Guy Wolf

Biography

Guy Wolf is a Full Professor in the Department of Mathematics and Statistics (DMS) at the Université de Montréal (UdeM), a Canada CIFAR AI Chair & Core Academic Member at Mila (the Quebec AI institute), an Associate Researcher with CRCHUM (the Montreal university hospital research center), and a participating PI in the Helmholtz International Lab for Causal Cell Dynamics.

In 2024 he has been awarded a Humboldt Experienced Research Fellowship, as part of which he was a visiting professor at Heidelberg University (2024) and Helmholtz Munich (2024-2026) in Germany. Prior to joining UdeM and Mila, he was a Gibbs Assistant Professor (2015-2018) in the Applied Math Program and an Associate Research Scientist in the Department of Genetics (2018) at Yale University (CT, USA). Previously, he was a Postdoctoral Researcher (2013-2015) in the Department of Computer Science at École Normale Supérieure in Paris (France). He holds a Ph.D. in Computer Science from Tel Aviv University (Israel), and has five years of prior experience in IT software design & development for data analysis in military settings.

His current research focuses on guided representation learning for data exploration, including methods that leverage manifold learning and geometric deep learning for dimensionality reduction, visualization, denoising, data augmentation, and coarse graining. While relevant for a wide range of applications, he is particularly interested in the intersection of AI & health, including tools supporting exploratory analysis of biomedical data, e.g., in single-cell multiomics, drug discovery, and neuroscience.

Current Students

Adrien Aumon

PhD - Université de Montréal

adrien.aumon@mila.quebec

Semih Cantürk

PhD - Université de Montréal

semihcanturk00@gmail.com

Joao Felipe Carneiro Barbosa Rocha

Collaborating researcher - Yale University

Co-supervisor :

joaofelipe.rocha@mila.quebec

sebastian.damrich@mila.quebec

Sebastian Damrich

Collaborating researcher - University of Tübingen

Maxine Dussault

Master's Research - Université de Montréal

Co-supervisor :

Margarida Carvalho

maxine.dussault@mila.quebec

Stefan Horoi

PhD - Université de Montréal

stefan.horoi@mila.quebec

Master's Research - Concordia University

Principal supervisor :

xiaolong.huang@mila.quebec

Collaborating Alumni - Université de Montréal

guillaume.huguet@mila.quebec

Paul Janson

PhD - Concordia University

Principal supervisor :

myriam.lizotte@mila.quebec

paul.janson@mila.quebec

PhD - Université de Montréal

Gabriele Malagoli

Independent visiting researcher - Helmholtz Munich

gabriele.malagoli@mila.quebec

Philippe Martin

PhD - Université de Montréal

Co-supervisor :

Paul François

philippe.martin@mila.quebec

Paria Mehrbod

Master's Research - Concordia University

Principal supervisor :

paria.mehrbod@mila.quebec

Lydia Mezrag

PhD - Université de Montréal

lydia.mezrag@mila.quebec

Kevin Moon

Collaborating researcher

Sacha Morin

PhD - Université de Montréal

Co-supervisor :

Liam Paull

sacha.morin@mila.quebec

Postdoctorate - Concordia University

Principal supervisor :

geraldin.nanfack@mila.quebec

Shuang Ni

PhD - Université de Montréal

shuang.ni@mila.quebec

Albert Orozco Camacho

PhD - Concordia University

Principal supervisor :

Jake Rhodes

Collaborating researcher - BYU

rhodes@stat.byu.edu

thomas.sabourin@mila.quebec

Thomas Sabourin

PhD - Université de Montréal

johannes.schmidt@mila.quebec

Johannes Schmidt

Independent visiting researcher - University of Fribourg

PhD - Université de Montréal

Principal supervisor :

