skills and chain them together — resulting in an effective representation of the observations.

Additionally, since VFS learns a skill-centric representation of the scene, it is robust to exogenous factors of variation, such as background distractors and appearances of task-irrelevant components of the scene. All configurations shown below are functionally equivalent — an open drawer with the blue cube in it, a red cube on the countertop, and an empty gripper — and can be interacted with identically, despite apparent differences.

The learned VFS representation can ignore task-irrelevant factors such as arm pose, distractor objects (green cube) and background appearance (brown desk).

Robotic Manipulation with VFS
This approach enables VFS to plan out complex robotic manipulation tasks. Take, for example, a simple model-based reinforcement learning (MBRL) algorithm that uses a simple one-step predictive model of the transition dynamics in value function space and randomly samples candidate skill sequences to select and execute the best one in a manner similar to the model-predictive control. Given a set of primitive pushing skills of the form “move Object A near Object B” and a high-level rearrangement task, we find that VFS can use MBRL to reliably find skill sequences that solve the high-level task.

A rollout of VFS performing a tabletop rearrangement task using a robotic arm. VFS can reason over a sequence of low-level primitives to achieve the desired goal configuration.

To better understand the attributes of the environment captured by VFS, we sample the VFS-encoded observations from a large number of independent trajectories in the robotic manipulation task and project them onto a two-dimensional axis using the t-SNE technique, which is useful for visualizing clusters in high-dimensional data. These t-SNE embeddings reveal interesting patterns identified and modeled by VFS. Looking at some of these clusters closely, we find that VFS can successfully capture information about the contents (objects) in the scene and affordances (e.g., a sponge can be manipulated when held by the robot’s gripper), while ignoring distractors like the relative positions of the objects on the table and the pose of the robotic arm. While these factors are certainly important to solve the task, the low-level primitives available to the robot abstract them away and hence, make them functionally irrelevant to the high-level controller.

Visualizing the 2D t-SNE projections of VFS embeddings show emergent clustering of equivalent configurations of the environment while ignoring task-irrelevant factors like arm pose.

Conclusions and Connections to Future Work
Value function spaces are representations built on value functions of underlying skills, enabling long-horizon reasoning and planning over skills. VFS is a compact representation that captures the affordances of the scene and task-relevant information while robustly ignoring distractors. Empirical experiments reveal that such a representation improves planning for model-based and model-free methods and enables zero-shot generalization. Going forward, this representation has the promise to continue improving along with the field of multitask reinforcement learning. The interpretability of VFS further enables integration into fields such as safe planning and grounding language models.

Acknowledgements
We thank our co-authors Sergey Levine, Ted Xiao, Alex Toshev, Peng Xu and Yao Lu for their contributions to the paper and feedback on this blog post. We also thank Tom Small for creating the informative visualizations used in this blog post.

Sometimes, a software’s best feature is the one you’ve added yourself. This post shows by example why you may want to extend torch, and how to proceed. It also explains a bit of what is going on in the background.

Posted by Cat Armato and Callan Hajosy, Program Managers

The 10th International Conference on Learning Representations (ICLR 2022) kicks off this week, bringing together researchers, entrepreneurs, engineers and students alike to discuss and explore the rapidly advancing field of deep learning. Entirely virtual this year, ICLR 2022 offers conference and workshop tracks that present some of the latest research in deep learning and its applications to areas ranging from computer vision, speech recognition and text understanding to robotics, computational biology, and more.

As a Platinum Sponsor of ICLR 2022 and Champion DEI Action Fund contributor, Google will have a robust presence with nearly 100 accepted publications and extensive participation on organizing committees and in workshops. If you have registered for ICLR 2022, we hope you’ll watch our talks and learn about the work done at Google to address complex problems that affect billions of people. Here you can learn more about the research we will be presenting as well as our general involvement at ICLR 2022 (those with Google affiliations in bold).

