Yoshua Bengio

Biography

*For media requests, please write to medias@mila.quebec.

For more information please contact Marie-Josée Beauchamp, Administrative Assistant at marie-josee.beauchamp@mila.quebec.

Yoshua Bengio is recognized worldwide as a leading expert in AI. He is most known for his pioneering work in deep learning, which earned him the 2018 A.M. Turing Award, “the Nobel Prize of computing,” with Geoffrey Hinton and Yann LeCun.

Bengio is a full professor at Université de Montréal, and the founder and scientific advisor of Mila – Quebec Artificial Intelligence Institute. He is also a senior fellow at CIFAR and co-directs its Learning in Machines & Brains program, serves as special advisor and founding scientific director of IVADO, and holds a Canada CIFAR AI Chair.

In 2019, Bengio was awarded the prestigious Killam Prize and in 2022, he was the most cited computer scientist in the world by h-index. He is a Fellow of the Royal Society of London, Fellow of the Royal Society of Canada, Knight of the Legion of Honor of France and Officer of the Order of Canada. In 2023, he was appointed to the UN’s Scientific Advisory Board for Independent Advice on Breakthroughs in Science and Technology.

Concerned about the social impact of AI, Bengio helped draft the Montréal Declaration for the Responsible Development of Artificial Intelligence and continues to raise awareness about the importance of mitigating the potentially catastrophic risks associated with future AI systems.

Current Students

Jamal Abou Haibeh

Collaborating Alumni - McGill University

Mohammed Abukalam

Collaborating Alumni - Université de Montréal

Berkes Anaïs

Collaborating researcher - Cambridge University

Principal supervisor :

Rim Assouel

PhD - Université de Montréal

Junyeob BAEK

Independent visiting researcher - KAIST

Independent visiting researcher

Co-supervisor :

Guillaume Lajoie

Paul Bertin

PhD - Université de Montréal

Shahana Chatterjee

Collaborating researcher - N/A

Principal supervisor :

David Rolnick

Xiaoyin Chen

PhD - Université de Montréal

Sanghyeok Choi

Collaborating researcher - KAIST

PhD - Université de Montréal

PhD - Université de Montréal

Research Intern - Université de Montréal

Co-supervisor :

Loubna Benabbou

Eric Elmoznino

PhD - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Jean-Pierre Falet

PhD - Université de Montréal

Co-supervisor :

Leo Feng

PhD - Université de Montréal

leo.feng@mila.quebec

Ivan Grega

Research Intern - Université de Montréal

PhD

PhD - Université de Montréal

mohsin.hasan@mila.quebec

Edward Hu

PhD - Université de Montréal

Moksh Jain

PhD - Université de Montréal

moksh.jain@mila.quebec

PhD - Université de Montréal

Principal supervisor :

Collaborating Alumni - Université de Montréal

Hyeonah Kim

Postdoctorate - Université de Montréal

Principal supervisor :

Alex Hernandez

Yaroslav KIVVA

Collaborating researcher - Université de Montréal

Salem Lahlou

Collaborating Alumni - Université de Montréal

Tabitha Edith Lee

Postdoctorate - Université de Montréal

Principal supervisor :

Seanie Lee

Collaborating Alumni - Université de Montréal

Collaborating Alumni

Zhen Liu

Collaborating Alumni - Université de Montréal

Principal supervisor :

Liam Paull

Kanika Madan

PhD - Université de Montréal

Nikolay Malkin

Collaborating Alumni - Université de Montréal

Cristian Dragos Manta

PhD - Université de Montréal

Co-supervisor :

Dhanya Sridhar

Sören Mindermann

Collaborating researcher - Université de Montréal

Sarthak Mittal

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

Postdoctorate - Université de Montréal

Principal supervisor :

Independent visiting researcher - Université de Montréal

Padideh Nouri

PhD - Université de Montréal

Principal supervisor :

Ali Parviz

Collaborating researcher - Ying Wu Coll of Computing

Lena Podina

PhD - University of Waterloo

Principal supervisor :

