Portrait of Yoshua Bengio

Yoshua Bengio

Core Academic Member

Canada CIFAR AI Chair

Full Professor, Université de Montréal

Research Topics

Causality

Computational Neuroscience

Deep Learning

Generative Models

Graph Neural Networks

Machine Learning Theory

Medical Machine Learning

Molecular Modeling

Natural Language Processing

Probabilistic Models

Reasoning

Recurrent Neural Networks

Reinforcement Learning

Representation Learning

Biography

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

For more information please contact Cassidy MacNeil, Senior Assistant and Operation Lead at cassidy.macneil@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

jamal.abouhaibeh@mila.quebec

Collaborating researcher - Cambridge University

Principal supervisor :

berkes.anais@mila.quebec

PhD - Université de Montréal

assouelr@mila.quebec

PhD - Université de Montréal

xiaoyin.chen@mila.quebec

Collaborating researcher - KAIST

sanghyeok.choi@mila.quebec

Aniket Didolkar

PhD - Université de Montréal

aniket.didolkar@mila.quebec

PhD - Université de Montréal

Co-supervisor :

Guillaume Lajoie

eric.elmoznino@mila.quebec

PhD - Université de Montréal

lena-nehale.ezzine@mila.quebec

Jean-Pierre Falet

PhD - Université de Montréal

jean-pierre.falet@mila.quebec

PhD

pietro.greiner@mila.quebec

PhD - Université de Montréal

mohsin.hasan@mila.quebec

PhD - Université de Montréal

moksh.jain@mila.quebec

Thomas Jiralerspong

PhD - Université de Montréal

Principal supervisor :

Guillaume Lajoie

thomas.jiralerspong@mila.quebec

Younesse Kaddar

Collaborating Alumni - Université de Montréal

younesse.kaddar@mila.quebec

Postdoctorate - Université de Montréal

Principal supervisor :

Alex Hernández-García

hyeonah.kim@mila.quebec

Collaborating researcher - Université de Montréal

minsu.kim@mila.quebec

Collaborating researcher - KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

jeongjae.lee@mila.quebec

Collaborating researcher - s.o.

liusong299@gmail.com

Collaborating researcher

liucheng@mila.quebec

Cristian Dragos Manta

PhD - Université de Montréal

Co-supervisor :

cristian-dragos.manta@mila.quebec

PhD - Université de Montréal

Principal supervisor :

Guillaume Lajoie

mittalsa@mila.quebec

Independent visiting researcher - Université de Montréal

nguyenph@mila.quebec

Collaborating researcher - Ying Wu Coll of Computing

ali.parviz@mila.quebec

Collaborating researcher - University of Waterloo

Principal supervisor :

elena.podina@mila.quebec

Jarrid Rector-Brooks

PhD - Université de Montréal

jarrid.rector-brooks@mila.quebec

Postdoctorate - Université de Montréal

danyal.rehman@mila.quebec

Postdoctorate - Université de Montréal

oliver.richardson@mila.quebec

Camille Rochefort-Boulanger

PhD - Université de Montréal

Principal supervisor :

rochefoc@mila.quebec

Postdoctorate - Université de Montréal

Co-supervisor :

Alex Hernández-García

divya.sharma@mila.quebec

Mélisande Astrid Crystal Teng

Collaborating Alumni - Université de Montréal

Co-supervisor :

Hugo Larochelle

tengmeli@mila.quebec

Collaborating Alumni - Université de Montréal

alexander.tong@mila.quebec

Collaborating researcher - University of Cambridge

oszkar.urban@mila.quebec

Collaborating Alumni - Université de Montréal

Co-supervisor :

donna.vakalis@mila.quebec

Siddarth Venkatraman

PhD - Université de Montréal

Principal supervisor :

siddarth.venkatraman@mila.quebec

Collaborating researcher

joseph.viviano2@mila.quebec

Esmeralda Whitammer

Collaborating researcher - Université de Montréal

esmeralda.whitammer@mila.quebec

Collaborating Alumni

omar.younis@mila.quebec

Collaborating researcher - Université de Montréal

taeyoung.yun@mila.quebec

PhD - McGill University

Principal supervisor :

Mathieu Blanchette

xi.zhang@mila.quebec

PhD - Université de Montréal

tianyu.zhang@mila.quebec

Collaborating Alumni - McGill University

Principal supervisor :

zhaoming@mila.quebec

Blog Posts

Generic thumbnail for Mila Blog articles.

