Portrait de Guy Wolf

Guy Wolf

Membre académique principal
wolfguy@mila.quebec
Chaire en IA Canada-CIFAR
Professeur agrégé, Université de Montréal, Département de mathématiques et statistiques
Concordia University
CHUM - Montreal University Hospital Center
Site web
Google Scholar

Biographie

Guy Wolf est professeur agrégé au Département de mathématiques et de statistique de l'Université de Montréal. Ses intérêts de recherche se situent au carrefour de l'apprentissage automatique, de la science des données et des mathématiques appliquées. Il s'intéresse particulièrement aux méthodes d'exploration de données qui utilisent l'apprentissage multiple et l'apprentissage géométrique profond, ainsi qu'aux applications pour l'analyse exploratoire des données biomédicales.

Ses recherches portent sur l'analyse exploratoire des données, avec des applications en bio-informatique. Ses approches sont multidisciplinaires et combinent l'apprentissage automatique, le traitement du signal et les outils mathématiques appliqués. En particulier, ses travaux récents utilisent une combinaison de géométries de diffusion et d'apprentissage profond pour trouver des modèles émergents, des dynamiques et des structures dans les mégadonnées à grande dimension (par exemple, dans la génomique et la protéomique de la cellule unique).

Étudiants actuels

Adrien Aumon
Doctorat - Université de Montréal
adrien.aumon@mila.quebec
Albert Orozco Camacho
Doctorat - Concordia University
Superviseur⋅e principal⋅e :
Eugene Belilovsky
orozcoca@mila.quebec
Site web
Github
Google Scholar
Amine Natik
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Guillaume Lajoie
natikami@mila.quebec
Charles-Etienne Joseph
Maîtrise recherche - Université de Montréal
Superviseur⋅e principal⋅e :
Eugene Belilovsky
charles-etienne.joseph@mila.quebec
Github
Will Hua
Maîtrise recherche - McGill University
Superviseur⋅e principal⋅e :
Doina Precup
chenqing.hua@mila.quebec
Donald Shenaj
Collaborateur·rice de recherche - Concordia University
Superviseur⋅e principal⋅e :
Eugene Belilovsky
donald.shenaj@mila.quebec
Site web
Github
Google Scholar
Edouard Oyallon
Visiteur de recherche indépendant
edouard.oyallon@mila.quebec
Site web
Github
Google Scholar
Geraldin Nanfack
Postdoctorat - Concordia University
Superviseur⋅e principal⋅e :
Eugene Belilovsky
geraldin.nanfack@mila.quebec
Guillaume Huguet
Doctorat - Université de Montréal
guillaume.huguet@mila.quebec
Github
Google Scholar
Hasti Nafisi
Maîtrise recherche - Université de Montréal
Co-superviseur⋅e :
Yashar Hezaveh
hasti.nafisi@mila.quebec
Jake Kovalic
Collaborateur·rice de recherche - Yale
jake.kovalic@mila.quebec
Github
Frederik Wenkel
Doctorat - Université de Montréal
frederik.wenkel@mila.quebec
Site web
Github
Google Scholar
Lydia Mezrag
Doctorat - Université de Montréal
lydia.mezrag@mila.quebec
Mehrbod Paria
Maîtrise recherche - Concordia University
Superviseur⋅e principal⋅e :
Eugene Belilovsky
paria.mehrbod@mila.quebec
Muawiz Chaudhary
Collaborateur·rice alumni
muawiz.chaudhary@mila.quebec
Github
Google Scholar
Myriam Lizotte
Doctorat - Université de Montréal
myriam.lizotte@mila.quebec
Nader Asadi
Collaborateur·rice alumni
Superviseur⋅e principal⋅e :
Eugene Belilovsky
nader.asadi@mila.quebec
Site web
Github
Google Scholar
Pedro Vianna
Collaborateur·rice de recherche - Université de Montréal
Co-superviseur⋅e :
Eugene Belilovsky
pedro.vianna@mila.quebec
Github
Google Scholar
Ria Arora
Maîtrise recherche - Université de Montréal
Co-superviseur⋅e :
Liam Paull
ria.arora@mila.quebec
Github
Sacha Morin
Doctorat - Université de Montréal
Co-superviseur⋅e :
Liam Paull
sacha.morin@mila.quebec
Semih Cantürk
Doctorat - Université de Montréal
semih.canturk@mila.quebec
Site web
Github
Google Scholar
Shuang Ni
Doctorat - Université de Montréal
shuang.ni@mila.quebec
Site web
Github
Siddharth Viswanath
Collaborateur·rice de recherche - Yale
siddarth.viswanath@mila.quebec
Stefan Horoi
Doctorat - Université de Montréal
stefan.horoi@mila.quebec
Site web
Github
Google Scholar
Vincent Létourneau
Postdoctorat - Université de Montréal
letournv@mila.quebec
Vivian White
Stagiaire de recherche - Western Washington University
Superviseur⋅e principal⋅e :
Guillaume Lajoie
vivian.white@mila.quebec
Github
Zhang Yanlei
Postdoctorat - Université de Montréal
yanlei.zhang@mila.quebec
Site web
Google Scholar

