Portrait of Guy Wolf

Guy Wolf

Core Academic Member
Canada CIFAR AI Chair
Full Professor, Université de Montréal
Affiliate Professor, Concordia University, Department of Computer Science and Software Engineering
Chief AI Scientist, DRI CHUM and Associate Director, AI & Data Science, CRCHUM and Scientific Director, CITADEL, CR/CHUM and Principal Scientist, CRCHUM
Research Topics
Data Mining
Deep Learning
Dynamical Systems
Graph Neural Networks
Information Retrieval
Learning on Graphs
Machine Learning Theory
Medical Machine Learning
Molecular Modeling
Multimodal Learning
Representation Learning
Spectral Learning

Biography

Guy Wolf is the Chief AI Scientist of the CHUM university healthcare center, the Associate Director of AI & Data Science of its research center (CRCHUM), and the Scientific Director of its medical data analysis & integration center (CITADEL). He is a Full Professor at the Université de Montréal (UdeM) and Core Academic Member at Mila, where he holds a Canada CIFAR AI Chair. He is also an IVADO professor, CRM member, and 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) and an Associate Research Scientist (2018) at Yale University (CT, USA), as well as a Postdoctoral Researcher (2013-2015) 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

PhD - Université de Montréal
Collaborating researcher - University of Tübingen
Master's Research - Université de Montréal
Co-supervisor :
Master's Research - Concordia University
Principal supervisor :
Collaborating Alumni - Université de Montréal
PhD - Concordia University
Principal supervisor :
PhD - Université de Montréal
Independent visiting researcher - Helmholtz Munich
PhD - Université de Montréal
Co-supervisor :
Master's Research - Concordia University
Principal supervisor :
PhD - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
Postdoctorate - Concordia University
Principal supervisor :
PhD - Université de Montréal
PhD - Concordia University
Principal supervisor :
Collaborating researcher - BYU
Independent visiting researcher - University of Fribourg
PhD - Université de Montréal
Principal supervisor :
PhD - Concordia University
Principal supervisor :
Master's Research - McGill University
PhD - Université de Montréal
Master's Research - Université de Montréal
Master's Research - Université de Montréal
Collaborating Alumni - Université de Montréal
Co-supervisor :