February 22, 2024

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

by

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Read the article

Scaling in the service of reasoning & model-based ML

April 4, 2023

Scaling in the Service of Reasoning & Model-Based ML

by

Read the article

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

March 23, 2022

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

by

Jake P. Taylor-King

Read the article

Generative Flow Networks

March 15, 2022

Generative Flow Networks

by

Read the article

Publications

SPE: Symmetrical Prompt Enhancement for Factual Knowledge Retrieval

James M. Crawford

Matthew L. Ginsberg

Jacob Devlin

Ming-Wei Chang

Kenton Lee

Alex Graves

Abdel rahman Mohamed

Adi Haviv

Jonathan Berant

Amir Globerson

Chloe Kiddon

Pedro M. Domingos

Brian Lester

Rami Al-rfou'

Noah Constant. 2021

Weizhe Yuan … (see 6 more)

Jinlan Fu

Zhengbao Jiang

Xiao Liu

Yanan Zheng

Zhengxiao Du

Ming Ding

Pretrained language models (PLMs) have 001 been shown to accumulate factual knowledge 002 from their unsupervised pretraining proce-003 dure… (see more)s (Petroni et al., 2019). Prompting is an 004 effective way to query such knowledge from 005 PLMs. Recently, continuous prompt methods 006 have been shown to have a larger potential 007 than discrete prompt methods in generating ef-008 fective queries (Liu et al., 2021a). However, 009 these methods do not consider symmetry of 010 the task. In this work, we propose Symmet-011 rical Prompt Enhancement (SPE), a continu-012 ous prompt-based method for fact retrieval that 013 leverages the symmetry of the task. Our results 014 on LAMA, a popular fact retrieval dataset, 015 show signiﬁcant improvement of SPE over pre-016 vious prompt methods

2020-12-31

(published)

www.semanticscholar.org

Tackling Situated Multi-Modal Task-Oriented Dialogs with a Single Transformer Model

−. i.eUT

R´ejean Ducharme

P Vincent

Morgan Kaufmann

Yen-Chun Chen

Linjie Li

Licheng Yu

Matthew Henderson

Blaise Thomson

Ehsan Hosseini-Asl

Bryan McCann

Chien-Sheng Wu

Samuel Humeau

Kurt Shuster

Marie-Anne Lachaux

The Situated Interactive Multi-Modal Conver-001 sations (SIMMC) 2.0 aims to create virtual 002 shopping assistants that can accept complex 0… (see more)03 multi-modal inputs, i.e. visual appearances of 004 objects and user utterances. It consists of four 005 subtasks, multi-modal disambiguation (MM-006 Disamb), multi-modal coreference resolution 007 (MM-Coref), multi-modal dialog state tracking 008 (MM-DST), and response retrieval and genera-009 tion. While many task-oriented dialog systems 010 usually tackle each subtask separately, we pro-011 pose a jointly learned encoder-decoder that per-012 forms all four subtasks at once for efficiency. 013 Moreover, we handle the multi-modality of the 014 challenge by representing visual objects as spe-015 cial tokens whose joint embedding is learned 016 via auxiliary tasks. This approach won the MM-017 Coref and response retrieval subtasks and nom-018 inated runner-up for the remaining subtasks 019 using a single unified model. In particular, 020 our model achieved 81.5% MRR, 71.2% R@1, 021 95.0% R@5, 98.2% R@10, and 1.9 mean rank 022 in response retrieval task, setting a high bar for 023 the state-of-the-art result in the SIMMC 2.0 024 track of the Dialog Systems Technology Chal-025 lenge 10 (DSTC10). 026

2020-12-31

(published)

www.semanticscholar.org

Test Sample Accuracy Scales with Training Sample Density in Neural Networks

Andrea Vedaldi

Balaji Lakshminarayanan

Intuitively, one would expect accuracy of a trained neural network's prediction on test samples to correlate with how densely the samples ar… (see more)e surrounded by seen training samples in representation space. We find that a bound on empirical training error smoothed across linear activation regions scales inversely with training sample density in representation space. Empirically, we verify this bound is a strong predictor of the inaccuracy of the network's prediction on test samples. For unseen test sets, including those with out-of-distribution samples, ranking test samples by their local region's error bound and discarding samples with the highest bounds raises prediction accuracy by up to 20% in absolute terms for image classification datasets, on average over thresholds.

2020-12-31

arXiv.org (preprint)

Unifying Likelihood-free Inference with Black-box Sequence Design and Beyond

Aaron Courville

2020-12-31

arXiv.org (preprint)

dblp.uni-trier.de

Using Artificial Intelligence to Visualize the Impacts of Climate Change

Alexandra Luccioni

Public awareness and concern about climate change often do not match the magnitude of its threat to humans and our environment. One reason f… (see more)or this disagreement is that it is difficult to mentally simulate the effects of a process as complex as climate change and to have a concrete representation of the impact that our individual actions will have on our own future, especially if the consequences are long term and abstract. To overcome these challenges, we propose to use cutting-edge artificial intelligence (AI) approaches to develop an interactive personalized visualization tool, the AI climate impact visualizer. It will allow a user to enter an address—be it their house, their school, or their workplace—-and it will provide them with an AI-imagined possible visualization of the future of this location in 2050 following the detrimental effects of climate change such as floods, storms, and wildfires. This image will be accompanied by accessible information regarding the science behind climate change, i.e., why extreme weather events are becoming more frequent and what kinds of changes are happening on a local and global scale.