Collaborating Alumni - Max-Planck-Institute for Intelligent Systems

Amine RAZIG

Research Intern - Université de Montréal

Co-supervisor :

Loubna Benabbou

Jarrid Rector-Brooks

PhD - Université de Montréal

Danyal REHMAN

Postdoctorate - Université de Montréal

James Requeima

Independent visiting researcher - Université de Montréal

Oli RICHARDSON

Postdoctorate - Université de Montréal

Camille Rochefort-Boulanger

PhD - Université de Montréal

Principal supervisor :

Julie Hussin

Victor Schmidt

Collaborating Alumni - Université de Montréal

Postdoctorate - Université de Montréal

Master's Research - Université de Montréal

Marcin Sendera

Collaborating Alumni - Université de Montréal

Vedant Shah

Master's Research - Université de Montréal

Postdoctorate

Marco Stock

Independent visiting researcher - Technical University of Munich

marco.stock@tum.de

Mélisande Astrid Crystal Teng

PhD - Université de Montréal

Co-supervisor :

Hugo Larochelle

alexander.tong@mila.quebec

Alex Tong

Postdoctorate - Université de Montréal

Postdoctorate - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Principal supervisor :

Collaborating researcher - Université de Montréal

Omar G. Younis

Collaborating researcher

Collaborating researcher - KAIST

Nicole Zhang

PhD - McGill University

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Harry Zhao

PhD - McGill University

Principal supervisor :

Blog Posts

Generic thumbnail for Mila Blog articles.

February 22, 2024

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Scaling in the Service of Reasoning & Model-Based ML

April 4, 2023

Yoshua Bengio

Edward J. Hu

A collaboration between Mila and Relation Therapeutics to discover novel synergistic combinations of drugs in vitro

March 23, 2022

Paul Bertin

Jake P. Taylor-King

Yoshua Bengio

March 15, 2022

Generative Flow Networks

Yoshua Bengio

Publications

CAMAP: Artificial neural networks unveil the role of 1 codon arrangement in modulating MHC-I peptides 2 presentation

Tariq Daouda

Maude Dumont-Lagacé

Albert Feghaly

Yahya Benslimane

6. Rébecca

Panes

Mathieu Courcelles

Mohamed Benhammadi

Lea Harrington

Pierre Thibault

François Major

Étienne Gagnon

Sébastien Lemieux

Claude Perreault

30 MHC-I associated peptides (MAPs) play a central role in the elimination of virus-infected and 31 neoplastic cells by CD8 T cells. However… (see more), accurately predicting the MAP repertoire remains 32 difficult, because only a fraction of the transcriptome generates MAPs. In this study, we 33 investigated whether codon arrangement (usage and placement) regulates MAP biogenesis. We 34 developed an artificial neural network called Codon Arrangement MAP Predictor (CAMAP), 35 predicting MAP presentation solely from mRNA sequences flanking the MAP-coding codons 36 (MCCs), while excluding the MCC per se . CAMAP predictions were significantly more accurate 37 when using original codon sequences than shuffled codon sequences which reflect amino acid 38 usage. Furthermore, predictions were independent of mRNA expression and MAP binding affinity 39 to MHC-I molecules and applied to several cell types and species. Combining MAP ligand scores, 40 transcript expression level and CAMAP scores was particularly useful to increaser MAP prediction 41 accuracy. Using an in vitro assay, we showed that varying the synonymous codons in the regions 42 flanking the MCCs (without changing the amino acid sequence) resulted in significant modulation 43 of MAP presentation at the cell surface. Taken together, our results demonstrate the role of codon 44 arrangement in the regulation of MAP presentation and support integration of both translational 45 and post-translational events in predictive algorithms to ameliorate modeling of the 46 immunopeptidome. 47 48 49 they modulated the levels of SIINFEKL presentation in both constructs, but enhanced translation efficiency could only be detected for OVA-RP. These data show that codon arrangement can modulate MAP presentation strength without any changes in the amino