Publications

A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
Guillaume Huguet
Alexander Tong
Edward De Brouwer
Yanlei Zhang
Guy Wolf
Ian Adelstein
Smita Krishnaswamy
openreview.net
Inferring Dynamic Regulatory Interaction Graphs From Time Series Data With Perturbations
Dhananjay Bhaskar
Daniel Sumner Magruder
Matheo Morales
Edward De Brouwer
Aarthi Venkat
Frederik Wenkel
Guy Wolf
Smita Krishnaswamy
2023-01-01
LoG (publié)
doi.org
openreview.net
Learning Shared Neural Manifolds from Multi-Subject FMRI Data
Jessie Huang
Je-chun Huang
Erica Lindsey Busch
Tom Wallenstein
Michal Gerasimiuk
Andrew Benz
Guillaume Lajoie
Guy Wolf
Nicholas Turk-Browne
Smita Krishnaswamy
Functional magnetic resonance imaging (fMRI) data is collected in millions of noisy, redundant dimensions. To understand how different brain… (voir plus)s process the same stimulus, we aim to denoise the fMRI signal via a meaningful embedding space that captures the data's intrinsic structure as shared across brains. We assume that stimulus-driven responses share latent features common across subjects that are jointly discoverable. Previous approaches to this problem have relied on linear methods like principal component analysis and shared response modeling. We propose a neural network called MRMD-AE (manifold-regularized multiple- decoder, autoencoder) that learns a common embedding from multi-subject fMRI data while retaining the ability to decode individual responses. Our latent common space represents an extensible manifold (where untrained data can be mapped) and improves classification accuracy of stimulus features of unseen timepoints, as well as cross-subject translation of fMRI signals.
2022-08-22
2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP) (publié)
doi.org
openreview.net
Parametric Scattering Networks
Shanel Gauthier
Benjamin Thérien
Laurent Alséne-Racicot
Muawiz Chaudhary
Irina Rish
Eugene Belilovsky
Michael Eickenberg
Guy Wolf
The wavelet scattering transform creates geometric in-variants and deformation stability. In multiple signal do-mains, it has been shown to … (voir plus)yield more discriminative rep-resentations compared to other non-learned representations and to outperform learned representations in certain tasks, particularly on limited labeled data and highly structured signals. The wavelet filters used in the scattering trans-form are typically selected to create a tight frame via a pa-rameterized mother wavelet. In this work, we investigate whether this standard wavelet filterbank construction is op-timal. Focusing on Morlet wavelets, we propose to learn the scales, orientations, and aspect ratios of the filters to produce problem-specific parameterizations of the scattering transform. We show that our learned versions of the scattering transform yield significant performance gains in small-sample classification settings over the standard scat-tering transform. Moreover, our empirical results suggest that traditional filterbank constructions may not always be necessary for scattering transforms to extract effective rep-resentations.
2022-06-18
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (publié)
doi.org
arxiv.org
Multiscale PHATE identifies multimodal signatures of COVID-19
Manik Kuchroo
Je-chun Huang
Patrick Wong
Jean-Christophe Grenier
Dennis Shung
Alexander Tong
Carolina Lucas
Jon Klein
Daniel B. Burkhardt
Scott Gigante
Abhinav Godavarthi
Bastian Rieck
Benjamin Israelow
Michael Simonov
Tianyang Mao
Ji Eun Oh
Julio Silva
Takehiro Takahashi
Camila D. Odio
Arnau Casanovas-Massana … (voir 10 de plus)
John Fournier
Shelli Farhadian
Charles S. Dela Cruz
Albert I. Ko
Matthew Hirn
F. Perry Wilson
Julie Hussin
Guy Wolf
Akiko Iwasaki
Smita Krishnaswamy
2022-02-28
Nature Biotechnology (publié)
doi.org
Multiscale PHATE identifies multimodal signatures of COVID-19
Manik Kuchroo
Je-chun Huang
Patrick W. Wong
Jean-Christophe Grenier
Dennis L. Shung
Alexander Tong
C. Lucas
J. Klein
Daniel B. Burkhardt
Scott Gigante
Abhinav Godavarthi
Bastian Rieck
Benjamin Israelow
Michael Simonov
Tianyang Mao
Ji Eun Oh
Julio Silva
Takehiro Takahashi
C. Odio
Arnau Casanovas‐massana … (voir 10 de plus)