2020-12-31

IEEE Computer Graphics and Applications (published)

What Makes Machine Reading Comprehension Questions Difﬁcult? Investigating Variation in Passage Sources and Question Types

Susan Bartlett

Grzegorz Kondrak

Max Bartolo

Alastair Roberts

Johannes Welbl

Steven Bird

Ewan Klein

Edward Loper

Samuel R. Bowman

George Dahl. 2021

What

Chao Pang

Junyuan Shang

Jiaxiang Liu

Xuyi Chen

Yanbin Zhao

Yuxiang Lu

Weixin Liu

Zhi-901 hua Wu

Weibao Gong … (see 21 more)

Jianzhong Liang

Zhizhou Shang

Peng Sun

Ouyang Xuan

Dianhai

Houwen Tian

Hua Wu

Haifeng Wang

Adam Trischler

Tong Wang

Xingdi Yuan

Justin Har-908

Alessandro Sordoni

Philip Bachman

Adina Williams

Nikita Nangia

Zhilin Yang

Peng Qi

ing. In

For a natural language understanding bench-001 mark to be useful in research, it has to con-002 sist of examples that are diverse and difﬁ… (see more)-003 cult enough to discriminate among current and 004 near-future state-of-the-art systems. However, 005 we do not yet know how best to select pas-006 sages to collect a variety of challenging exam-007 ples. In this study, we crowdsource multiple-008 choice reading comprehension questions for 009 passages taken from seven qualitatively dis-010 tinct sources, analyzing what attributes of pas-011 sages contribute to the difﬁculty and question 012 types of the collected examples. To our sur-013 prise, we ﬁnd that passage source, length, and 014 readability measures do not signiﬁcantly affect 015 question difﬁculty. Through our manual anno-016 tation of seven reasoning types, we observe 017 several trends between passage sources and 018 reasoning types, e.g., logical reasoning is more 019 often required in questions written for techni-020 cal passages. These results suggest that when 021 creating a new benchmark dataset, selecting a 022 diverse set of passages can help ensure a di-023 verse range of question types, but that passage 024 difﬁculty need not be a priority. 025

2020-12-31

(published)

www.semanticscholar.org

Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya

Benjamin Akera

Bibek Aryal

Tenzing Chogyal Sherpa

Finu Shresta

Anthony Ortiz

Juan Lavista Ferres

M. Matin

2020-12-08

ArXiv (preprint)

Hybrid Models for Learning to Branch

Prateek Gupta

Maxime Gasse

Elias B. Khalil

M. Pawan Kumar

Andrea Lodi

A recent Graph Neural Network (GNN) approach for learning to branch has been shown to successfully reduce the running time of branch-and-bou… (see more)nd algorithms for Mixed Integer Linear Programming (MILP). While the GNN relies on a GPU for inference, MILP solvers are purely CPU-based. This severely limits its application as many practitioners may not have access to high-end GPUs. In this work, we ask two key questions. First, in a more realistic setting where only a CPU is available, is the GNN model still competitive? Second, can we devise an alternate computationally inexpensive model that retains the predictive power of the GNN architecture? We answer the first question in the negative, and address the second question by proposing a new hybrid architecture for efficient branching on CPU machines. The proposed architecture combines the expressive power of GNNs with computationally inexpensive multi-layer perceptrons (MLP) for branching. We evaluate our methods on four classes of MILP problems, and show that they lead to up to 26% reduction in solver running time compared to state-of-the-art methods without a GPU, while extrapolating to harder problems than it was trained on. The code for this project is publicly available at https://github.com/pg2455/Hybrid-learn2branch.

2020-12-06

Conference on Neural Information Processing Systems (Accept (poster))

Untangling tradeoffs between recurrence and self-attention in neural networks

Bhargav Kanuparthi

Guillaume Lajoie

2020-12-06

Advances in Neural Information Processing Systems (Accept (poster))

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling

Tong Che

Jascha Sohl-Dickstein

Hugo Larochelle

Yuan Cao

We show that the sum of the implicit generator log-density …

2020-12-06

Conference on Neural Information Processing Systems (Accept (poster))

Establishing an evaluation metric to quantify climate change image realism

Sharon Zhou

Alexandra Luccioni

Gautier Cosne

Michael S. Bernstein

2020-11-30

Informatica: Journal of Applied Machines Electrical Electronics Computer Science and Communication Systems (published)

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design

Cheng-Hao Liu

Maksym Korablyov

Stanisław Jastrzębski

Paweł Włodarczyk-Pruszyński

Marwin H. S. Segler

De novo molecule generation often results in chemically unfeasible molecules. A natural idea to mitigate this problem is to bias the search … (see more)process towards more easily synthesizable molecules using a proxy for synthetic accessibility. However, using currently available proxies still results in highly unrealistic compounds. We investigate the feasibility of training deep graph neural networks to approximate the outputs of a retrosynthesis planning software, and their use to bias the search process. We evaluate our method on a benchmark involving searching for drug-like molecules with antibiotic properties. Compared to enumerating over five million existing molecules from the ZINC database, our approach finds molecules predicted to be more likely to be antibiotics while maintaining good drug-like properties and being easily synthesizable. Importantly, our deep neural network can successfully filter out hard to synthesize molecules while achieving a

2020-11-24

arXiv (preprint)