Publications

Trade-off Between Accuracy and Fairness of Data-driven Building and Indoor Environment Models: A Comparative Study of Pre-processing Methods
Ying Sun
Fariborz Haghighat
Benjamin C. M. Fung
2021-09-30
Energy (published)
doi.org
Weighted automata are compact and actively learnable
Artem Kaznatcheev
Prakash Panangaden
2021-09-30
Information Processing Letters (published)
doi.org
arxiv.org
Graph Neural Networks in Natural Language Processing
Bang Liu
Lingfei Wu
Natural language processing (NLP) and understanding aim to read from unformatted text to accomplish different tasks. While word embeddings l… (see more)earned by deep neural networks are widely used, the underlying linguistic and semantic structures of text pieces cannot be fully exploited in these representations. Graph is a natural way to capture the connections between different text pieces, such as entities, sentences, and documents. To overcome the limits in vector space models, researchers combine deep learning models with graph-structured representations for various tasks in NLP and text mining. Such combinations help to make full use of both the structural information in text and the representation learning ability of deep neural networks. In this chapter, we introduce the various graph representations that are extensively used in NLP, and show how different NLP tasks can be tackled from a graph perspective. We summarize recent research works on graph-based NLP, and discuss two case studies related to graph-based text clustering, matching, and multihop machine reading comprehension in detail. Finally, we provide a synthesis about the important open problems of this subfield.
2021-09-29
Deep Learning on Graphs (published)
doi.org
Data-driven approaches for genetic characterization of SARS-CoV-2 lineages
Fatima Mostefai
Isabel Gamache
Jessie Huang
Arnaud N’Guessan
Justin Pelletier
Ahmad Pesaranghader
David Hamelin
Carmen Lia Murall
Raphaël Poujol
Jean-Christophe Grenier
Martin Smith
Etienne Caron
Morgan Craig
Jesse Shapiro
Guy Wolf
Smita Krishnaswamy
Julie G. Hussin
The genome of the Severe Acute Respiratory Syndrome coronavirus 2 (SARS-CoV-2), the pathogen that causes coronavirus disease 2019 (COVID-19)… (see more), has been sequenced at an unprecedented scale, leading to a tremendous amount of viral genome sequencing data. To understand the evolution of this virus in humans, and to assist in tracing infection pathways and designing preventive strategies, we present a set of computational tools that span phylogenomics, population genetics and machine learning approaches. To illustrate the utility of this toolbox, we detail an in depth analysis of the genetic diversity of SARS-CoV-2 in first year of the COVID-19 pandemic, using 329,854 high-quality consensus sequences published in the GISAID database during the pre-vaccination phase. We demonstrate that, compared to standard phylogenetic approaches, haplotype networks can be computed efficiently on much larger datasets, enabling real-time analyses. Furthermore, time series change of Tajima’s D provides a powerful metric of population expansion. Unsupervised learning techniques further highlight key steps in variant detection and facilitate the study of the role of this genomic variation in the context of SARS-CoV-2 infection, with Multiscale PHATE methodology identifying fine-scale structure in the SARS-CoV-2 genetic data that underlies the emergence of key lineages. The computational framework presented here is useful for real-time genomic surveillance of SARS-CoV-2 and could be applied to any pathogen that threatens the health of worldwide populations of humans and other organisms.
2021-09-28
BioRxiv (preprint)
doi.org
Latent Attention Augmentation for Robust Autonomous Driving Policies
Ran Cheng
Christopher Agia
Florian Shkurti
David Meger
Gregory Dudek
Model-free reinforcement learning has become a viable approach for vision-based robot control. However, sample complexity and adaptability t… (see more)o domain shifts remain persistent challenges when operating in high-dimensional observation spaces (images, LiDAR), such as those that are involved in autonomous driving. In this paper, we propose a flexible framework by which a policy’s observations are augmented with robust attention representations in the latent space to guide the agent’s attention during training. Our method encodes local and global descriptors of the augmented state representations into a compact latent vector, and scene dynamics are approximated by a recurrent network that processes the latent vectors in sequence. We outline two approaches for constructing attention maps; a supervised pipeline leveraging semantic segmentation networks, and an unsupervised pipeline relying only on classical image processing techniques. We conduct our experiments in simulation and test the learned policy against varying seasonal effects and weather conditions. Our design decisions are supported in a series of ablation studies. The results demonstrate that our state augmentation method both improves learning efficiency and encourages robust domain adaptation when compared to common end-to-end frameworks and methods that learn directly from intermediate representations.
