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

Founder and Scientific Advisor, Leadership Team

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.

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

GFlowNets and Variational Inference

This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically us… (see more)ed to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs. We demonstrate that, in certain cases, VI algorithms are equivalent to special cases of GFlowNets in the sense of equality of expected gradients of their learning objectives. We then point out the differences between the two families and show how these differences emerge experimentally. Notably, GFlowNets, which borrow ideas from reinforcement learning, are more amenable than VI to off-policy training without the cost of high gradient variance induced by importance sampling. We argue that this property of GFlowNets can provide advantages for capturing diversity in multimodal target distributions.

2023-01-31

ICLR.cc/2023/Conference (poster)

Latent Bottlenecked Attentive Neural Processes

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on… (see more) a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong performance but require quadratic computation with respect to the number of context datapoints, significantly limiting its scalability. Conversely, existing sub-quadratic NP variants perform significantly worse than that of TNPs. Tackling this issue, we propose Latent Bottlenecked Attentive Neural Processes (LBANPs), a new computationally efficient sub-quadratic NP variant, that has a querying computational complexity independent of the number of context datapoints. The model encodes the context dataset into a constant number of latent vectors on which self-attention is performed. When making predictions, the model retrieves higher-order information from the context dataset via multiple cross-attention mechanisms on the latent vectors. We empirically show that LBANPs achieve results competitive with the state-of-the-art on meta-regression, image completion, and contextual multi-armed bandits. We demonstrate that LBANPs can trade-off the computational cost and performance according to the number of latent vectors. Finally, we show LBANPs can scale beyond existing attention-based NP variants to larger dataset settings.

2023-01-31

ICLR.cc/2023/Conference (poster)

Latent State Marginalization as a Low-Cost Approach for Improving Exploration

Aaron Courville

Qinqing Zheng

Ricky T. Q. Chen

While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- … (see more)is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity. In this work, we propose the adoption of latent variable policies within the MaxEnt framework, which we show can provably approximate any policy distribution, and additionally, naturally emerges under the use of world models with a latent belief state. We discuss why latent variable policies are difficult to train, how naive approaches can fail, then subsequently introduce a series of improvements centered around low-cost marginalization of the latent state, allowing us to make full use of the latent state at minimal additional cost. We instantiate our method under the actor-critic framework, marginalizing both the actor and critic. The resulting algorithm, referred to as Stochastic Marginal Actor-Critic (SMAC), is simple yet effective. We experimentally validate our method on continuous control tasks, showing that effective marginalization can lead to better exploration and more robust training. Our implementation is open sourced at https://github.com/zdhNarsil/Stochastic-Marginal-Actor-Critic.

2023-01-31

ICLR.cc/2023/Conference (poster)

Predictive Inference with Feature Conformal Prediction

Jiaye Teng

Chuan Wen

Yang Gao

Yang Yuan

Conformal prediction is a distribution-free technique for establishing valid prediction intervals. Although conventionally people conduct co… (see more)nformal prediction in the output space, this is not the only possibility. In this paper, we propose feature conformal prediction, which extends the scope of conformal prediction to semantic feature spaces by leveraging the inductive bias of deep representation learning. From a theoretical perspective, we demonstrate that feature conformal prediction provably outperforms regular conformal prediction under mild assumptions. Our approach could be combined with not only vanilla conformal prediction, but also other adaptive conformal prediction methods. Apart from experiments on existing predictive inference benchmarks, we also demonstrate the state-of-the-art performance of the proposed methods on large-scale tasks such as ImageNet classification and Cityscapes image segmentation.The code is available at https://github.com/AlvinWen428/FeatureCP.

2023-01-31

ICLR.cc/2023/Conference (poster)

Robust and Controllable Object-Centric Learning through Energy-based Models

Tong Che

Boris Ivanovic

Marco Pavone

Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations in… (see more)to discrete objects allows us to build a grounded abstract representation and identify the compositional structure of the world. Accordingly, it is a crucial step for machine learning models to be capable of inferring objects and their properties from visual scenes without explicit supervision. However, existing works on object-centric representation learning either rely on tailor-made neural network modules or strong probabilistic assumptions in the underlying generative and inference processes. In this work, we present \ours, a conceptually simple and general approach to learning object-centric representations through an energy-based model. By forming a permutation-invariant energy function using vanilla attention blocks readily available in Transformers, we can infer object-centric latent variables via gradient-based MCMC methods where permutation equivariance is automatically guaranteed. We show that \ours can be easily integrated into existing architectures and can effectively extract high-quality object-centric representations, leading to better segmentation accuracy and competitive downstream task performance. Further, empirical evaluations show that \ours's learned representations are robust against distribution shift. Finally, we demonstrate the effectiveness of \ours in systematic compositional generalization, by re-composing learned energy functions for novel scene generation and manipulation.