Senior Area Chairs:
Includes: Been Kim, Dale Schuurmans, Sergey Levine

Area Chairs:
Includes: Adam White, Aditya Menon, Aleksandra Faust, Amin Karbasi, Amir Globerson, Andrew Dai, Balaji Lakshminarayanan, Behnam Neyshabur, Ben Poole, Bhuwan Dhingra, Bo Dai, Boqing Gong, Cristian Sminchisescu, David Ha, David Woodruff, Denny Zhou, Dipanjan Das, Dumitru Erhan, Dustin Tran, Emma Strubell, Eunsol Choi, George Dahl, George Tucker, Hanie Sedghi, Heinrich Jiang, Hossein Mobahi, Hugo Larochelle, Izhak Shafran, Jasper Snoek, Jean-Philippe Vert, Jeffrey Pennington, Justin Gilmer, Karol Hausman, Kevin Swersky, Krzysztof Choromanski, Mathieu Blondel, Matt Kusner, Michael Ryoo, Ming-Hsuan Yang, Minmin Chen, Mirella Lapata, Mohammad Ghavamzadeh, Mohammad Norouzi, Naman Agarwal, Nicholas Carlini, Olivier Bachem, Piyush Rai, Prateek Jain, Quentin Berthet, Richard Nock, Rose Yu, Sewoong Oh, Silvio Lattanzi, Slav Petrov, Srinadh Bhojanapalli, Tim Salimans, Ting Chen, Tong Zhang, Vikas Sindhwani, Weiran Wang, William Cohen, Xiaoming Liu

Workflow Chairs:
Includes: Yaguang Li

Diversity Equity & Inclusion Chairs:
Includes: Rosanne Liu

Invited Talks
Beyond Interpretability: Developing a Language to Shape Our Relationships with AI
Google Speaker: Been Kim

Do You See What I See? Large-Scale Learning from Multimodal Videos
Google Speaker: Cordelia Schmid

Publications
Hyperparameter Tuning with Renyi Differential Privacy – 2022 Outstanding Paper Award
Nicolas Papernot, Thomas Steinke

MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
Yusong Wu, Ethan Manilow, Yi Deng, Rigel Swavely, Kyle Kastner, Tim Cooijmans, Aaron Courville, Cheng-Zhi Anna Huang, Jesse Engel

The Information Geometry of Unsupervised Reinforcement Learning
Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

Learning Strides in Convolutional Neural Networks – 2022 Outstanding Paper Award
Rachid Riad^*, Olivier Teboul, David Grangier, Neil Zeghidour

Poisoning and Backdooring Contrastive Learning
Nicholas Carlini, Andreas Terzis

Coordination Among Neural Modules Through a Shared Global Workspace
Anirudh Goyal, Aniket Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke, Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Mozer, Yoshua Bengio

Fine-Tuned Language Models Are Zero-Shot Learners (see the blog post)
Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, Quoc V. Le

Large Language Models Can Be Strong Differentially Private Learners
Xuechen Li, Florian Tramèr, Percy Liang, Tatsunori Hashimoto

Progressive Distillation for Fast Sampling of Diffusion Models
Tim Salimans, Jonathan Ho

Exploring the Limits of Large Scale Pre-training
Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, Hanie Sedghi

Scarf: Self-Supervised Contrastive Learning Using Random Feature Corruption
Dara Bahri, Heinrich Jiang, Yi Tay, Donald Metzler

Scalable Sampling for Nonsymmetric Determinantal Point Processes
Insu Han, Mike Gartrell, Jennifer Gillenwater, Elvis Dohmatob, Amin Karbasi

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
Xiangning Chen, Cho-Jui Hsieh, Boqing Gong

ViTGAN: Training GANs with Vision Transformers
Kwonjoon Lee, Huiwen Chang, Lu Jiang, Han Zhang, Zhuowen Tu, Ce Liu

Generalized Decision Transformer for Offline Hindsight Information Matching
Hiroki Furuta, Yutaka Matsuo, Shixiang Shane Gu

The MultiBERTs: BERT Reproductions for Robustness Analysis
Thibault Sellam, Steve Yadlowsky, Ian Tenney, Jason Wei, Naomi Saphra, Alexander D’Amour, Tal Linzen, Jasmijn Bastings, Iulia Turc, Jacob Eisenstein, Dipanjan Das, Ellie Pavlick

Scaling Laws for Neural Machine Translation
Behrooz Ghorbani, Orhan Firat, Markus Freitag, Ankur Bapna, Maxim Krikun, Xavier Garcia, Ciprian Chelba, Colin Cherry

Interpretable Unsupervised Diversity Denoising and Artefact Removal
Mangal Prakash, Mauricio Delbracio, Peyman Milanfar, Florian Jug

Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective
Qi Lyu, Xiao Fu, Weiran Wang, Songtao Lu

Memorizing Transformers
Yuhuai Wu, Markus N. Rabe, DeLesley Hutchins, Christian Szegedy