2021-09-26
IEEE/RJS International Conference on Intelligent Robots and Systems (published)
doi.org
Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain
Stefan Wapnick
Travis Manderson
David Meger
Gregory Dudek
We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in vis… (see more)ual navigation tasks. Our method learns to place visual attention at locations in latent image space which follow trajectories caused by vehicle control actions to enhance predictive accuracy during planning. The attention model is jointly optimized by the task-specific loss and an additional trajectory-constraint loss, allowing adaptability yet encouraging a regularized structure for improved generalization and reliability. Importantly, visual attention is applied in latent feature map space instead of raw image space to promote efficient planning. We validated our model in visual navigation tasks of planning low turbulence, collision-free trajectories in off-road settings and hill climbing with locking differentials in the presence of slippery terrain. Experiments involved randomized procedural generated simulation and real-world environments. We found our method improved generalization and learning efficiency when compared to no-attention and self-attention alternatives.
2021-09-26
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (published)
doi.org
arxiv.org
Population modeling with machine learning can enhance measures of mental health
Kamalaker Dadi
Gael Varoquaux
Josselin Houenou
Danilo Bzdok
Bertrand Thirion
Denis Engemann
We applied machine learning on more than 10.000 individuals from the general population to define empirical approximations of health-related… (see more) psychological measures that do not require human judgment.We found that machine-learning enriched the given psychological measures via approximation from brain and sociodemographic data: Resulting proxy measures related as well or better to real-world health behavior than the original measures.Model comparisons showed that sociodemographic information contributed most to characterizing psychological traits beyond aging.
2021-09-23
bioRxiv (preprint)
doi.org
Author Correction: Open-access quantitative MRI data of the spinal cord and reproducibility across participants, sites and manufacturers
Julien Cohen-Adad
Eva Alonso‐Ortiz
Mihael Abramovic
Carina Arneitz
Nicole Atcheson
Laura Barlow
Robert L. Barry
Markus Barth
Marco Battiston
Christian Büchel
Matthew D. Budde
Virginie Callot
Anna J. E. Combes
Benjamin De Leener
Maxime Descoteaux
Paulo Loureiro de Sousa
Marek Dostál
Julien Doyon
Adam Dvorak
Falk Eippert … (see 71 more)
Karla R. Epperson
Kevin S. Epperson
Patrick Freund
Jürgen Finsterbusch
Alexandru Foias
Michela Fratini
Issei Fukunaga
Claudia A. M. Gandini Wheeler-Kingshott
Giancarlo Germani
Guillaume Gilbert
Federico Giove
Charley Gros
Francesco Grussu
Akifumi Hagiwara
Pierre-Gilles Henry
Tomáš Horák
Masaaki Hori
James Joers
Kouhei Kamiya
Haleh Karbasforoushan
Miloš Keřkovský
Ali Khatibi
Joo‐Won Kim
Nawal Kinany
Hagen H. Kitzler
Shannon Kolind
Yazhuo Kong
Petr Kudlička
Paul Kuntke
Nyoman D. Kurniawan
Slawomir Kusmia
René Labounek
Maria Marcella Laganà
Cornelia Laule
Christine S. Law
Christophe Lenglet
Tobias Leutritz
Yaou Liu
Sara Llufriu
Sean Mackey
Eloy Martinez-Heras
Loan Mattera
Igor Nestrasil
Kristin P. O’Grady
Nico Papinutto
Daniel Papp
Deborah Pareto
Todd B. Parrish
Anna Pichiecchio
Ferran Prados
Àlex Rovira
Marc J. Ruitenberg
Rebecca S. Samson
Giovanni Savini
Maryam Seif
Alan C. Seifert
Alex K. Smith
Seth A. Smith
Zachary A. Smith
Elisabeth Solana
Y. Suzuki
George Tackley
Alexandra Tinnermann
Jan Valosek
Dimitri Van De Ville
Marios C. Yiannakas
Kenneth A. Weber
Nikolaus Weiskopf
Richard G. Wise
Patrik O. Wyss
Junqian Xu
2021-09-22
Scientific Data (published)
doi.org
Cohort Bias Adaptation in Aggregated Datasets for Lesion Segmentation
Brennan Nichyporuk
Jillian Cardinell
Justin Szeto
Raghav Mehta
Sotirios Tsaftaris
Douglas L. Arnold
Tal Arbel
Many automatic machine learning models developed for focal pathology (e.g. lesions, tumours) detection and segmentation perform well, but do… (see more) not generalize as well to new patient cohorts, impeding their widespread adoption into real clinical contexts. One strategy to create a more diverse, generalizable training set is to naively pool datasets from different cohorts. Surprisingly, training on this \it{big data} does not necessarily increase, and may even reduce, overall performance and model generalizability, due to the existence of cohort biases that affect label distributions. In this paper, we propose a generalized affine conditioning framework to learn and account for cohort biases across multi-source datasets, which we call Source-Conditioned Instance Normalization (SCIN). Through extensive experimentation on three different, large scale, multi-scanner, multi-centre Multiple Sclerosis (MS) clinical trial MRI datasets, we show that our cohort bias adaptation method (1) improves performance of the network on pooled datasets relative to naively pooling datasets and (2) can quickly adapt to a new cohort by fine-tuning the instance normalization parameters, thus learning the new cohort bias with only 10 labelled samples.
