Publications

arxiv.org

Inferring global-scale temporal latent topics from news reports to predict public health interventions for COVID-19

Zhi Wen

Guido Powell

Imane Chafi

David Buckeridge

Y. K. Li

Yue Li

2022-02-01

Patterns (publié)

Exploring social inequalities in healthcare trajectories following diagnosis of diabetes: a state sequence analysis of linked survey and administrative data

Rachel Marie Mckay

Laurence Letarte

Alain Gillian Lucie David Manon Catherine Anaïs Benoit A Vanasse Bartlett Blais Buckeridge Choinière Hudon

Alain Vanasse

Gillian M. Bartlett

Lucie Blais

David Buckeridge

Manon. Choinière

Catherine. Hudon

Anaïs Lacasse

Benoit Lamarche

Alexandre Lebel

Amélie Quesnel-Vallée

Pasquale Roberge

Valérie Émond

Marie-Pascale Pomey

Mike Benigeri

Anne-Marie Cloutier

Marc Dorais

Josiane Courteau … (voir 15 de plus)

Mireille Courteau

Stéphanie Plante

Pierre Cambon

Annie Giguère

Isabelle Nogueira Leroux

Danielle St-Laurent

Denis Roy

Jaime Borja

A. Néron

Geneviève Landry

J. Éthier

Roxanne Dault

Marc-Antoine Côté-Marcil

Pier Tremblay

Sonia Quirion

2022-01-31

BMC Health Services Research (published)

Exploring social inequalities in healthcare trajectories following diagnosis of diabetes: a state sequence analysis of linked survey and administrative data

Rachel McKay

Laurence Letarte

Alain Gillian Lucie David Manon Catherine Anaïs Benoit Alexandre Amélie Pasquale Valérie Marie-Pascale Mike Anne-Marie Marc Josiane Mireille Stéphanie Pierre Annie Isabelle Danielle Denis Jaime André Geneviève Jean-François Roxanne Marc-Antoine Pier Sonia Vanasse

Alain Gillian Lucie David Manon Catherine Anaïs Benoit A Vanasse Bartlett Blais Buckeridge Choinière Hudon

Alain Vanasse

Gillian Bartlett

Lucie Blais

David Buckeridge

Manon Choinière

Catherine Hudon

Anaïs Lacasse

Benoit Lamarche

Alexandre Lebel

Amélie Quesnel-Vallée

Pasquale Roberge

Valérie Émond

Marie-Pascale Pomey

Mike Benigeri

Anne-Marie Cloutier

Marc Dorais … (voir 16 de plus)

Josiane Courteau

Mireille Courteau

Stéphanie Plante

Pierre Cambon

Annie Giguère

Isabelle Leroux

Danielle St-Laurent

Denis Roy

Jaime Borja

André Néron

Geneviève Landry

Jean-François Ethier

Roxanne Dault

Marc-Antoine Côté-Marcil

Pier Tremblay

Sonia Quirion

2022-01-31

BMC Health Services Research (publié)

Memory-Aware Functional IR for Higher-Level Synthesis of Accelerators

Christof Schlaak

Tzung-Han Juang

Christophe Dubach

2022-01-31

ACM Transactions on Architecture and Code Optimization (publié)

Memory-Aware Functional IR for Higher-Level Synthesis of Accelerators

Christof Schlaak

Tzung-Han Juang

Christophe Dubach

Specialized accelerators deliver orders of a magnitude of higher performance than general-purpose processors. The ever-changing nature of mo… (voir plus)dern workloads is pushing the adoption of Field Programmable Gate Arrays (FPGAs) as the substrate of choice. However, FPGAs are hard to program directly using Hardware Description Languages (HDLs). Even modern high-level HDLs, e.g., Spatial and Chisel, still require hardware expertise. This article adopts functional programming concepts to provide a hardware-agnostic higher-level programming abstraction. During synthesis, these abstractions are mechanically lowered into a functional Intermediate Representation (IR) that defines a specific hardware design point. This novel IR expresses different forms of parallelism and standard memory features such as asynchronous off-chip memories or synchronous on-chip buffers. Exposing such features at the IR level is essential for achieving high performance. The viability of this approach is demonstrated on two stencil computations and by exploring the optimization space of matrix-matrix multiplication. Starting from a high-level representation for these algorithms, our compiler produces low-level VHSIC Hardware Description Language (VHDL) code automatically. Several design points are evaluated on an Intel Arria 10 FPGA, demonstrating the ability of the IR to exploit different hardware features. This article also shows that the designs produced are competitive with highly tuned OpenCL implementations and outperform hardware-agnostic OpenCL code.

2022-01-31

ACM Transactions on Architecture and Code Optimization (TACO) (published)

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

Victor Schmidt

Alexandra Luccioni

Mélisande Teng

Tianyu Zhang

Alexia Reynaud

Sunand Raghupathi

Gautier Cosne

Adrien Juraver

Vahe Vardanyan

Alex Hernandez-Garcia

Climate change is a major threat to humanity, and the actions required to prevent its catastrophic consequences include changes in both poli… (voir plus)cy-making and individual behaviour. However, taking action requires understanding the effects of climate change, even though they may seem abstract and distant. Projecting the potential consequences of extreme climate events such as flooding in familiar places can help make the abstract impacts of climate change more concrete and encourage action. As part of a larger initiative to build a website that projects extreme climate events onto user-chosen photos, we present our solution to simulate photo-realistic floods on authentic images. To address this complex task in the absence of suitable training data, we propose ClimateGAN, a model that leverages both simulated and real data for unsupervised domain adaptation and conditional image generation. In this paper, we describe the details of our framework, thoroughly evaluate components of our architecture and demonstrate that our model is capable of robustly generating photo-realistic flooding.

