Portrait of Yoshua Bengio

Yoshua Bengio

Core Academic Member

Canada CIFAR AI Chair

Full Professor, Université de Montréal, Department of Computer Science and Operations Research Department

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

Shahana Chatterjee

Collaborating researcher - N/A

Principal supervisor :

shahana.chatterjee@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

Research Intern - 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

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 - Université de Montréal

tianyu.zhang@mila.quebec

PhD - McGill University

Principal supervisor :

Mathieu Blanchette

xi.zhang@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

Path-filtering in path-integral simulations of open quantum systems using GFlowNets

Jeremy Lackman-Mincoff

Nikolay Malkin

An important class of methods for modeling dynamics in open quantum systems is based on the well-known influence functional (IF) approach to… (see more) solving path-integral equations of motion. Within this paradigm, path-filtering schemes based on the removal of IF elements that fall below a certain threshold aim to reduce the effort needed to calculate and store the influence functional, making very challenging simulations possible. A filtering protocol of this type is considered acceptable as long as the simulation remains mathematically stable. This, however, does not guarantee that the approximated dynamics preserve the physics of the simulated process. In this paper, we explore the possibility of training Generative Flow Networks (GFlowNets) to produce filtering protocols while optimizing for mathematical stability and for physical accuracy. Trained using the trajectory balance objective, the model produces sets of paths to be added to a truncated initial set; it is rewarded if the combined set of paths gives rise to solutions in which the trace of the density matrix is conserved, the populations remain real, and the dynamics approach the exact reference. Using a simple two-level system coupled to a dissipative reservoir, we perform proof-of-concept simulations and demonstrate the elegant and surprising filtering solutions proposed by the GFlowNet.

2024-10-07

Journal of Chemical Physics (published)

Were RNNs All We Needed?

Frederick Tung

Mohamed Osama Ahmed

Hossein Hajimirsadeghi

The introduction of Transformers in 2017 reshaped the landscape of deep learning. Originally proposed for sequence modelling, Transformers h… (see more)ave since achieved widespread success across various domains. However, the scalability limitations of Transformers - particularly with respect to sequence length - have sparked renewed interest in novel recurrent models that are parallelizable during training, offer comparable performance, and scale more effectively. In this work, we revisit sequence modelling from a historical perspective, focusing on Recurrent Neural Networks (RNNs), which dominated the field for two decades before the rise of Transformers. Specifically, we examine LSTMs (1997) and GRUs (2014). We demonstrate that by simplifying these models, we can derive minimal versions (minLSTMs and minGRUs) that (1) use fewer parameters than their traditional counterparts, (2) are fully parallelizable during training, and (3) achieve surprisingly competitive performance on a range of tasks, rivalling recent models including Transformers.

2024-10-01

ArXiv (preprint)

Were RNNs All We Needed?

Frederick Tung

Mohamed Osama Ahmed

Hossein Hajimirsadeghi

2024-10-01

ArXiv (preprint)

MAP: Model Merging with Amortized Pareto Front Using Limited Computation

Li Li

Zhiqi Bu

Huan He

Yonghui Wu

Jiang Bian

Yong Chen

2024-09-30

NeurIPS.cc/2024/Workshop/Federated_Learning (oral)

Al content detection in the emerging information ecosystem: new obligations for media and tech companies

Alistair Knott

Dino Pedreschi

Toshiya Jitsuzumi

Susan Leavy

David Eyers

Tapabrata Chakraborti

Andrew Trotman

Sundar Sundareswaran

Ricardo Baeza-Yates

Przemyslaw Biecek

Adrian Weller

Paul D. Teal

Subhadip Basu

Mehmet Haklidir

Virginia Morini

Stuart Russell

2024-09-20

Ethics and Information Technology (published)

A high-throughput phenotypic screen combined with an ultra-large-scale deep learning-based virtual screening reveals novel scaffolds of antibacterial compounds

Gabriele Scalia

Steven T. Rutherford

Ziqing Lu

Kerry R. Buchholz

Nicholas Skelton

Kangway Chuang

Nathaniel Diamant

Jan-Christian Hütter

Jerome-Maxim Luescher

Anh Miu

Jeff Blaney

Leo Gendelev

Elizabeth Skippington

Greg Zynda

Nia Dickson

Michał Koziarski

Aviv Regev

Man-Wah Tan

Tommaso Biancalani

The proliferation of multi-drug-resistant bacteria underscores an urgent need for novel antibiotics. Traditional discovery methods face chal… (see more)lenges due to limited chemical diversity, high costs, and difficulties in identifying structurally novel compounds. Here, we explore the integration of small molecule high-throughput screening with a deep learning-based virtual screening approach to uncover new antibacterial compounds. Leveraging a diverse library of nearly 2 million small molecules, we conducted comprehensive phenotypic screening against a sensitized Escherichia coli strain that, at a low hit rate, yielded thousands of hits. We trained a deep learning model, GNEprop, to predict antibacterial activity, ensuring robustness through out-of-distribution generalization techniques. Virtual screening of over 1.4 billion compounds identified potential candidates, of which 82 exhibited antibacterial activity, illustrating a 90X improved hit rate over the high-throughput screening experiment GNEprop was trained on. Importantly, a significant portion of these newly identified compounds exhibited high dissimilarity to known antibiotics, indicating promising avenues for further exploration in antibiotic discovery.