2021-09-20
Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health (published)
doi.org
arxiv.org
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
Eric Larsen
Sébastien Lachapelle
Yoshua Bengio
Emma Frejinger
Simon Lacoste-Julien
Andrea Lodi
This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a method… (see more)ology to quickly predict tactical solutions to a given operational problem. In this context, the tactical solution is less detailed than the operational one but it has to be computed in very short time and under imperfect information. The problem is of importance in various applications where tactical and operational planning problems are interrelated and information about the operational problem is revealed over time. This is for instance the case in certain capacity planning and demand management systems. We formulate the problem as a two-stage optimal prediction stochastic program whose solution we predict with a supervised machine learning algorithm. The training data set consists of a large number of deterministic (second stage) problems generated by controlled probabilistic sampling. The labels are computed based on solutions to the deterministic problems (solved independently and offline) employing appropriate aggregation and subselection methods to address uncertainty. Results on our motivating application in load planning for rail transportation show that deep learning algorithms produce highly accurate predictions in very short computing time (milliseconds or less). The prediction accuracy is comparable to solutions computed by sample average approximation of the stochastic program.
2021-09-20
INFORMS Journal on Computing (unknown)
doi.org
arxiv.org
Stacked Hourglass Network with a Multi-level Attention Mechanism: Where to Look for Intervertebral Disc Labeling
Reza Azad
Lucas Rouhier
Julien Cohen-Adad
Labeling vertebral discs from MRI scans is important for the proper diagnosis of spinal related diseases, including multiple sclerosis, amyo… (see more)trophic lateral sclerosis, degenerative cervical myelopathy and cancer. Automatic labeling of the vertebral discs in MRI data is a difficult task because of the similarity between discs and bone area, the variability in the geometry of the spine and surrounding tissues across individuals, and the variability across scans (manufacturers, pulse sequence, image contrast, resolution and artefacts). In previous studies, vertebral disc labeling is often done after a disc detection step and mostly fails when the localization algorithm misses discs or has false positive detection. In this work, we aim to mitigate this problem by reformulating the semantic vertebral disc labeling using the pose estimation technique. To do so, we propose a stacked hourglass network with multi-level attention mechanism to jointly learn intervertebral disc position and their skeleton structure. The proposed deep learning model takes into account the strength of semantic segmentation and pose estimation technique to handle the missing area and false positive detection. To further improve the performance of the proposed method, we propose a skeleton-based search space to reduce false positive detection. The proposed method evaluated on spine generic public multi-center dataset and demonstrated better performance comparing to previous work, on both T1w and T2w contrasts. The method is implemented in ivadomed (https://ivadomed.org).
2021-09-20
Machine Learning in Medical Imaging (published)
doi.org
arxiv.org
An Autonomous Probing System for Collecting Measurements at Depth from Small Surface Vehicles
Yuying Huang
Yiming Yao
Johanna Hansen
Jeremy Mallette
Sandeep Manjanna
Gregory Dudek
David Meger
This paper presents the portable autonomous probing system (APS), a low-cost robotic design for collecting water quality measurements at tar… (see more)geted depths from an autonomous surface vehicle (ASV). This system fills an important but often overlooked niche in marine sampling by enabling mobile sensor observations throughout the near-surface water column without the need for advanced underwater equipment. We present a probe delivery mechanism built with commercially available components and describe the corresponding open-source simulator and winch controller. Finally, we demonstrate the system in a field deployment and discuss design trade-offs and areas for future improvement. Project details are available on https://johannah.github.io/publication/sample-at-depth our website
2021-09-19
OCEANS 2021: San Diego – Porto (published)
doi.org
arxiv.org