Publications

Weakly Supervised Representation Learning with Sparse Perturbations
Kartik Ahuja
Jason Hartford
Yoshua Bengio
The theory of representation learning aims to build methods that provably invert the data generating process with minimal domain knowledge o… (see more)r any source of supervision. Most prior approaches require strong distributional assumptions on the latent variables and weak supervision (auxiliary information such as timestamps) to provide provable identification guarantees. In this work, we show that if one has weak supervision from observations generated by sparse perturbations of the latent variables--e.g. images in a reinforcement learning environment where actions move individual sprites--identification is achievable under unknown continuous latent distributions. We show that if the perturbations are applied only on mutually exclusive blocks of latents, we identify the latents up to those blocks. We also show that if these perturbation blocks overlap, we identify latents up to the smallest blocks shared across perturbations. Consequently, if there are blocks that intersect in one latent variable only, then such latents are identified up to permutation and scaling. We propose a natural estimation procedure based on this theory and illustrate it on low-dimensional synthetic and image-based experiments.
2021-12-31
Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (published)
doi.org
openreview.net
What does it mean to be an AI Ethicist: An ontology of existing roles
Shalaleh Rismani
AJung Moon
With the increasing adoption of Artificial Intelligence systems (AIS) in various application and the growing efforts to regulate such system… (see more)s, a new set of occupations has emerged in the industry. This new set of roles take different titles and hold varying responsibilities. However, the individuals in these roles are tasked with interpreting and operationalizing best practices for developing ethical and safe AI systems. We will broadly refer to this new set of occupations as AI ethicists and recognize that they often hold a specific role in the intersection of technology development, business needs, and societal implications. In this work, we examine what it means to be an AI ethicist in the industry and propose an ontology of existing roles under this broad title along with their required competencies. We create this ontology by examining the job postings for such roles over the past two years and conduct expert interviews with fourteen individuals who currently hold such a role in the industry. The proposed ontology will inform executives and leaders who are looking to build responsible AI teams and provide educators the necessary information for creating new learning objectives and curriculum.
2021-12-31
arXiv.org (preprint)
doi.org
Importance of Empirical Sample Complexity Analysis for Offline Reinforcement Learning
Samin Yeasar Arnob
Riashat Islam
Doina Precup
2021-12-30
ArXiv (preprint)
arxiv.org
arxiv.org
Single-Shot Pruning for Offline Reinforcement Learning
Samin Yeasar Arnob
Riyasat Ohib
Sergey Plis
Doina Precup
2021-12-30
ArXiv (preprint)
arxiv.org
arxiv.org
Heterogeneous Crowd Simulation Using Parametric Reinforcement Learning.
Kaidong Hu
M. Brandon Haworth
Glen Berseth
Vladimir Pavlovic
Petros Faloutsos
Mubbasir Kapadia
Agent-based synthetic crowd simulation affords the cost-effective large-scale simulation and animation of interacting digital humans. Model-… (see more)based approaches have successfully generated a plethora of simulators with a variety of foundations. However, prior approaches have been based on statically defined models predicated on simplifying assumptions, limited video-based datasets, or homogeneous policies. Recent works have applied reinforcement learning to learn policies for navigation. However, these approaches may learn static homogeneous rules, are typically limited in their generalization to trained scenarios, and limited in their usability in synthetic crowd domains. In this article, we present a multi-agent reinforcement learning-based approach that learns a parametric predictive collision avoidance and steering policy. We show that training over a parameter space produces a flexible model across crowd configurations. That is, our goal-conditioned approach learns a parametric policy that affords heterogeneous synthetic crowds. We propose a model-free approach without centralization of internal agent information, control signals, or agent communication. The model is extensively evaluated. The results show policy generalization across unseen scenarios, agent parameters, and out-of-distribution parameterizations. The learned model has comparable computational performance to traditional methods. Qualitatively the model produces both expected (laminar flow, shuffling, bottleneck) and unexpected (side-stepping) emergent qualitative behaviours, and quantitatively the approach is performant across measures of movement quality.
2021-12-28
IEEE Transactions on Visualization and Computer Graphics (published)
doi.org
Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models
Enoch Amoatey Tetteh
Joseph D Viviano
Yoshua Bengio
David M. Krueger
Joseph Paul Cohen
Learning models that generalize under different distribution shifts in medical imaging has been a long-standing research challenge. There ha… (see more)ve been several proposals for efficient and robust visual representation learning among vision research practitioners, especially in the sensitive and critical biomedical domain. In this paper, we propose an idea for out-of-distribution generalization of chest X-ray pathologies that uses a simple balanced batch sampling technique. We observed that balanced sampling between the multiple training datasets improves the performance over baseline models trained without balancing.