Churn Reduction via Distillation
Heinrich Jiang, Harikrishna Narasimhan, Dara Bahri, Andrew Cotter, Afshin Rostamizadeh

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization
Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron Courville, George Tucker, Sergey Levine

Path Auxiliary Proposal for MCMC in Discrete Space
Haoran Sun, Hanjun Dai, Wei Xia, Arun Ramamurthy

On the Relation Between Statistical Learning and Perceptual Distances
Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Johannes Ballé, Jesús Malo

Possibility Before Utility: Learning And Using Hierarchical Affordances
Robby Costales, Shariq Iqbal, Fei Sha

MT3: Multi-Task Multitrack Music Transcription
Josh Gardner^*, Ian Simon, Ethan Manilow^*, Curtis Hawthorne, Jesse Engel

Bayesian Neural Network Priors Revisited
Vincent Fortuin, Adrià Garriga-Alonso, Sebastian W. Ober, Florian Wenzel, Gunnar Rätsch, Richard E. Turner, Mark van der Wilk, Laurence Aitchison

GradMax: Growing Neural Networks using Gradient Information
Utku Evci, Bart van Merrienboer, Thomas Unterthiner, Fabian Pedregosa, Max Vladymyrov

Scene Transformer: A Unified Architecture for Predicting Future Trajectories of Multiple Agents
Jiquan Ngiam, Benjamin Caine, Vijay Vasudevan, Zhengdong Zhang, Hao-Tien Lewis Chiang, Jeffrey Ling, Rebecca Roelofs, Alex Bewley, Chenxi Liu, Ashish Venugopal, David Weiss, Ben Sapp, Zhifeng Chen, Jonathon Shlens

The Role of Pretrained Representations for the OOD Generalization of RL Agents
Frederik Träuble, Andrea Dittadi, Manuel Wüthrich, Felix Widmaier, Peter Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

Autoregressive Diffusion Models
Emiel Hoogeboom, Alexey A. Gritsenko, Jasmijn Bastings, Ben Poole, Rianne van den Berg, Tim Salimans

The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
Rahim Entezari, Hanie Seghi, Olga Saukh, Behnam Neyshabur

DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
Asma Ghandeharioun, Been Kim, Chun-Liang Li, Brendan Jou, Brian Eoff, Rosalind W. Picard

Anisotropic Random Feature Regression in High Dimensions
Gabriel C. Mel, Jeffrey Pennington

Open-Vocabulary Object Detection via Vision and Language Knowledge Distillation
Xiuye Gu, Tsung-Yi Lin^*, Weicheng Kuo, Yin Cui

MCMC Should Mix: Learning Energy-Based Model with Flow-Based Backbone
Erik Nijkamp^*, Ruiqi Gao, Pavel Sountsov, Srinivas Vasudevan, Bo Pang, Song-Chun Zhu, Ying Nian Wu

Effect of Scale on Catastrophic Forgetting in Neural Networks
Vinay Ramasesh, Aitor Lewkowycz, Ethan Dyer

Incremental False Negative Detection for Contrastive Learning
Tsai-Shien Chen, Wei-Chih Hung, Hung-Yu Tseng, Shao-Yi Chien, Ming-Hsuan Yang

Towards Evaluating the Robustness of Neural Networks Learned by Transduction
Jiefeng Chen, Xi Wu, Yang Guo, Yingyu Liang, Somesh Jha

What Do We Mean by Generalization in Federated Learning?
Honglin Yuan^*, Warren Morningstar, Lin Ning, Karan Singhal

ViDT: An Efficient and Effective Fully Transformer-Based Object Detector
Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang

Measuring CLEVRness: Black-Box Testing of Visual Reasoning Models
Spyridon Mouselinos, Henryk Michalewski, Mateusz Malinowski

Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models (see the blog post)
Xiaofang Wang, Dan Kondratyuk, Eric Christiansen, Kris M. Kitani, Yair Alon (prev. Movshovitz-Attias), Elad Eban

Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Saurabh Garg^*, Sivaraman Balakrishnan, Zachary C. Lipton, Behnam Neyshabur, Hanie Sedghi

Data-Driven Offline Optimization for Architecting Hardware Accelerators (see the blog post)
Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine

Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions
Chen Zhu^*, Zheng Xu, Mingqing Chen, Jakub Konecny, Andrew Hard, Tom Goldstein

Policy Gradients Incorporating the Future
David Venuto, Elaine Lau, Doina Precup, Ofir Nachum