2023-01-31

ICLR.cc/2023/Conference (poster)

Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning

Dianbo Liu

Oussama Boussif

Tianmin Shu

Michael Mozer

Nicolas Heess

In cooperative multi-agent reinforcement learning, a team of agents works together to achieve a common goal. Different environments or tasks… (see more) may require varying degrees of coordination among agents in order to achieve the goal in an optimal way. The nature of coordination will depend on the properties of the environment -- its spatial layout, distribution of obstacles, dynamics, etc. We term this variation of properties within an environment as heterogeneity. Existing literature has not sufficiently addressed the fact that different environments may have different levels of heterogeneity. We formalize the notions of coordination level and heterogeneity level of an environment and present HECOGrid, a suite of multi-agent RL environments that facilitates empirical evaluation of different MARL approaches across different levels of coordination and environmental heterogeneity by providing a quantitative control over coordination and heterogeneity levels of the environment. Further, we propose a Centralized Training Decentralized Execution learning approach called Stateful Active Facilitator (SAF) that enables agents to work efficiently in high-coordination and high-heterogeneity environments through a differentiable and shared knowledge source used during training and dynamic selection from a shared pool of policies. We evaluate SAF and compare its performance against baselines IPPO and MAPPO on HECOGrid. Our results show that SAF consistently outperforms the baselines across different tasks and different heterogeneity and coordination levels. We release the code for HECOGrid as well as all our experiments.

2023-01-31

ICLR.cc/2023/Conference (poster)

Leveraging the Third Dimension in Contrastive Learning

Sumukh K Aithal

Michael Curtis Mozer

Self-Supervised Learning (SSL) methods operate on unlabeled data to learn robust representations useful for downstream tasks. Most SSL metho… (see more)ds rely on augmentations obtained by transforming the 2D image pixel map. These augmentations ignore the fact that biological vision takes place in an immersive three-dimensional, temporally contiguous environment, and that low-level biological vision relies heavily on depth cues. Using a signal provided by a pretrained state-of-the-art monocular RGB-to-depth model (the \emph{Depth Prediction Transformer}, Ranftl et al., 2021), we explore two distinct approaches to incorporating depth signals into the SSL framework. First, we evaluate contrastive learning using an RGB+depth input representation. Second, we use the depth signal to generate novel views from slightly different camera positions, thereby producing a 3D augmentation for contrastive learning. We evaluate these two approaches on three different SSL methods -- BYOL, SimSiam, and SwAV -- using ImageNette (10 class subset of ImageNet), ImageNet-100 and ImageNet-1k datasets. We find that both approaches to incorporating depth signals improve the robustness and generalization of the baseline SSL methods, though the first approach (with depth-channel concatenation) is superior. For instance, BYOL with the additional depth channel leads to an increase in downstream classification accuracy from 85.3\% to 88.0\% on ImageNette and 84.1\% to 87.0\% on ImageNet-C.

2023-01-26

ArXiv (preprint)

Regeneration Learning: A Learning Paradigm for Data Generation

Xu Tan

Tao Qin

Jiang Bian

Tie-Yan Liu

2023-01-20

ArXiv (preprint)

Scalable Neural Network Algorithms for High Dimensional Data

Mukesh Soni

Marwan Ali Shnan

2023-01-14

Mesopotamian Journal of Big Data (published)

Benchmarking Graph Neural Networks

Vijay Prakash Dwivedi

Chaitanya K. Joshi

Thomas Laurent

Anh Tuan Luu

Xavier Bresson

2022-12-31

J. Mach. Learn. Res. (published)

Conditional Flow Matching: Simulation-Free Dynamic Optimal Transport

Guillaume Huguet

Yanlei Zhang

Jarrid Rector-Brooks

2022-12-31

arXiv.org (preprint)

Constant Memory Attentive Neural Processes

Frederick Tung

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

2022-12-31

arXiv.org (preprint)