Publications

Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
Tong Che
Xiaofeng Liu
Site Li
Yubin Ge
Ruixiang Zhang
Caiming Xiong
Yoshua Bengio
AI Safety is a major concern in many deep learning applications such as autonomous driving. Given a trained deep learning model, an importan… (voir plus)t natural problem is how to reliably verify the model's prediction. In this paper, we propose a novel framework --- deep verifier networks (DVN) to detect unreliable inputs or predictions of deep discriminative models, using separately trained deep generative models. Our proposed model is based on conditional variational auto-encoders with disentanglement constraints to separate the label information from the latent representation. We give both intuitive and theoretical justifications for the model. Our verifier network is trained independently with the prediction model, which eliminates the need of retraining the verifier network for a new model. We test the verifier network on both out-of-distribution detection and adversarial example detection problems, as well as anomaly detection problems in structured prediction tasks such as image caption generation. We achieve state-of-the-art results in all of these problems.
2021-05-18
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
Object-Centric Image Generation from Layouts
Tristan Sylvain
Pengchuan Zhang
Yoshua Bengio
(Rex) Devon Hjelm
Shikhar Sharma
2021-05-18
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies
Giulia Zarpellon
Jason Jo
Andrea Lodi
Yoshua Bengio
Branch and Bound (B&B) is the exact tree search method typically used to solve Mixed-Integer Linear Programming problems (MILPs). Learning b… (voir plus)ranching policies for MILP has become an active research area, with most works proposing to imitate the strong branching rule and specialize it to distinct classes of problems. We aim instead at learning a policy that generalizes across heterogeneous MILPs: our main hypothesis is that parameterizing the state of the B&B search tree can aid this type of generalization. We propose a novel imitation learning framework, and introduce new input features and architectures to represent branching. Experiments on MILP benchmark instances clearly show the advantages of incorporating an explicit parameterization of the state of the search tree to modulate the branching decisions, in terms of both higher accuracy and smaller B&B trees. The resulting policies significantly outperform the current state-of-the-art method for "learning to branch" by effectively allowing generalization to generic unseen instances.
2021-05-18
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
Visual Concept Reasoning Networks
Taesup Kim
Sungwoong Kim
Yoshua Bengio
2021-05-18
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
How does hemispheric specialization contribute to human-defining cognition?
Gesa Hartwigsen
Yoshua Bengio
Danilo Bzdok
2021-05-11
Neuron (publié)
doi.org
Toward Causal Representation Learning
Bernhard Schölkopf
Francesco Locatello
Stefan Bauer
Nan Rosemary Ke
Nal Kalchbrenner
Anirudh Goyal
Yoshua Bengio
The two fields of machine learning and graphical causality arose and are developed separately. However, there is, now, cross-pollination and… (voir plus) increasing interest in both fields to benefit from the advances of the other. In this article, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, that is, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.
2021-05-01
Proceedings of the IEEE (publié)
doi.org
A Two-Stream Continual Learning System With Variational Domain-Agnostic Feature Replay
Qicheng Lao
Xiang Jiang
Mohammad Havaei
Yoshua Bengio
Learning in nonstationary environments is one of the biggest challenges in machine learning. Nonstationarity can be caused by either task dr… (voir plus)ift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data. This article aims to tackle this challenge with a modularized two-stream continual learning (CL) system, where the model is required to learn new tasks from a support stream and adapted to new domains in the query stream while maintaining previously learned knowledge. To deal with both drifts within and across the two streams, we propose a variational domain-agnostic feature replay-based approach that decouples the system into three modules: an inference module that filters the input data from the two streams into domain-agnostic representations, a generative module that facilitates the high-level knowledge transfer, and a solver module that applies the filtered and transferable knowledge to solve the queries. We demonstrate the effectiveness of our proposed approach in addressing the two fundamental scenarios and complex scenarios in two-stream CL.
2021-03-03
IEEE Transactions on Neural Networks and Learning Systems (publié)
doi.org
Towards Causal Representation Learning
Bernhard Schölkopf
Francesco Locatello
Stefan Bauer
Nan Rosemary Ke
Nal Kalchbrenner
Anirudh Goyal
Yoshua Bengio
The two fields of machine learning and graphical causality arose and developed separately. However, there is now cross-pollination and incre… (voir plus)asing interest in both fields to benefit from the advances of the other. In the present paper, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.
2021-02-22
ArXiv (prépublication)
arxiv.org
arxiv.org
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias
Axel Laborieux
Maxence Ernoult
Benjamin Scellier
Yoshua Bengio
Julie Grollier
Damien Querlioz
2021-02-18
Frontiers in Neuroscience (publié)
doi.org
arxiv.org
Structured Sparsity Inducing Adaptive Optimizers for Deep Learning
Tristan Deleu
Yoshua Bengio
The parameters of a neural network are naturally organized in groups, some of which might not contribute to its overall performance. To prun… (voir plus)e out unimportant groups of parameters, we can include some non-differentiable penalty to the objective function, and minimize it using proximal gradient methods. In this paper, we derive the weighted proximal operator, which is a necessary component of these proximal methods, of two structured sparsity inducing penalties. Moreover, they can be approximated efficiently with a numerical solver, and despite this approximation, we prove that existing convergence guarantees are preserved when these operators are integrated as part of a generic adaptive proximal method. Finally, we show that this adaptive method, together with the weighted proximal operators derived here, is indeed capable of finding solutions with structure in their sparsity patterns, on representative examples from computer vision and natural language processing.
2021-02-07
ArXiv (prépublication)
arxiv.org
arxiv.org
Using Artificial Intelligence to Visualize the Impacts of Climate Change
Alexandra Luccioni
Victor Schmidt
Vahe Vardanyan
Yoshua Bengio
T. Rhyne
Public awareness and concern about climate change often do not match the magnitude of its threat to humans and our environment. One reason f… (voir plus)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.
2021-02-01
IEEE Computer Graphics and Applications (publié)
doi.org
Training neural networks to recognize speech increased their correspondence to the human auditory pathway but did not yield a shared hierarchy of acoustic features
Jessica A.F. Thompson
Yoshua Bengio
Elia Formisano
Marc Schönwiesner
The correspondence between the activity of artificial neurons in convolutional neural networks (CNNs) trained to recognize objects in images… (voir plus) and neural activity collected throughout the primate visual system has been well documented. Shallower layers of CNNs are typically more similar to early visual areas and deeper layers tend to be more similar to later visual areas, providing evidence for a shared representational hierarchy. This phenomenon has not been thoroughly studied in the auditory domain. Here, we compared the representations of CNNs trained to recognize speech (triphone recognition) to 7-Tesla fMRI activity collected throughout the human auditory pathway, including subcortical and cortical regions, while participants listened to speech. We found no evidence for a shared representational hierarchy of acoustic speech features. Instead, all auditory regions of interest were most similar to a single layer of the CNNs: the first fully-connected layer. This layer sits at the boundary between the relatively task-general intermediate layers and the highly task-specific final layers. This suggests that alternative architectural designs and/or training objectives may be needed to achieve fine-grained layer-wise correspondence with the human auditory pathway. Highlights Trained CNNs more similar to auditory fMRI activity than untrained No evidence of a shared representational hierarchy for acoustic features All ROIs were most similar to the first fully-connected layer CNN performance on speech recognition task positively associated with fmri similarity
2021-01-27
bioRxiv (prépublication)
doi.org