CAMAP: Artificial neural networks unveil the role of 1 codon arrangement in modulating MHC-I peptides 2 presentation discovery of minor histocompatibility with

Tariq Daouda

Maude Dumont-Lagacé

Albert Feghaly

Yahya Benslimane

6. Rébecca

Panes

Mathieu Courcelles

Mohamed Benhammadi

Lea Harrington

Pierre Thibault

François Major

Étienne Gagnon

Sébastien Lemieux

Claude Perreault

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

Harry Zhao

Mingde Zhao

Zhen Liu

Sitao Luan

Shuyuan Zhang

Doina Precup

We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during plan… (see more)ning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by attending to the relevant objects, leading to better out-of-distribution generalization performance.

Cooperative Semi-Supervised Transfer Learning of Machine Reading Comprehension

Oliver Bender

Franz Josef Och

R´ejean Ducharme

Pascal Vincent

Kevin Clark

Quoc Minh-Thang Luong

V. Le

Jacob Devlin

Ming-Wei Chang

Kenton Lee

Adam Fisch

Alon Talmor

Robin Jia

Minjoon Seo

Michael R. Glass

A. Gliozzo

Rishav Chakravarti

Ian J Goodfellow

Jean Pouget-Abadie … (see 39 more)

Mehdi Mirza

Serhii Havrylov

Ivan Titov. 2017

Emergence

Jun-Tao He

Jiatao Gu

Jiajun Shen

Marc’Aurelio

Matthew Henderson

I. Casanueva

Nikola Mrkˇsi´c

Pei-hao Su

Tsung-Hsien Wen

Ivan Vuli´c

Yikang Shen

Yi Tay

Che Zheng

Dara Bahri

Donald

Metzler Aaron

Courville

Structformer

Ashish Vaswani

Noam M. Shazeer

Niki Parmar

Thomas Wolf

Lysandre Debut

Julien Victor Sanh

Clement Chaumond

Anthony Delangue

Pier-339 Moi

Tim ric Cistac

R´emi Rault

Morgan Louf

Qizhe Xie

Eduard H. Hovy

Silei Xu

Sina Jandaghi Semnani

Giovanni Campagna

Pretrained language models have signiﬁcantly 001 improved the performance of down-stream 002 language understanding tasks, including ex-00… (see more)3 tractive question answering, by providing 004 high-quality contextualized word embeddings. 005 However, training question answering models 006 still requires large amounts of annotated data 007 for speciﬁc domains. In this work, we pro-008 pose a cooperative, self-play learning frame-009 work, REGEX, for automatically generating 010 more non-trivial question-answer pairs to im-011 prove model performance. REGEX is built 012 upon a masked answer extraction task with an 013 interactive learning environment containing an 014 answer entity REcognizer, a question Gener-015 ator, and an answer EXtractor. Given a pas-016 sage with a masked entity, the generator gen-017 erates a question around the entity, and the 018 extractor is trained to extract the masked en-019 tity with the generated question and raw texts. 020 The framework allows the training of question 021 generation and answering models on any text 022 corpora without annotation. We further lever-023 age a reinforcement learning technique to re-024 ward generating high-quality questions and to 025 improve the answer extraction model’s perfor-026 mance. Experiment results show that REGEX 027 outperforms the state-of-the-art (SOTA) pre-028 trained language models and transfer learning 029 approaches on standard question-answering 030 benchmarks, and yields the new SOTA per-031 formance under given model size and transfer 032 learning settings. 033

Dynamic Inference with Neural Interpreters

Nasim Rahaman

Muhammad Waleed Gondal

Shruti Joshi

Peter Vincent Gehler

Francesco Locatello

Bernhard Schölkopf

Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they ar… (see more)e less capable of systematic generalization to data drawn from unseen but related distributions, a feat that is hypothesized to require compositional reasoning and reuse of knowledge. In this work, we present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules, which we call _functions_. Inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. The proposed architecture can flexibly compose computation along width and depth, and lends itself well to capacity extension after training. To demonstrate the versatility of Neural Interpreters, we evaluate it in two distinct settings: image classification and visual abstract reasoning on Raven Progressive Matrices. In the former, we show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner. In the latter, we find that Neural Interpreters are competitive with respect to the state-of-the-art in terms of systematic generalization.