Julie Hussin

matthew.scicluna@mila.quebec

Ammar Sherif

PhD - Concordia University

Principal supervisor :

francisco.jose.tellez@mila.quebec

ammar.sherif@mila.quebec

Simeon Tchoffo

PhD - Université de Montréal

simeontchoffo@gmail.com

Francisco Tellez

Master's Research - Université de Montréal

César Miguel Valdez Cordova

PhD - McGill University

Principal supervisor :

Mathieu Blanchette

cesar.valdez@mila.quebec

Master's Research - Université de Montréal

Collaborating Alumni - Université de Montréal

Co-supervisor :

yanlei.zhang@mila.quebec

Exploring the COVID-19 Interferon Paradox with Dimensionality Reduction and Clustering

Blog Posts

Graph and representation of working methodology, and graph of data on deaths 60 days after onset of symptoms.

February 19, 2025

Sacha Morin

Elsa Brunet-Ratnasingham

Guy Wolf

Read the article

Publications

EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics

Yang Liu

Odin Zhang

Kevin K Yang

Shuangjia Zheng

2024-10-12

NeurIPS.cc/2024/Workshop/AIDrugX (poster)

openreview.net

Neurospectrum: A Geometric and Topological Deep Learning Framework for Uncovering Spatiotemporal Signatures in Neural Activity

Dhananjay Bhaskar

Yanlei Zhang

Jessica Moore

Feng Gao

Bastian Rieck

Firas Khasawneh

Elizabeth Munch

Valentina Greco

J. Adam Noah

Helen Pushkarskaya

Christopher Pittenger

Neural signals are high-dimensional, noisy, and dynamic, making it challenging to extract interpretable features linked to behavior or disea… (see more)se. We introduce Neurospectrum , a framework that encodes neural activity as latent trajectories shaped by spatial and temporal structure. At each timepoint, signals are represented on a graph capturing spatial relationships, with a learnable attention mechanism highlighting important regions. These are embedded using graph wavelets and passed through a manifold-regularized autoencoder that preserves temporal geometry. The resulting latent trajectory is summarized using a principled set of descriptors - including curvature, path signatures, persistent homology, and recurrent networks -that capture multiscale geometric, topological, and dynamical features. These features drive downstream prediction in a modular, interpretable, and end-to-end trainable framework. We evaluate Neurospectrum on simulated and experimental datasets. It tracks phase synchronization in Kuramoto simulations, reconstructs visual stimuli from calcium imaging, and identifies biomarkers of obsessive-compulsive disorder in fMRI. Across tasks, Neurospectrum uncovers meaningful neural dynamics and outperforms traditional analysis methods.

2024-10-12

bioRxiv (preprint)

Learning Stochastic Rainbow Networks

Vivian White

Muawiz Sajjad Chaudhary

Guillaume Lajoie

Kameron Decker Harris

Random feature models are a popular approach for studying network learning that can capture important behaviors while remaining simpler than… (see more) traditional training. Guth et al. [2024] introduced “rainbow” networks which model the distribution of trained weights as correlated random features conditioned on previous layer activity. Sampling new weights from distributions fit to learned networks led to similar performance in entirely untrained networks, and the observed weight covariance were found to be low rank. This provided evidence that random feature models could be extended to some networks away from initialization, but White et al. [2024] failed to replicate their results in the deeper ResNet18 architecture. Here we ask whether the rainbow formulation can succeed in deeper networks by directly training a stochastic ensemble of random features, which we call stochastic rainbow networks. At every gradient descent iteration, new weights are sampled for all intermediate layers and features aligned layer-wise. We find: (1) this approach scales to deeper models, which outperform shallow networks at large widths; (2) ensembling multiple samples from the stochastic model is better than retraining the classifier head; and (3) low-rank parameterization of the learnable weight covariances can approach the accuracy of full-rank networks. This offers more evidence for rainbow and other structured random feature networks as reduced models of deep learning.