2022-01-28

ICLR.cc/2022/Conference (poster)

Continuous-Time Meta-Learning with Forward Mode Differentiation

Tristan Deleu

David Kanaa

Leo Feng

Giancarlo Kerg

Guillaume Lajoie

Pierre-Luc Bacon

Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learni… (voir plus)ng (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specifically, representations of the inputs are meta-learned such that a task-specific linear classifier is obtained as a solution of an ordinary differential equation (ODE). Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous, as opposed to a fixed and discrete number of gradient steps. As a consequence, we can optimize the amount of adaptation necessary to solve a new task using stochastic gradient descent, in addition to learning the initial conditions as is standard practice in gradient-based meta-learning. Importantly, in order to compute the exact meta-gradients required for the outer-loop updates, we devise an efficient algorithm based on forward mode differentiation, whose memory requirements do not scale with the length of the learning trajectory, thus allowing longer adaptation in constant memory. We provide analytical guarantees for the stability of COMLN, we show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.

2022-01-28

ICLR.cc/2022/Conference (spotlight)

Coordination Among Neural Modules Through a Shared Global Workspace

Anirudh Goyal

Aniket Rajiv Didolkar

Alex Lamb

Kartikeya Badola

Nan Rosemary Ke

Nasim Rahaman

Jonathan Binas

Charles Blundell

Michael Curtis Mozer

Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For exam… (voir plus)ple, Transformers segment by position, and object-centric architectures decompose images into entities. In all these architectures, interactions between different elements are modeled via pairwise interactions: Transformers make use of self-attention to incorporate information from other positions and object-centric architectures make use of graph neural networks to model interactions among entities. We consider how to improve on pairwise interactions in terms of global coordination and a coherent, integrated representation that can be used for downstream tasks. In cognitive science, a global workspace architecture has been proposed in which functionally specialized components share information through a common, bandwidth-limited communication channel. We explore the use of such a communication channel in the context of deep learning for modeling the structure of complex environments. The proposed method includes a shared workspace through which communication among different specialist modules takes place but due to limits on the communication bandwidth, specialist modules must compete for access. We show that capacity limitations have a rational basis in that (1) they encourage specialization and compositionality and (2) they facilitate the synchronization of otherwise independent specialists.

2022-01-28

ICLR.cc/2022/Conference (présentation orale)

Fortuitous Forgetting in Connectionist Networks

Hattie Zhou

Ankit Vani

Hugo Larochelle

Aaron Courville

Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact b… (voir plus)e favorable to learning. We introduce"forget-and-relearn"as a powerful paradigm for shaping the learning trajectories of artificial neural networks. In this process, the forgetting step selectively removes undesirable information from the model, and the relearning step reinforces features that are consistently useful under different conditions. The forget-and-relearn framework unifies many existing iterative training algorithms in the image classification and language emergence literature, and allows us to understand the success of these algorithms in terms of the disproportionate forgetting of undesirable information. We leverage this understanding to improve upon existing algorithms by designing more targeted forgetting operations. Insights from our analysis provide a coherent view on the dynamics of iterative training in neural networks and offer a clear path towards performance improvements.

2022-01-28

ICLR.cc/2022/Conference (poster)

Graph Neural Networks with Learnable Structural and Positional Representations

Vijay Prakash Dwivedi

Anh Tuan Luu

Thomas Laurent

Xavier Bresson

Graph neural networks (GNNs) have become the standard learning architectures for graphs. GNNs have been applied to numerous domains ranging … (voir plus)from quantum chemistry, recommender systems to knowledge graphs and natural language processing. A major issue with arbitrary graphs is the absence of canonical positional information of nodes, which decreases the representation power of GNNs to distinguish e.g. isomorphic nodes and other graph symmetries. An approach to tackle this issue is to introduce Positional Encoding (PE) of nodes, and inject it into the input layer, like in Transformers. Possible graph PE are Laplacian eigenvectors. In this work, we propose to decouple structural and positional representations to make easy for the network to learn these two essential properties. We introduce a novel generic architecture which we call LSPE (Learnable Structural and Positional Encodings). We investigate several sparse and fully-connected (Transformer-like) GNNs, and observe a performance increase for molecular datasets, from 1.79% up to 64.14% when considering learnable PE for both GNN classes.

2022-01-28

ICLR.cc/2022/Conference (poster)

Medical Doctors in Health Reforms

Jean-Louis Denis

Sabrina Germain

Catherine Régis

Gianluca Veronesi

Health and legal experts from England and Canada consider the influence of medical doctors on reforms in this comparative study. With reflec… (voir plus)tions on participation since the inception of publicly funded healthcare systems, they show how the status of doctors affects change.

2022-01-28

(publié)