2024-09-13

bioRxiv (preprint)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Usman Anwar

Abulhair Saparov

Javier Rando

Daniel Paleka

Miles Turpin

Peter Hase

Ekdeep Singh Lubana

Erik Jenner

Stephen Casper

Oliver Sourbut

Benjamin L. Edelman

Zhaowei Zhang

Mario Günther

Anton Korinek

Jose Hernandez-Orallo

Lewis Hammond

Eric Bigelow

Alexander Pan

Lauro Langosco

Tomasz Korbak … (see 22 more)

Heidi Zhang

Ruiqi Zhong

Seán Ó hÉigeartaigh

Gabriel Recchia

Giulio Corsi

Markus Anderljung

Lilian Edwards

Aleksandar Petrov

Christian Schroeder de Witt

Sumeet Ramesh Motwani

Samuel Albanie

Danqi Chen

Philip H.S. Torr

Jakob Foerster

Florian Tramèr

He He

Atoosa Kasirzadeh

Yejin Choi

David Krueger

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are o… (see more)rganized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose

2024-09-01

TMLR (accepted)

Zero-Shot Object-Centric Representation Learning

Aniket Rajiv Didolkar

Andrii Zadaianchuk

Michael Curtis Mozer

Georg Martius

Maximilian Seitzer

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities… (see more). Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we study current object-centric methods through the lens of zero-shot generalization by introducing a benchmark comprising eight different synthetic and real-world datasets. We analyze the factors influencing zero-shot performance and find that training on diverse real-world images improves transferability to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.

2024-08-16

ArXiv (preprint)

Multi-Fidelity Active Learning with GFlowNets

Alex Hernández-García

Moksh J. Jain

Cheng-Hao Liu

In the last decades, the capacity to generate large amounts of data in science and engineering applications has been growing steadily. Meanw… (see more)hile, the progress in machine learning has turned it into a suitable tool to process and utilise the available data. Nonetheless, many relevant scientific and engineering problems present challenges where current machine learning methods cannot yet efficiently leverage the available data and resources. For example, in scientific discovery, we are often faced with the problem of exploring very large, high-dimensional spaces, where querying a high fidelity, black-box objective function is very expensive. Progress in machine learning methods that can efficiently tackle such problems would help accelerate currently crucial areas such as drug and materials discovery. In this paper, we propose the use of GFlowNets for multi-fidelity active learning, where multiple approximations of the black-box function are available at lower fidelity and cost. GFlowNets are recently proposed methods for amortised probabilistic inference that have proven efficient for exploring large, high-dimensional spaces and can hence be practical in the multi-fidelity setting too. Here, we describe our algorithm for multi-fidelity active learning with GFlowNets and evaluate its performance in both well-studied synthetic tasks and practically relevant applications of molecular discovery. Our results show that multi-fidelity active learning with GFlowNets can efficiently leverage the availability of multiple oracles with different costs and fidelities to accelerate scientific discovery and engineering design.

2024-07-24

TMLR (accepted)

Improving Gradient-Guided Nested Sampling for Posterior Inference

Nikolay Malkin

Will Handley

Laurence Perreault-Levasseur

We present a performant, general-purpose gradient-guided nested sampling algorithm, …

2024-07-22

International Conference on Machine Learning (Accept (Poster))

proceedings.mlr.press

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities

Tara Akhound-Sadegh

Jarrid Rector-Brooks

Avishek Joey Bose

Cheng-Hao Liu

Siamak Ravanbakhsh

Nikolay Malkin

Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-… (see more)body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient -- and no data samples -- to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is simulation-free, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant

2024-07-22

International Conference on Machine Learning (Accept (Poster))

proceedings.mlr.press

Learning to Scale Logits for Temperature-Conditional GFlowNets

Joohwan Ko

Woo Chang Kim

Jinkyoo Park

Emmanuel Bengio

GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, tempera… (see more)ture-conditional GFlowNets can introduce temperature-based controllability for exploration and exploitation. We propose \textit{Logit-scaling GFlowNets} (Logit-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed approaches introduced numerical challenges in the deep network training, since different temperatures may give rise to very different gradient profiles as well as magnitudes of the policy's logits. We find that the challenge is greatly reduced if a learned function of the temperature is used to scale the policy's logits directly. Also, using Logit-GFN, GFlowNets can be improved by having better generalization capabilities in offline learning and mode discovery capabilities in online learning, which is empirically verified in various biological and chemical tasks. Our code is available at https://github.com/dbsxodud-11/logit-gfn

2024-07-22

International Conference on Machine Learning (Accept (Poster))

proceedings.mlr.press