2024-10-09

NeurIPS.cc/2024/Workshop/SciForDL (poster)

openreview.net

Harnessing population diversity: in search of tools of the trade

Danilo Bzdok

Jakub Kopal

Big neuroscience datasets are not big small datasets when it comes to quantitative data analysis. Neuroscience has now witnessed the advent … (see more)of many population cohort studies that deep-profile participants, yielding hundreds of measures, capturing dimensions of each individual’s position in the broader society. Indeed, there is a rebalancing from small, strictly selected, and thus homogenized cohorts toward always larger, more representative, and thus diverse cohorts. This shift in cohort composition is prompting the revision of incumbent modeling practices. Major sources of population stratification increasingly overshadow the subtle effects that neuroscientists are typically studying. In our opinion, as we sample individuals from always wider diversity backgrounds, we will require a new stack of quantitative tools to realize diversity-aware modeling. We here take inventory of candidate analytical frameworks. Better incorporating driving factors behind population structure will allow refining our understanding of how brain–behavior relationships depend on human subgroups.

2024-09-26

GigaScience (published)

Harnessing population diversity: in search of tools of the trade

Danilo Bzdok

Jakub Kopal

Abstract Big neuroscience datasets are not big small datasets when it comes to quantitative data analysis. Neuroscience has now witnessed th… (see more)e advent of many population cohort studies that deep-profile participants, yielding hundreds of measures, capturing dimensions of each individual’s position in the broader society. Indeed, there is a rebalancing from small, strictly selected, and thus homogenized cohorts toward always larger, more representative, and thus diverse cohorts. This shift in cohort composition is prompting the revision of incumbent modeling practices. Major sources of population stratification increasingly overshadow the subtle effects that neuroscientists are typically studying. In our opinion, as we sample individuals from always wider diversity backgrounds, we will require a new stack of quantitative tools to realize diversity-aware modeling. We here take inventory of candidate analytical frameworks. Better incorporating driving factors behind population structure will allow refining our understanding of how brain–behavior relationships depend on human subgroups.

2024-09-26

GigaScience (published)

Are Heterophily-Specific GNNs and Homophily Metrics Really Effective? Evaluation Pitfalls and New Benchmarks

Sitao Luan

Qincheng Lu

Chenqing Hua

Xinyu Wang

Jiaqi Zhu

Xiao-Wen Chang

Jian Tang

Over the past decade, Graph Neural Networks (GNNs) have achieved great success on machine learning tasks with relational data. However, rece… (see more)nt studies have found that heterophily can cause significant performance degradation of GNNs, especially on node-level tasks. Numerous heterophilic benchmark datasets have been put forward to validate the efficacy of heterophily-specific GNNs and various homophily metrics have been designed to help people recognize these malignant datasets. Nevertheless, there still exist multiple pitfalls that severely hinder the proper evaluation of new models and metrics. In this paper, we point out three most serious pitfalls: 1) a lack of hyperparameter tuning; 2) insufficient model evaluation on the real challenging heterophilic datasets; 3) missing quantitative evaluation benchmark for homophily metrics on synthetic graphs. To overcome these challenges, we first train and fine-tune baseline models on

2024-09-08

ArXiv (preprint)

arxiv.org

Graph Positional and Structural Encoder

Renming Liu

Semih Cantürk

Olivier Lapointe-Gagné

Positional and structural encodings (PSE) enable better identifiability of nodes within a graph, rendering them essential tools for empoweri… (see more)ng modern GNNs, and in particular graph Transformers. However, designing PSEs that work optimally for all graph prediction tasks is a challenging and unsolved problem. Here, we present the Graph Positional and Structural Encoder (GPSE), the first-ever graph encoder designed to capture rich PSE representations for augmenting any GNN. GPSE learns an efficient common latent representation for multiple PSEs, and is highly transferable: The encoder trained on a particular graph dataset can be used effectively on datasets drawn from markedly different distributions and modalities. We show that across a wide range of benchmarks, GPSE-enhanced models can significantly outperform those that employ explicitly computed PSEs, and at least match their performance in others. Our results pave the way for the development of foundational pre-trained graph encoders for extracting positional and structural information, and highlight their potential as a more powerful and efficient alternative to explicitly computed PSEs and existing self-supervised pre-training approaches. Our framework and pre-trained models are publicly available at https://github.com/G-Taxonomy-Workgroup/GPSE. For convenience, GPSE has also been integrated into the PyG library to facilitate downstream applications.