2021-12-26
ArXiv (preprint)
arxiv.org
arxiv.org
Fall 2021 Resurgence and COVID-19 Seroprevalence in Canada: Modelling waning and boosting COVID-19 immunity in Canada, A Canadian Immunization Research Network Study
David W. Dick
Lauren Childs
Zhilan Feng
Jing Li
Gergely Röst
David L Buckeridge
Nick H. Ogden
Jane Heffernan
2021-12-22
Vaccines (published)
doi.org
Generative Models of Brain Dynamics -- A review
Mahta Ramezanian Panahi
Germán Abrevaya
Jean-christophe Gagnon-audet
Vikram Voleti
Irina Rish
Guillaume Dumas
The principled design and discovery of biologically- and physically-informed models of neuronal dynamics has been advancing since the mid-tw… (see more)entieth century. Recent developments in artificial intelligence (AI) have accelerated this progress. This review article gives a high-level overview of the approaches across different scales of organization and levels of abstraction. The studies covered in this paper include fundamental models in computational neuroscience, nonlinear dynamics, data-driven methods, as well as emergent practices. While not all of these models span the intersection of neuroscience, AI, and system dynamics, all of them do or can work in tandem as generative models, which, as we argue, provide superior properties for the analysis of neuroscientific data. We discuss the limitations and unique dynamical traits of brain data and the complementary need for hypothesis- and data-driven modeling. By way of conclusion, we present several hybrid generative models from recent literature in scientific machine learning, which can be efficiently deployed to yield interpretable models of neural dynamics.
2021-12-21
ArXiv (preprint)
arxiv.org
arxiv.org
Recovery after stroke: the severely impaired are a distinct group
Anna K. Bonkhoff
Thomas Hope
Danilo Bzdok
Adrian G. Guggisberg
Rachel L. Hawe
Sean P. Dukelow
François Chollet
David J. Lin
Christian Grefkes
Howard Bowman
Our work highlights the benefit of simultaneously modelling recovery of severely-to-non-severely impaired patients and demonstrates both sha… (see more)red and distinct recovery patterns. Our findings provide evidence that the severe/non-severe subdivision in recovery modelling is not an artefact of previous confounds. The presented out-of-sample prediction performance may serve as benchmark to evaluate promising biomarkers of stroke recovery.
2021-12-21
Journal of Neurology Neurosurgery & Psychiatry (published)
doi.org
The Myelin-Weighted Connectome in Parkinson's Disease
Tommy Boshkovski
Julien Cohen-Adad
Bratislav Misic
Isabelle Arnulf
Jean-Christophe Corvol
Marie Vidailhet
Stéphane Lehéricy
Nikola Stikov
Matteo Mancini
Even though Parkinson's disease (PD) is typically viewed as largely affecting gray matter, there is growing evidence that there are also str… (see more)uctural changes in the white matter. Traditional connectomics methods that study PD may not be specific to underlying microstructural changes, such as myelin loss. The primary objective of this study is to investigate the PD‐induced changes in myelin content in the connections emerging from the basal ganglia and the brainstem. For the weighting of the connectome, we used the longitudinal relaxation rate as a biologically grounded myelin‐sensitive metric. We computed the myelin‐weighted connectome in 35 healthy control subjects and 81 patients with PD. We used partial least squares to highlight the differences between patients with PD and healthy control subjects. Then, a ring analysis was performed on selected brainstem and subcortical regions to evaluate each node's potential role as an epicenter for disease propagation. Then, we used behavioral partial least squares to relate the myelin alterations with clinical scores. Most connections (~80%) emerging from the basal ganglia showed a reduced myelin content. The connections emerging from potential epicentral nodes (substantia nigra, nucleus basalis of Meynert, amygdala, hippocampus, and midbrain) showed significant decrease in the longitudinal relaxation rate (P  0.05). This effect was not seen for the medulla and the pons. The myelin‐weighted connectome was able to identify alteration of the m
2021-12-21
Movement Disorders (unknown)
doi.org
A Cost-Efficient Metadata Scheme for High-Performance Deduplication Systems
Yuxuan Mo
Yu Hua
Pengfei Li
Qin Cao
Xue Liu
Data deduplication has been widely used in backup systems to eliminate redundant data, which speeds up the backup process and reduces the st… (see more)orage overhead. Deduplication packs multiple chunks into a large, fixed-size container as a storage unit to maintain the locality and achieve efficient compression. We observe that the traditional containers have low filling ratios due to a large amount of metadata generated by small files. Unfilled containers require more space to store a backup, which decreases the storage efficiency and reduces restore performance. In order to address this problem, we propose a Metadata region Adaptive Container Structure, called MACS. MACS maintains a tag to record the length of metadata region in the container. The boundary between meta-data region and data region is dynamically decided to ensure the maximum space efficiency of the containers. Moreover, we propose a container metadata length-based indexing and cache replacement strategy to allow MACS to be practical in data backup systems. We demonstrate the advantages of MACS with three real world backup datasets. MACS achieves over 95% average container filling ratio, which is significantly higher than existing designs. MACS further achieves better restore performance than the traditional container structure. When combined with existing rewriting method, MACS achieves an efficient trade-off between deduplication ratio and restore performance.
2021-12-19
2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys) (published)
doi.org
Faults in deep reinforcement learning programs: a taxonomy and a detection approach
Amin Nikanjam
Mohammad Mehdi Morovati
Foutse Khomh
Houssem Ben Braiek
2021-12-19
Automated Software Engineering (published)
doi.org
arxiv.org