Publications

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… (see more)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.
2021-02-21
ArXiv (preprint)
arxiv.org
arxiv.org
Model-Invariant State Abstractions for Model-Based Reinforcement Learning
Manan Tomar
Amy Zhang
Roberto Calandra
Matthew E. Taylor
Joelle Pineau
Accuracy and generalization of dynamics models is key to the success of model-based reinforcement learning (MBRL). As the complexity of task… (see more)s increases, so does the sample inefficiency of learning accurate dynamics models. However, many complex tasks also exhibit sparsity in the dynamics, i.e., actions have only a local effect on the system dynamics. In this paper, we exploit this property with a causal invariance perspective in the single-task setting, introducing a new type of state abstraction called \textit{model-invariance}. Unlike previous forms of state abstractions, a model-invariance state abstraction leverages causal sparsity over state variables. This allows for compositional generalization to unseen states, something that non-factored forms of state abstractions cannot do. We prove that an optimal policy can be learned over this model-invariance state abstraction and show improved generalization in a simple toy domain. Next, we propose a practical method to approximately learn a model-invariant representation for complex domains and validate our approach by showing improved modelling performance over standard maximum likelihood approaches on challenging tasks, such as the MuJoCo-based Humanoid. Finally, within the MBRL setting we show strong performance gains with respect to sample efficiency across a host of other continuous control tasks.
2021-02-18
ArXiv (preprint)
openreview.net
openreview.net
Concurrent prescriptions for opioids and benzodiazepines and risk of opioid overdose: protocol for a retrospective cohort study using linked administrative data
Erin Y Liu
Robyn Tamblyn
Kristian B Filion
David L Buckeridge
2021-02-17
BMJ Open (published)
doi.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
2021-02-17
Frontiers in Neuroscience (published)
doi.org
arxiv.org
Smart Futures Based Resource Trading and Coalition Formation for Real-Time Mobile Data Processing
Ruitao Chen
Xianbin Wang
Xue Liu
Collaboration among mobile devices (MDs) is becoming more important, as it could augment computing capacity at the network edge through peer… (see more)-to-peer service provisioning, and directly enhance real-time computational performance in smart Internet-of-Things applications. As an important aspect of collaboration mechanism, conventional resource trading (RT) among MDs relies on an onsite interaction process, i.e., price negotiation between service providers and requesters, which, however, inevitably incurs excessive latency and degrades RT efficiency. To overcome this challenge, this article adopts the concept of futures contract (FC) used in financial market, and proposes a smart futures for low latency RT. This new technique enables MDs to form trading coalitions and negotiate multilateral forward contracts applied to a collaboration term in the future. To maximize the benefits of self-interested MDs, the negotiation process of FC is modelled as a coalition formation game comprised of three components executed in an iterative manner, i.e., futures resource allocation, revenue sharing and payment allocation, and distributed decision-making of individual MD. Additionally, a FC enforcement scheme is implemented to efficiently manage the onsite resource sharing via recording resource balances of different task-types and MDs. Simulation results prove the superiority of smart futures in RT latency reduction and trading fairness provisioning.
2021-02-17
IEEE Transactions on Services Computing (published)
doi.org
Bridging the Gap Between Adversarial Robustness and Optimization Bias
Fartash Faghri
Cristina Vasconcelos
David J Fleet
Fabian Pedregosa
Nicolas Roux
2021-02-16
ArXiv (preprint)
arxiv.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… (see more)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.
2021-02-06
ArXiv (preprint)
arxiv.org
arxiv.org
Enabling Secure Trustworthiness Assessment and Privacy Protection in Integrating Data for Trading Person-Specific Information
Rashid Hussain Khokhar
Farkhund Iqbal
Benjamin C. M. Fung
Jamal Bentahar
With increasing adoption of cloud services in the e-market, collaboration between stakeholders is easier than ever. Consumer stakeholders de… (see more)mand data from various sources to analyze trends and improve customer services. Data-as-a-service enables data integration to serve the demands of data consumers. However, the data must be of good quality and trustful for accurate analysis and effective decision making. In addition, a data custodian or provider must conform to privacy policies to avoid potential penalties for privacy breaches. To address these challenges, we propose a twofold solution: 1) we present the first information entropy-based trust computation algorithm, IEB_Trust, that allows a semitrusted arbitrator to detect the covert behavior of a dishonest data provider and chooses the qualified providers for a data mashup and 2) we incorporate the Vickrey–Clarke–Groves (VCG) auction mechanism for the valuation of data providers’ attributes into the data mashup process. Experiments on real-life data demonstrate the robustness of our approach in restricting dishonest providers from participation in the data mashup and improving the efficiency in comparison to provenance-based approaches. Furthermore, we derive the monetary shares for the chosen providers from their information utility and trust scores over the differentially private release of the integrated dataset under their joint privacy requirements.
2021-01-31
IEEE transactions on engineering management (published)
doi.org
Task dependent deep LDA pruning of neural networks
Qing Tian
Tal Arbel
James J. Clark
2021-01-31
Computer Vision and Image Understanding (published)
doi.org
The neural correlates of ongoing conscious thought
Jonathan Smallwood
Adam Turnbull
Hao-Ting Wang
Nerissa S.P. Ho
Giulia L. Poerio
Theodoros Karapanagiotidis
Delali Konu
Brontë Mckeown
Meichao Zhang
Charlotte Murphy
Deniz Vatansever
Danilo Bzdok
Mahiko Konishi
Robert Leech
Paul Seli
Jonathan W. Schooler
Boris C Bernhardt
Daniel S. Margulies
Elizabeth Jefferies
2021-01-31
iScience (published)
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
Trained CNNs more similar to auditory fMRI activity than untrainedNo evidence of a shared representational hierarchy for acoustic featuresAl… (see more)l ROIs were most similar to the first fully-connected layerCNN performance on speech recognition task positively associated with fmri similarity
2021-01-26
bioRxiv (preprint)
doi.org
Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference
Sahand Rezaei-Shoshtari
David Meger
Inna Sharf
Utilization of latent space to capture a lower-dimensional representation of a complex dynamics model is explored in this work. The targeted… (see more) application is of a robotic manipulator executing a complex environment interaction task, in particular, cutting a wooden object. We train two flavours of Variational Autoencoders---standard and Vector-Quantised---to learn the latent space which is then used to infer certain properties of the cutting operation, such as whether the robot is cutting or not, as well as, material and geometry of the object being cut. The two VAE models are evaluated with reconstruction, prediction and a combined reconstruction/prediction decoders. The results demonstrate the expressiveness of the latent space for robotic interaction inference and the competitive prediction performance against recurrent neural networks.
2021-01-23
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (published)
doi.org
arxiv.org