2024-07-22

International Conference on Machine Learning (Accept (Poster))

proceedings.mlr.press

The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges

Sitao Luan

Chenqing Hua

Qincheng Lu

Liheng Ma

Lirong Wu

Xinyu Wang

Minkai Xu

Xiao-Wen Chang

Doina Precup

Rex Ying

Stan Z. Li

Jian Tang

Stefanie Jegelka

Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to b… (see more)e the main reason for the superiority of Graph Neural Networks (GNNs) over traditional Neural Networks (NNs) on graph-structured data, especially on node-level tasks. However, recent work has identified a non-trivial set of datasets where GNN's performance compared to the NN's is not satisfactory. Heterophily, i.e. low homophily, has been considered the main cause of this empirical observation. People have begun to revisit and re-evaluate most existing graph models, including graph transformer and its variants, in the heterophily scenario across various kinds of graphs, e.g. heterogeneous graphs, temporal graphs and hypergraphs. Moreover, numerous graph-related applications are found to be closely related to the heterophily problem. In the past few years, considerable effort has been devoted to studying and addressing the heterophily issue. In this survey, we provide a comprehensive review of the latest progress on heterophilic graph learning, including an extensive summary of benchmark datasets and evaluation of homophily metrics on synthetic graphs, meticulous classification of the most updated supervised and unsupervised learning methods, thorough digestion of the theoretical analysis on homophily/heterophily, and broad exploration of the heterophily-related applications. Notably, through detailed experiments, we are the first to categorize benchmark heterophilic datasets into three sub-categories: malignant, benign and ambiguous heterophily. Malignant and ambiguous datasets are identified as the real challenging datasets to test the effectiveness of new models on the heterophily challenge. Finally, we propose several challenges and future directions for heterophilic graph representation learning.

2024-07-11

arXiv (Cornell University) (preprint)

arxiv.org

Geometry-Aware Generative Autoencoders for Metric Learning and Generative Modeling on Data Manifolds

Xingzhi Sun

Danqi Liao

Kincaid MacDonald

Yanlei Zhang

Guillaume Huguet

Ian Adelstein

Tim G. J. Rudner

Non-linear dimensionality reduction methods have proven successful at learning low-dimensional representations of high-dimensional point clo… (see more)uds on or near data manifolds. However, existing methods are not easily extensible—that is, for large datasets, it is prohibitively expensive to add new points to these embeddings. As a result, it is very difficult to use existing embeddings generatively, to sample new points on and along these manifolds. In this paper, we propose GAGA (geometry-aware generative autoencoders) a framework which merges the power of generative deep learning with non-linear manifold learning by: 1) learning generalizable geometry-aware neural network embeddings based on non-linear dimensionality reduction methods like PHATE and diffusion maps, 2) deriving a non-euclidean pullback metric on the embedded space to generate points faithfully along manifold geodesics, and 3) learning a flow on the manifold that allows us to transport populations. We provide illustration on easily-interpretable synthetic datasets and showcase results on simulated and real single cell datasets. In particular, we show that the geodesic-based generation can be especially important for scientific datasets where the manifold represents a state space and geodesics can represent dynamics of entities over this space.