Publications

Scalable Tree Ensemble Proximities in Python
Kevin R. Moon
Jake S. Rhodes
From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging
Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized dataset… (see more)s. This has led to a proliferation of expert models and adapters, often shared via platforms like HuggingFace and AdapterHub. Model merging has recently emerged as an effective way to leverage these existing resources, enabling the composition of capabilities from different model checkpoints. A natural pipeline has thus formed to harness the benefits of transfer learning and amortize sunk training costs: models are pre-trained on general data, fine-tuned on specific tasks, and then multiple checkpoints are merged to obtain a more capable model. A prevailing assumption is that improvements at one stage of this pipeline propagate downstream, leading to gains at subsequent steps. In this work, we challenge that assumption by examining how expert fine-tuning affects model merging. We show that long fine-tuning of experts that optimizes for their individual performance leads to degraded merging performance across vision and language modalities, multiple model scales, and both fully fine-tuned and LoRA-adapted models. We trace this degradation to the memorization of a small set of difficult examples that dominate late fine-tuning steps. This causes negative parameter interference and encodes knowledge that is forgotten during merging. Finally, we demonstrate that task-dependent aggressive early stopping strategies can significantly improve model merging performance.
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Antonis Vasileiou
Juan Cervino
Pascal Frossard
Charilaos I. Kanatsoulis
Michael T. Schaub
Pierre Vandergheynst
Zhiyang Wang
Ron Levie
Geometry-Aware Edge Pooling for Graph Neural Networks
Graph Neural Networks (GNNs) have shown significant success for graph-based tasks. Motivated by the prevalence of large datasets in real-wor… (see more)ld applications, pooling layers are crucial components of GNNs. By reducing the size of input graphs, pooling enables faster training and potentially better generalisation. However, existing pooling operations often optimise for the learning task at the expense of discarding fundamental graph structures, thus reducing interpretability. This leads to unreliable performance across dataset types, downstream tasks and pooling ratios. Addressing these concerns, we propose novel graph pooling layers for structure-aware pooling via edge collapses. Our methods leverage diffusion geometry and iteratively reduce a graph's size while preserving both its metric structure and its structural diversity. We guide pooling using magnitude, an isometry-invariant diversity measure, which permits us to control the fidelity of the pooling process. Further, we use the spread of a metric space as a faster and more stable alternative ensuring computational efficiency. Empirical results demonstrate that our methods (i) achieve top performance compared to alternative pooling layers across a range of diverse graph classification tasks, (ii) preserve key spectral properties of the input graphs, and (iii) retain high accuracy across varying pooling ratios.
Random Forest Autoencoders for Guided Representation Learning
Kevin R. Moon
Jake S. Rhodes
Extensive research has produced robust methods for unsupervised data visualization. Yet supervised visualization…
Retro SynFlow: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis
Robin Yadav
Qi Yan
Avishek Joey Bose
Renjie Liao
A fundamental problem in organic chemistry is identifying and predicting the series of reactions that synthesize a desired target product mo… (see more)lecule. Due to the combinatorial nature of the chemical search space, single-step reactant prediction -- i.e. single-step retrosynthesis -- remains challenging even for existing state-of-the-art template-free generative approaches to produce an accurate yet diverse set of feasible reactions. In this paper, we model single-step retrosynthesis planning and introduce RETRO SYNFLOW (RSF) a discrete flow-matching framework that builds a Markov bridge between the prescribed target product molecule and the reactant molecule. In contrast to past approaches, RSF employs a reaction center identification step to produce intermediate structures known as synthons as a more informative source distribution for the discrete flow. To further enhance diversity and feasibility of generated samples, we employ Feynman-Kac steering with Sequential Monte Carlo based resampling to steer promising generations at inference using a new reward oracle that relies on a forward-synthesis model. Empirically, we demonstrate \nameshort achieves
Freeze, Diffuse, Decode: Geometry-Aware Adaptation of Pretrained Transformer Embeddings for Antimicrobial Peptide Design
Pankhil Gawade
Adam Izdebski
Kevin R. Moon
Jake S. Rhodes
Ewa Szczurek
Graph topological property recovery with heat and wave dynamics-based features on graphs
Dhananjay Bhaskar
Yanlei Zhang
Charles Xu
Xingzhi Sun
Oluwadamilola Fasina
Maximilian Nickel
Michael Perlmutter
Neural FIM: Bridging Statistical Manifolds and Generative Modeling through Fisher Geometry
Yanlei Zhang
Edward De Brouwer
Danqi Liao
Oluwadamilola Fasina
Ricky T. Q. Chen
Maximilian Nickel
Ian Adelstein
While data diffusion-based embeddings are widely used in unsupervised learning to reveal the intrinsic geometry of data, they are fundamenta… (see more)lly constrained by their discrete nature and inability to generalize beyond training points. This limitation ob
Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs
Sangwoo Cho
Supriyo Chakraborty
Shi-Xiong Zhang
Sambit Sahu
Genta Indra Winata
Measure Before You Look: Grounding Embeddings Through Manifold Metrics
Low-dimensional embeddings of high-dimensional data
Cyril de Bodt
Alex Diaz-Papkovich
Michael Bleher
Kerstin Bunte
Corinna Coupette
Fred Hamprecht
EmHoke-'Agnes Horv'at
Dhruv Kohli
John A. Lee 0001
Boudewijn P. F. Lelieveldt
Leland McInnes
Ian T. Nabney
Maximilian Noichl
Pavlin G. Polivcar
Bastian Rieck
Gal Mishne … (see 1 more)
Dmitry Kobak
Large collections of high-dimensional data have become nearly ubiquitous across many academic fields and application domains, ranging from b… (see more)iology to the humanities. Since working directly with high-dimensional data poses challenges, the demand for algorithms that create low-dimensional representations, or embeddings, for data visualization, exploration, and analysis is now greater than ever. In recent years, numerous embedding algorithms have been developed, and their usage has become widespread in research and industry. This surge of interest has resulted in a large and fragmented research field that faces technical challenges alongside fundamental debates, and it has left practitioners without clear guidance on how to effectively employ existing methods. Aiming to increase coherence and facilitate future work, in this review we provide a detailed and critical overview of recent developments, derive a list of best practices for creating and using low-dimensional embeddings, evaluate popular approaches on a variety of datasets, and discuss the remaining challenges and open problems in the field.