Discrete Representations Strengthen Vision Transformer Robustness
Chengzhi Mao^*, Lu Jiang, Mostafa Dehghani, Carl Vondrick, Rahul Sukthankar, Irfan Essa

SimVLM: Simple Visual Language Model Pretraining with Weak Supervision (see the blog post)
Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, Yuan Cao

Neural Stochastic Dual Dynamic Programming
Hanjun Dai, Yuan Xue, Zia Syed, Dale Schuurmans, Bo Dai

PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Zhaoqi Leng, Mingxing Tan, Chenxi Liu, Ekin Dogus Cubuk, Xiaojie Shi, Shuyang Cheng, Dragomir Anguelov

Information Prioritization Through Empowerment in Visual Model-Based RL
Homanga Bharadhwaj^*, Mohammad Babaeizadeh, Dumitru Erhan, Sergey Levine

Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Dhruv Shah, Peng Xu, Yao Lu, Ted Xiao, Alexander Toshev, Sergey Levine, Brian Ichter

Understanding and Leveraging Overparameterization in Recursive Value Estimation
Chenjun Xiao, Bo Dai, Jincheng Mei, Oscar Ramirez, Ramki Gummadi, Chris Harris, Dale Schuurmans

The Efficiency Misnomer
Mostafa Dehghani, Anurag Arnab, Lucas Beyer, Ashish Vaswani, Yi Tay

On the Role of Population Heterogeneity in Emergent Communication
Mathieu Rita, Florian Strub, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux

No One Representation to Rule Them All: Overlapping Features of Training Methods
Raphael Gontijo-Lopes, Yann Dauphin, Ekin D. Cubuk

Data Poisoning Won’t Save You From Facial Recognition
Evani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian Tramèr

AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation
David Berthelot, Rebecca Roelofs, Kihyuk Sohn, Nicholas Carlini, Alex Kurakin

Maximum Entropy RL (Provably) Solves Some Robust RL Problems
Benjamin Eysenbach, Sergey Levine

Auto-scaling Vision Transformers Without Training
Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou

Optimizing Few-Step Diffusion Samplers by Gradient Descent
Daniel Watson, William Chan, Jonathan Ho, Mohammad Norouzi

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
Vamsi Aribandi, Yi Tay, Tal Schuster, Jinfeng Rao, Huaixiu Steven Zheng, Sanket Vaibhav Mehta, Honglei Zhuang, Vinh Q. Tran, Dara Bahri, Jianmo Ni, Jai Gupta, Kai Hui, Sebastian Ruder, Donald Metzler

Fortuitous Forgetting in Connectionist Networks
Hattie Zhou, Ankit Vani, Hugo Larochelle, Aaron Courville

Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent
Oliver Bryniarski, Nabeel Hingun, Pedro Pachuca, Vincent Wang, Nicholas Carlini

Benchmarking the Spectrum of Agent Capabilities
Danijar Hafner

Charformer: Fast Character Transformers via Gradient-Based Subword Tokenization
Yi Tay, Vinh Q. Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, Donald Metzler

Mention Memory: Incorporating Textual Knowledge into Transformers Through Entity Mention Attention
Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Fei Sha, William Cohen

Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums
Rui Pan, Haishan Ye, Tong Zhang

Scale Efficiently: Insights from Pre-training and Fine-Tuning Transformers
Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler

Omni-Scale CNNs: A Simple and Effective Kernel Size Configuration for Time Series Classification
Wensi Tang, Guodong Long, Lu Liu,Tianyi Zhou, Michael Blumenstein, Jing Jiang

Embedded-Model Flows: Combining the Inductive Biases of Model-Free Deep Learning and Explicit Probabilistic Modeling
Gianluigi Silvestri, Emily Fertig, Dave Moore, Luca Ambrogioni

Post Hoc Explanations May be Ineffective for Detecting Unknown Spurious Correlation
Julius Adebayo, Michael Muelly, Hal Abelson, Been Kim

Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
Mark Hamilton, Scott Lundberg, Stephanie Fu, Lei Zhang, William T. Freeman

Pix2seq: A Language Modeling Framework for Object Detection (see the blog post)
Ting Chen, Saurabh Saxena, Lala Li, David J. Fleet, Geoffrey Hinton

Mirror Descent Policy Optimization
Manan Tomar, Lior Shani, Yonathan Efroni, Mohammad Ghavamzadeh