John Byrne Fournier
Shelli F. Farhadian
C. D. Dela Cruz
A. Ko
Matthew Hirn
F. Wilson
Julie Hussin
Guy Wolf
Akiko Iwasaki
Smita Krishnaswamy
2022-02-28
Nature Biotechnology (published)
doi.org
Population Genomics Approaches for Genetic Characterization of SARS-CoV-2 Lineages
Fatima Mostefai
I. Gamache
Arnaud N’Guessan
Justin Pelletier
Jessie Huang
Carmen Lia Murall
Ahmad Pesaranghader
Vanda Gaonac'h-Lovejoy
David J. Hamelin
Raphael Poujol
Jean-Christophe Grenier
Martin W. Smith
Étienne Caron
Morgan Craig
Guy Wolf
Smita Krishnaswamy
B. Jesse Shapiro
Julie Hussin
The genome of the Severe Acute Respiratory Syndrome coronavirus 2 (SARS-CoV-2), the pathogen that causes coronavirus disease 2019 (COVID-19)… (voir plus), has been sequenced at an unprecedented scale leading to a tremendous amount of viral genome sequencing data. To assist in tracing infection pathways and design preventive strategies, a deep understanding of the viral genetic diversity landscape is needed. We present here a set of genomic surveillance tools from population genetics which can be used to better understand the evolution of this virus in humans. 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. We analyzed 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. This approach enables real-time lineage identification, a clear description of the relationship between variants of concern, and efficient detection of recurrent mutations. Furthermore, time series change of Tajima's D by haplotype provides a powerful metric of lineage expansion. Finally, principal component analysis (PCA) highlights key steps in variant emergence and facilitates the visualization of genomic variation in the context of SARS-CoV-2 diversity. The computational framework presented here is simple to implement and insightful for real-time genomic surveillance of SARS-CoV-2 and could be applied to any pathogen that threatens the health of populations of humans and other organisms.
2022-02-21
Frontiers in Medicine (published)
doi.org
Population Genomics Approaches for Genetic Characterization of SARS-CoV-2 Lineages
Fatima Mostefai
Isabel Gamache
Arnaud N’Guessan
Justin Pelletier
Jessie Huang
Carmen Lia Murall
Ahmad Pesaranghader
Vanda Gaonac'h-Lovejoy
David J. Hamelin
Raphael Poujol
Jean-Christophe Grenier
Martin Smith
Etienne Caron
Morgan Craig
Guy Wolf
Smita Krishnaswamy
B. Jesse Shapiro
Julie Hussin
2022-02-21
Frontiers in Medicine (publié)
doi.org
Goal-driven optimization of single-neuron properties in artificial networks reveals regularization role of neural diversity and adaptation in the brain
Victor Geadah
Stefan Horoi
Giancarlo Kerg
Guy Wolf
Guillaume Lajoie
Neurons in the brain have rich and adaptive input-output properties. Features such as diverse f-I curves and spike frequency adaptation are … (voir plus)known to place single neurons in optimal coding regimes when facing changing stimuli. Yet, it is still unclear how brain circuits exploit single neuron flexibility, and how network-level requirements may have shaped such cellular function. To answer this question, a multi-scaled approach is needed where the computations of single neurons and of neural circuits must be considered as a complete system. In this work, we use artificial neural networks to systematically investigate single neuron input-output adaptive mechanisms, optimized in an end-to-end fashion. Throughout the optimization process, each neuron has the liberty to modify its nonlinear activation function, parametrized to mimic f-I curves of biological neurons, and to learn adaptation strategies to modify activation functions in real-time during a task. We find that such networks show much-improved robustness to noise and changes in input statistics. Importantly, we find that this procedure recovers precise coding strategies found in biological neurons, such as gain scaling and fractional order differentiation/integration. Using tools from dynamical systems theory, we analyze the role of these emergent single neuron properties and argue that neural diversity and adaptation plays an active regularization role that enables neural circuits to optimally propagate information across time.