2024-06-16

ICML.cc/2024/Workshop/GRaM (published)

openreview.net

Simulating federated learning for steatosis detection using ultrasound images

Yue Qi

Pedro Vianna

Alexandre Cadrin-Chênevert

Katleen Blanchet

Emmanuel Montagnon

Louis-Antoine Mullie

Guy Cloutier

Michaël Chassé

An Tang

We aimed to implement four data partitioning strategies evaluated with four federated learning (FL) algorithms and investigate the impact of… (see more) data distribution on FL model performance in detecting steatosis using B-mode US images. A private dataset (153 patients; 1530 images) and a public dataset (55 patient; 550 images) were included in this retrospective study. The datasets contained patients with metabolic dysfunction-associated fatty liver disease (MAFLD) with biopsy-proven steatosis grades and control individuals without steatosis. We employed four data partitioning strategies to simulate FL scenarios and we assessed four FL algorithms. We investigated the impact of class imbalance and the mismatch between the global and local data distributions on the learning outcome. Classification performance was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. AUCs were 0.93 (95% CI 0.92, 0.94) for source-based partitioning scenario with FedAvg, 0.90 (95% CI 0.89, 0.91) for a centralized model, and 0.83 (95% CI 0.81, 0.85) for a model trained in a single-center scenario. When data was perfectly balanced on the global level and each site had an identical data distribution, the model yielded an AUC of 0.90 (95% CI 0.88, 0.92). When each site contained data exclusively from one single class, irrespective of the global data distribution, the AUC fell in the range of 0.34–0.70. FL applied to B-mode US images provide performance comparable to a centralized model and higher than single-center scenario. Global data imbalance and local data heterogeneity influenced the learning outcome.

2024-06-09

Scientific Reports (published)

Noisy Data Visualization using Functional Data Analysis

Haozhe Chen

Andres Felipe Duque Correa

Kevin R. Moon

Data visualization via dimensionality reduction is an important tool in exploratory data analysis. However, when the data are noisy, many ex… (see more)isting methods fail to capture the underlying structure of the data. The method called Empirical Intrinsic Geometry (EIG) was previously proposed for performing dimensionality reduction on high dimensional dynamical processes while theoretically eliminating all noise. However, implementing EIG in practice requires the construction of high-dimensional histograms, which suffer from the curse of dimensionality. Here we propose a new data visualization method called Functional Information Geometry (FIG) for dynamical processes that adapts the EIG framework while using approaches from functional data analysis to mitigate the curse of dimensionality. We experimentally demonstrate that the resulting method outperforms a variant of EIG designed for visualization in terms of capturing the true structure, hyperparameter robustness, and computational speed. We then use our method to visualize EEG brain measurements of sleep activity.

2024-06-04

ArXiv (preprint)

arxiv.org

Supervised latent factor modeling isolates cell-type-specific transcriptomic modules that underlie Alzheimer’s disease progression

Liam Hodgson

Yue Li

Yasser Iturria-Medina

Jo Anne Stratton

David A. Bennett

Danilo Bzdok

Late onset Alzheimer’s disease (AD) is a progressive neurodegenerative disease, with brain changes beginning years before symptoms surface… (see more). AD is characterized by neuronal loss, the classic feature of the disease that underlies brain atrophy. However, GWAS reports and recent single-nucleus RNA sequencing (snRNA-seq) efforts have highlighted that glial cells, particularly microglia, claim a central role in AD pathophysiology. Here, we tailor pattern-learning algorithms to explore distinct gene programs by integrating the entire transcriptome, yielding distributed AD-predictive modules within the brain’s major cell-types. We show that these learned modules are biologically meaningful through the identification of new and relevant enriched signaling cascades. The predictive nature of our modules, especially in microglia, allows us to infer each subject’s progression along a disease pseudo-trajectory, confirmed by post-mortem pathological brain tissue markers. Additionally, we quantify the interplay between pairs of cell-type modules in the AD brain, and localized known AD risk genes to enriched module gene programs. Our collective findings advocate for a transition from cell-type-specificity to gene modules specificity to unlock the potential of unique gene programs, recasting the roles of recently reported genome-wide AD risk loci. Designing a supervised latent factor framework for snRNA-seq human brain, the authors find distinct Alzheimer’s-predictive gene modules across celltypes, suggesting subcelltype disease progression trajectories.

2024-05-16

Communications Biology (published)