Episodes Meta Sequence S 2 Fast Update Slow Update Fast Update Slow Update

Kanika Madan

Nan Rosemary Ke

Anirudh Goyal

Bernhard Schölkopf

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning age… (see more)nt interacting with its environment is likely to be faced with situations requiring novel combinations of existing pieces of knowledge. We hypothesize that such a decomposition of knowledge is particularly relevant for being able to generalize in a systematic manner to out-of-distribution changes. To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks. An attention mechanism dynamically selects which modules can be adapted to the current task, and the parameters of the selected modules are allowed to change quickly as the learner is confronted with variations in what it experiences, while the parameters of the attention mechanisms act as stable, slowly changing, metaparameters.We focus on pieces of knowledge captured by an ensemble of modules sparsely communicating with each other via a bottleneck of attention. We find that meta-learning the modular aspects of the proposed system greatly helps in achieving faster adaptation in a reinforcement learning setup involving navigation in a partially observed grid world with image-level input. We also find that reversing the role of parameters and meta-parameters does not work nearly as well, suggesting a particular role for fast adaptation of the dynamically selected modules.

Explaining by Analogy: Case-based Abductive Natural Language Inference

Ruben Cartuyvels

Graham Spinks

Marie Francine

Peter Clark

Isaac Cowhey

Oren Etzioni

Tushar Khot

Rajarshi Das

Ameya Godbole

Shehzaad Dhuliawala

Manzil Zaheer

Andrew McCallum

Dung Ngoc Thai

Ameya

Ethan Godbole

Jay-Yoon Perez

Lee

Lizhen

Ramón López De Mántaras

David Mcsherry … (see 37 more)

David Bridge

Barry Leake

Susan Smyth

Craw.

Boi

Maryalice Faltings

Michael T Maher

Ken-552 Cox

Dorottya Demszky

Kelvin Guu

Percy Liang

Jacob Devlin

Ming-Wei Chang

Kenton Lee

Daniel Fried

Peter Jansen

Gus Hahn-Powell

Higher-575

Rebecca Emilie Sharp

M. Surdeanu

Zhengnan Xie

Sebastian Thiem

Jaycie Ryrholm Martin

Eliz-721 abeth Wainwright

Steven Marmorstein

Wenhan Xiong

Xiang Lorraine Li

Srini Iyer

Jingfei Du

Vikas Yadav

Steven Bethard

Zhilin Yang

Peng Qi

Saizheng Zhang

William W Cohen

Russ Salakhutdinov

Existing accounts of explanation emphasise 001 the role of prior experience and analogy in 002 the solution of new problems. However, most 0… (see more)03 of the contemporary models for multi-hop tex-004 tual inference construct explanations consider-005 ing each test case in isolation. This paradigm 006 is known to suffer from semantic drift, which 007 causes the construction of spurious explana-008 tions leading to wrong predictions. In con-009 trast, we propose an abductive framework for 010 multi-hop inference that adopts the retrieve - 011 reuse - revise paradigm largely studied in case-012 based reasoning . Speciﬁcally, we present 013 ETNA ( E xplana t io n by A nalogy), a novel 014 model that addresses unseen inference prob-015 lems by retrieving and adapting prior expla-016 nations from similar training examples. We 017 empirically evaluate the case-based abductive 018 framework on downstream commonsense and 019 scientiﬁc reasoning tasks. Our experiments 020 demonstrate that ETNA can be effectively in-021 tegrated with sparse and dense encoding mech-022 anisms or downstream transformers, achiev-023 ing strong performance when compared to ex-024 isting explainable approaches. Moreover, we 025 study the impact of the retrieve - reuse - revise 026 paradigm on explainability and semantic drift, 027 showing that it boosts the quality of the con-028 structed explanations, resulting in improved 029 downstream inference performance. 030

Exploring the Wasserstein metric for time-to-event analysis.

