Publications

A Remedy For Distributional Shifts Through Expected Domain Translation.
Jean-christophe Gagnon-audet
Soroosh Shahtalebi
Frank Rudzicz
Irina Rish
Machine learning models often fail to generalize to unseen domains due to the distributional shifts. A family of such shifts, “correlation… (see more) shifts,” is caused by spurious correlations in the data. It is studied under the overarching topic of “domain generalization.” In this work, we employ multi-modal translation networks to tackle the correlation shifts that appear when data is sampled out-of-distribution. Learning a generative model from training domains enables us to translate each training sample under the special characteristics of other possible domains. We show that by training a predictor solely on the generated samples, the spurious correlations in training domains average out, and the invariant features corresponding to true correlations emerge. Our proposed technique, Expected Domain Translation (EDT), is benchmarked on the Colored MNIST dataset and drastically improves the state-of-the-art classification accuracy by 38% with train-domain validation model selection.
2022-05-22
IEEE International Conference on Acoustics, Speech, and Signal Processing (published)
doi.org
Roboethics as a Design Challenge: Lessons Learned from the Roboethics to Design and Development Competition.
Jimin Rhim
Cheng Lin
Alexander Werner
Brandon J. DeHart
Vivian Qiang
Shalaleh Rismani
AJung Moon
How do we make concrete progress towards de-signing robots that can navigate ethically sensitive contexts? Almost two decades after the word… (see more) ‘roboethics’ was coined, translating interdisciplinary roboethics discussions into techni-cal design still remains a daunting task. This paper describes our first attempt at addressing these challenges through a roboethics-themed design competition. The design competition setting allowed us to (a) formulate ethical considerations as an engineering design task that anyone with basic programming skills can tackle; and (b) develop a prototype evaluation scheme that incorporates diverse normative perspectives of multiple stakeholders. The initial implementation of the competition was held online at the RO-MAN 2021 conference. The competition task involved programming a simulated mobile robot (TIAGo) that delivers items for individuals in the home environment, where many of these tasks involve ethically sensitive con-texts (e.g., an underage family member asks for an alcoholic drink). This paper outlines our experiences implementing the competition and the lessons we learned. We highlight design competitions as a promising mechanism to enable a new wave of roboethics research equipped with technical design solutions.
2022-05-22
2022 International Conference on Robotics and Automation (ICRA) (published)
doi.org
Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
Kuangqi Zhou
Kaixin Wang
Jiashi Feng
Jian Tang
Tingyang Xu
Xinchao Wang
How to accurately predict the properties of molecules is an essential problem in AI-driven drug discovery, which generally requires a large … (see more)amount of annotation for training deep learning models. Annotating molecules, however, is quite costly because it requires lab experiments conducted by experts. To reduce annotation cost, deep Active Learning (AL) methods are developed to select only the most representative and informative data for annotating. However, existing best deep AL methods are mostly developed for a single type of learning task (e.g., single-label classification), and hence may not perform well in molecular property prediction that involves various task types. In this paper, we propose a Task-type-generic active learning framework (termed Tyger) that is able to handle different types of learning tasks in a unified manner. The key is to learn a chemically-meaningful embedding space and perform active selection fully based on the embeddings, instead of relying on task-type-specific heuristics (e.g., class-wise prediction probability) as done in existing works. Specifically, for learning the embedding space, we instantiate a querying module that learns to translate molecule graphs into corresponding SMILES strings. Furthermore, to ensure that samples selected from the space are both representative and informative, we propose to shape the embedding space by two learning objectives, one based on domain knowledge and the other leveraging feedback from the task learner (i.e., model that performs the learning task at hand). We conduct extensive experiments on benchmark datasets of different task types. Experimental results show that Tyger consistently achieves high AL performance on molecular property prediction, outperforming baselines by a large margin. We also perform ablative experiments to verify the effectiveness of each component in Tyger.
2022-05-22
ArXiv (preprint)
doi.org
arxiv.org
Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
Dianbo Liu
Vedant Shah
Oussama Boussif
Cristian Meo
Anirudh Goyal
Tianmin Shu
Michael Curtis Mozer
Nicolas Heess
Yoshua Bengio
In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one a… (see more)nother. In this paper, we propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents’ collective performance. To ensure that this facilitator does not become a centralized controller, agents are incentivized to reduce their dependence on the messages it conveys, and the messages can only influence the selection of a policy from a fixed set, not instantaneous actions given the policy. We demonstrate the strength of this architecture over existing baselines on several cooperative MARL environments.