2022-01-01
(published)
www.semanticscholar.org
Goal-driven optimization of single-neuron properties in artificial networks reveals regularization role of neural diversity and adaptation in the brain
Victor Geadah
Stefan Horoi
Giancarlo Kerg
Guy Wolf
Guillaume Lajoie
Neurons in the brain have rich and adaptive input-output properties. Features such as diverse f-I curves and spike frequency adaptation are … (voir plus)known to place single neurons in optimal coding regimes when facing changing stimuli. Yet, it is still unclear how brain circuits exploit single neuron flexibility, and how network-level requirements may have shaped such cellular function. To answer this question, a multi-scaled approach is needed where the computations of single neurons and of neural circuits must be considered as a complete system. In this work, we use artificial neural networks to systematically investigate single neuron input-output adaptive mechanisms, optimized in an end-to-end fashion. Throughout the optimization process, each neuron has the liberty to modify its nonlinear activation function, parametrized to mimic f-I curves of biological neurons, and to learn adaptation strategies to modify activation functions in real-time during a task. We find that such networks show much-improved robustness to noise and changes in input statistics. Importantly, we find that this procedure recovers precise coding strategies found in biological neurons, such as gain scaling and fractional order differentiation/integration. Using tools from dynamical systems theory, we analyze the role of these emergent single neuron properties and argue that neural diversity and adaptation plays an active regularization role that enables neural circuits to optimally propagate information across time.
2022-01-01
(publié)
www.semanticscholar.org
Long Range Graph Benchmark
Vijay Prakash Dwivedi
Ladislav Rampášek
Mikhail Galkin
Ali Parviz
Guy Wolf
Anh Tuan Luu
Dominique Beaini
Graph Neural Networks (GNNs) that are based on the message passing (MP) paradigm generally exchange information between 1-hop neighbors to b… (voir plus)uild node representations at each layer. In principle, such networks are not able to capture long-range interactions (LRI) that may be desired or necessary for learning a given task on graphs. Recently, there has been an increasing interest in development of Transformer-based methods for graphs that can consider full node connectivity beyond the original sparse structure, thus enabling the modeling of LRI. However, MP-GNNs that simply rely on 1-hop message passing often fare better in several existing graph benchmarks when combined with positional feature representations, among other innovations, hence limiting the perceived utility and ranking of Transformer-like architectures. Here, we present the Long Range Graph Benchmark (LRGB) with 5 graph learning datasets: PascalVOC-SP, COCO-SP, PCQM-Contact, Peptides-func and Peptides-struct that arguably require LRI reasoning to achieve strong performance in a given task. We benchmark both baseline GNNs and Graph Transformer networks to verify that the models which capture long-range dependencies perform significantly better on these tasks. Therefore, these datasets are suitable for benchmarking and exploration of MP-GNNs and Graph Transformer architectures that are intended to capture LRI.
openreview.net
Recipe for a General, Powerful, Scalable Graph Transformer
Ladislav Rampášek
Mikhail Galkin
Vijay Prakash Dwivedi
Anh Tuan Luu
Guy Wolf
Dominique Beaini
We propose a recipe on how to build a general, powerful, scalable (GPS) graph Transformer with linear complexity and state-of-the-art result… (voir plus)s on a diverse set of benchmarks. Graph Transformers (GTs) have gained popularity in the field of graph representation learning with a variety of recent publications but they lack a common foundation about what constitutes a good positional or structural encoding, and what differentiates them. In this paper, we summarize the different types of encodings with a clearer definition and categorize them as being
openreview.net