Tristan Sylvain

Margaux Luck

Joseph Paul Cohen

Heloise Cardinal

Andrea Lodi

2021-01-01

SPACA (published)

proceedings.mlr.press

Exploring the Wasserstein metric for survival analysis

Tristan Sylvain

Margaux Luck

Joseph Paul Cohen

Andrea Lodi

Survival analysis is a type of semi-supervised task where the target output (the survival time) is often right-censored. Utilizing this info… (see more)rmation is a challenge because it is not obvious how to correctly incorporate these censored examples into a model. We study how three categories of loss functions can take advantage of this information: partial likelihood methods, rank methods, and our own classiﬁcation method based on a Wasserstein metric (WM) and the non-parametric Kaplan Meier (KM) estimate of the probability density to impute the labels of censored examples. The proposed method predicts the probability distribution of an event, letting us compute survival curves and expected times of survival that are easier to interpret than the rank. We also demonstrate that this approach directly optimizes the expected C-index which is the most common evaluation metric for survival models.

Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments

Anirudh Goyal

Alex Lamb

Phanideep Gampa

Philippe Beaudoin

Charles Blundell

Sergey Levine

Michael Curtis Mozer

2021-01-01

ICLR (published)

Fast and Slow Learning of Recurrent Independent Mechanisms

Kanika Madan

Nan Rosemary Ke

Anirudh Goyal

Bernhard Schölkopf

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning age… (see more)nt interacting with its environment is likely to be faced with situations requiring novel combinations of existing pieces of knowledge. We hypothesize that such a decomposition of knowledge is particularly relevant for being able to generalize in a systematic manner to out-of-distribution changes. To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks. An attention mechanism dynamically selects which modules can be adapted to the current task, and the parameters of the selected modules are allowed to change quickly as the learner is confronted with variations in what it experiences, while the parameters of the attention mechanisms act as stable, slowly changing, meta-parameters. We focus on pieces of knowledge captured by an ensemble of modules sparsely communicating with each other via a bottleneck of attention. We find that meta-learning the modular aspects of the proposed system greatly helps in achieving faster adaptation in a reinforcement learning setup involving navigation in a partially observed grid world with image-level input. We also find that reversing the role of parameters and meta-parameters does not work nearly as well, suggesting a particular role for fast adaptation of the dynamically selected modules.

2021-01-01

ICLR (published)

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation

Emmanuel Bengio

Moksh J. Jain

Maksym Korablyov

Doina Precup

This paper is about the problem of learning a stochastic policy for generating an object (like a molecular graph) from a sequence of actions… (see more), such that the probability of generating an object is proportional to a given positive reward for that object. Whereas standard return maximization tends to converge to a single return-maximizing sequence, there are cases where we would like to sample a diverse set of high-return solutions. These arise, for example, in black-box function optimization when few rounds are possible, each with large batches of queries, where the batches should be diverse, e.g., in the design of new molecules. One can also see this as a problem of approximately converting an energy function to a generative distribution. While MCMC methods can achieve that, they are expensive and generally only perform local exploration. Instead, training a generative policy amortizes the cost of search during training and yields to fast generation. Using insights from Temporal Difference learning, we propose GFlowNet, based on a view of the generative process as a flow network, making it possible to handle the tricky case where different trajectories can yield the same final state, e.g., there are many ways to sequentially add atoms to generate some molecular graph. We cast the set of trajectories as a flow and convert the flow consistency equations into a learning objective, akin to the casting of the Bellman equations into Temporal Difference methods. We prove that any global minimum of the proposed objectives yields a policy which samples from the desired distribution, and demonstrate the improved performance and diversity of GFlowNet on a simple domain where there are many modes to the reward function, and on a molecule synthesis task.