2022-05-20
ArXiv (preprint)
doi.org
arxiv.org
Bayesian Structure Learning with Generative Flow Networks
Tristan Deleu
Antonio Gois
Chris Emezue
Mansi Rankawat
Simon Lacoste-Julien
Stefan Bauer
Yoshua Bengio
In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) structure of Bayesian ne… (see more)tworks, from data. Defining such a distribution is very challenging, due to the combinatorially large sample space, and approximations based on MCMC are often required. Recently, a novel class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling of discrete and composite objects, such as graphs. In this work, we propose to use a GFlowNet as an alternative to MCMC for approximating the posterior distribution over the structure of Bayesian networks, given a dataset of observations. Generating a sample DAG from this approximate distribution is viewed as a sequential decision problem, where the graph is constructed one edge at a time, based on learned transition probabilities. Through evaluation on both simulated and real data, we show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs, and it compares favorably against other methods based on MCMC or variational inference.
2022-05-19
Conference on Uncertainty in Artificial Intelligence (poster)
doi.org
proceedings.mlr.press
Hardware Architecture for Guessing Random Additive Noise Decoding Markov Order (GRAND-MO)
Syed Mohsin Abbas
Marwan Jalaleddine
Warren J. Gross
2022-05-19
Journal of Signal Processing Systems (published)
doi.org
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
Akram Erraqabi
Marlos C. Machado
Mingde Zhao
Sainbayar Sukhbaatar
Alessandro Lazaric
Ludovic Denoyer
Yoshua Bengio
In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-agnostic setting, with applications ranging from… (see more) skill discovery to reward shaping. Recently, learning the Laplacian representation has been framed as the optimization of a temporally-contrastive objective to overcome its computational limitations in large (or continuous) state spaces. However, this approach requires uniform access to all states in the state space, overlooking the exploration problem that emerges during the representation learning process. In this work, we propose an alternative method that is able to recover, in a non-uniform-prior setting, the expressiveness and the desired properties of the Laplacian representation. We do so by combining the representation learning with a skill-based covering policy, which provides a better training distribution to extend and refine the representation. We also show that a simple augmentation of the representation objective with the learned temporal abstractions improves dynamics-awareness and helps exploration. We find that our method succeeds as an alternative to the Laplacian in the non-uniform setting and scales to challenging continuous control environments. Finally, even if our method is not optimized for skill discovery, the learned skills can successfully solve difficult continuous navigation tasks with sparse rewards, where standard skill discovery approaches are no so effective.
2022-05-19
Conference on Uncertainty in Artificial Intelligence (poster)
doi.org
proceedings.mlr.press
Universal antigen encoding of T cell activation from high-dimensional cytokine dynamics
Sooraj R. Achar
François X. P. Bourassa
Thomas J. Rademaker
Angela Lee
Taisuke Kondo
Emanuel Salazar-Cavazos
John S. Davies
Naomi Taylor
Paul François
Grégoire Altan-Bonnet
2022-05-19
Science (published)
doi.org
FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data
Mike He Zhu
Lena Nehale Ezzine
Dianbo Liu
Yoshua Bengio
2022-05-18
ArXiv (preprint)
doi.org
arxiv.org
IL-flOw: Imitation Learning from Observation using Normalizing Flows
Wei-Di Chang
Juan Higuera
Scott Fujimoto
David Meger
Gregory Dudek
2022-05-18
ArXiv (preprint)
doi.org
arxiv.org
Human brain anatomy reflects separable genetic and environmental components of socioeconomic status
Hyeokmoon Kweon
Gökhan Aydogan
Alain Dagher
Danilo Bzdok
Christian C. Ruff
Gideon Nave
Martha J. Farah
Philipp D. Koellinger
Socioeconomic status (SES) correlates with brain structure, a relation of interest given the long-observed relations of SES to cognitive abi… (see more)lities and health. Yet, major questions remain open, in particular, the pattern of causality that underlies this relation. In an unprecedently large study, here, we assess genetic and environmental contributions to SES differences in neuroanatomy. We first establish robust SES–gray matter relations across a number of brain regions, cortical and subcortical. These regional correlates are parsed into predominantly genetic factors and those potentially due to the environment. We show that genetic effects are stronger in some areas (prefrontal cortex, insula) than others. In areas showing less genetic effect (cerebellum, lateral temporal), environmental factors are likely to be influential. Our results imply a complex interplay of genetic and environmental factors that influence the SES-brain relation and may eventually provide insights relevant to policy.
2022-05-17
Science Advances (published)
doi.org
Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties
Courtney Paquette
Elliot Paquette
Ben Adlam
Jeffrey Pennington
2022-05-13
ArXiv (preprint)
arxiv.org
arxiv.org