CodeTrek: Flexible Modeling of Code Using an Extensible Relational Representation
Pardis Pashakhanloo, Aaditya Naik, Yuepeng Wang, Hanjun Dai, Petros Maniatis, Mayur Naik

Conditional Object-Centric Learning From Video
Thomas Kipf, Gamaleldin F. Elsayed, Aravindh Mahendran, Austin Stone, Sara Sabour, Georg Heigold, Rico Jonschkowski, Alexey Dosovitskiy, Klaus Greff

A Loss Curvature Perspective on Training Instabilities of Deep Learning Models
Justin Gilmer, Behrooz Ghorbani, Ankush Garg, Sneha Kudugunta, Behnam Neyshabur, David Cardoze, George E. Dahl, Zack Nado, Orhan Firat

Autonomous Reinforcement Learning: Formalism and Benchmarking
Archit Sharma, Kelvin Xu, Nikhil Sardana, Abhishek Gupta, Karol Hausman, Sergey Levine, Chelsea Finn

TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
Mengjiao Yang, Sergey Levine, Ofir Nachum

Minimax Optimization With Smooth Algorithmic Adversaries
Tanner Fiez, Lillian J. Ratliff, Chi Jin, Praneeth Netrapalli

Unsupervised Semantic Segmentation by Distilling Feature Correspondences
Mark Hamilton, Zhoutong Zhang, Bharath Hariharan, Noah Snavely, William T. Freeman

InfinityGAN: Towards Infinite-Pixel Image Synthesis
Chieh Hubert Lin, Hsin-Ying Lee, Yen-Chi Cheng, Sergey Tulyakov, Ming-Hsuan Yang

Shuffle Private Stochastic Convex Optimization
Albert Cheu, Matthew Joseph, Jieming Mao, Binghui Peng

Hybrid Random Features
Krzysztof Choromanski, Haoxian Chen, Han Lin, Yuanzhe Ma, Arijit Sehanobish, Deepali Jain, Michael S Ryoo, Jake Varley, Andy Zeng, Valerii Likhosherstov, Dmitry Kalashnikov, Vikas Sindhwani, Adrian Weller

Vector-Quantized Image Modeling With Improved VQGAN
Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu

On the Benefits of Maximum Likelihood Estimation for Regression and Forecasting
Pranjal Awasthi, Abhimanyu Das, Rajat Sen, Ananda Theertha Suresh

Surrogate Gap Minimization Improves Sharpness-Aware Training
Juntang Zhuang^*, Boqing Gong, Liangzhe Yuan, Yin Cui, Hartwig Adam, Nicha C. Dvornek, Sekhar Tatikonda, James S. Duncan, Ting Liu

Online Target Q-learning With Reverse Experience Replay: Efficiently Finding the Optimal Policy for Linear MDPs
Naman Agarwal, Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli, Syomantak Chaudhuri

CrossBeam: Learning to Search in Bottom-Up Program Synthesis
Kensen Shi, Hanjun Dai, Kevin Ellis, Charles Sutton

Workshops
Workshop on the Elements of Reasoning: Objects, Structure, and Causality (OSC)
Organizers include: Klaus Greff, Thomas Kipf

Workshop on Agent Learning in Open-Endedness
Organizers include: Krishna Srinivasan
Speakers include: Natasha Jaques, Danijar Hafner

Wiki-M3L: Wikipedia and Multi-modal & Multi-lingual Research
Organizers include: Klaus Greff, Thomas Kipf
Speakers include: Jason Baldridge, Tom Duerig

Setting Up ML Evaluation Standards to Accelerate Progress
Organizers include: Rishabh Agarwal
Speakers and Panelists include: Katherine Heller, Sara Hooker, Corinna Cortes

From Cells to Societies: Collective Learning Across Scales
Organizers include: Mark Sandler, Max Vladymyrov
Speakers include: Blaise Aguera y Arcas, Alexander Mordvintsev, Michael Mozer

Emergent Communication: New Frontiers
Speakers include: Natasha Jaques

Deep Learning for Code
Organizers include: Jonathan Herzig

GroundedML: Anchoring Machine Learning in Classical Algorithmic Theory
Speakers include: Gintare Karolina Dziugaite

Generalizable Policy Learning in the Physical World
Speakers and Panelists include: Mrinal Kalakrishnan

CoSubmitting Summer (CSS) Workshop
Organizers include: Rosanne Liu

---

^*Work done while at Google.  ^↩