Christian Gagné

Biographie

Christian Gagné est professeur au Département de génie électrique et de génie informatique de l’Université Laval depuis 2008, et dirige l’Institut intelligence et données (IID). Il détient une chaire en IA Canada-CIFAR et est membre associé à Mila – Institut québécois d’intelligence artificielle. Il est également membre du Laboratoire de vision et systèmes numériques (LVSN), une composante du Centre de recherche en robotique, vision et intelligence machine (CeRVIM) ainsi que du Centre de recherche en données massives (CRDM) de l’Université Laval. Il fait partie des regroupements stratégiques REPARTI et UNIQUE du Fonds de recherche du Québec – Nature et technologies (FRQNT), du centre VITAM du Fonds de recherche du Québec – Santé (FRQS) et de l’Observatoire international sur les impacts sociétaux de l’IA et du numérique (OBVIA).

Ses intérêts de recherche portent sur l’élaboration de méthodes pour l’apprentissage automatique et l’optimisation stochastique. En particulier, il se consacre aux réseaux de neurones profonds, à l’apprentissage et au transfert de représentations, au méta-apprentissage ainsi qu’à l’apprentissage multitâche. Il s’intéresse également aux approches d’optimisation basées sur des modèles probabilistes ainsi qu’aux algorithmes évolutionnaires, entre autres pour l’optimisation boîte noire et la programmation automatique. Une part importante de ses travaux porte également sur la mise en pratique de ces techniques dans des domaines comme la vision numérique, la microscopie, la santé, l’énergie et les transports.

Étudiants actuels

Frédéric Beaupré

Doctorat - Université Laval

Catherine Bouchard

Doctorat - Université Laval

Olivier Bussière

Maîtrise recherche - Université Laval

Cynthia García Ybarra

Maîtrise recherche - Université Laval

Sara Karami

Doctorat - Université Laval

Nayoung Kwon

Doctorat - Université Laval

Benjamin Léger

Doctorat - Université Laval

Samy Mammeri

Stagiaire de recherche - Université Laval

Doctorat - Université Laval

Fatemeh Nourilenjan Nokabadi

Doctorat - Université Laval

Doctorat - Université Laval

Adam Tupper

Doctorat - Université Laval

Publications

Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare

Adam Tupper

2025-10-14

ArXiv (prépublication)

Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare

Adam Tupper

Foundation models open up new possibilities for the use of AI in healthcare. However, even when pre-trained on health data, they still need … (voir plus)to be fine-tuned for specific downstream tasks. Furthermore, although foundation models reduce the amount of training data required to achieve good performance, obtaining sufficient data is still a challenge. This is due, in part, to restrictions on sharing and aggregating data from different sources to protect patients'privacy. One possible solution to this is to fine-tune foundation models via federated learning across multiple participating clients (i.e., hospitals, clinics, etc.). In this work, we propose a new personalized federated fine-tuning method that learns orthogonal LoRA adapters to disentangle general and client-specific knowledge, enabling each client to fully exploit both their own data and the data of others. Our preliminary results on real-world federated medical imaging tasks demonstrate that our approach is competitive against current federated fine-tuning methods.

2025-10-14

ArXiv (prépublication)

A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy

Rishika Bhagwatkar

Yann Batiste Pequignot

Ola Ahmad

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations … (voir plus)was pursued by training models from scratch (i.e., with random initializations) using specialized loss ob- jectives. Recently, robust fine-tuning has emerged as a more efficient alternative: instead of training from scratch, pretrained models are adapted to maximize pre- dictive performance and robustness. To conduct robust fine-tuning, practitioners design an optimization strategy that includes the model update protocol (e.g., full or partial) and the specialized loss objective. Additional design choices include the architecture type and size, and the pretrained representation. These design choices affect robust generalization, which is the model’s ability to maintain performance when exposed to new and unseen perturbations at test time. Understanding how these design choices influence generalization remains an open question with signif- icant practical implications. In response, we present an empirical study spanning 6 datasets, 40 pretrained architectures, 2 specialized losses, and 3 adaptation proto- cols — yielding 1, 440 training configurations and 7, 200 robustness measurements across five perturbation types. To our knowledge, this is the most diverse and comprehensive benchmark of robust fine-tuning to date. While attention-based architectures and robust pretrained representations are increasingly popular, we find that convolutional neural networks pretrained in a supervised manner on large datasets often perform best. Our analysis both confirms and challenges prior design assumptions, highlighting promising research directions and offering practical guidance.

2025-09-29

NeurIPS.cc/2025/Workshop/Reliable_ML (publié)

A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy

Rishika Bhagwatkar

Yann Batiste Pequignot

Ola Ahmad

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations … (voir plus)was pursued by training models from scratch (i.e., with random initializations) using specialized loss objectives. Recently, robust fine-tuning has emerged as a more efficient alternative: instead of training from scratch, pretrained models are adapted to maximize predictive performance and robustness. To conduct robust fine-tuning, practitioners design an optimization strategy that includes the model update protocol (e.g., full or partial) and the specialized loss objective. Additional design choices include the architecture type and size, and the pretrained representation. These design choices affect robust generalization, which is the model's ability to maintain performance when exposed to new and unseen perturbations at test time. Understanding how these design choices influence generalization remains an open question with significant practical implications. In response, we present an empirical study spanning 6 datasets, 40 pretrained architectures, 2 specialized losses, and 3 adaptation protocols, yielding 1,440 training configurations and 7,200 robustness measurements across five perturbation types. To our knowledge, this is the most diverse and comprehensive benchmark of robust fine-tuning to date. While attention-based architectures and robust pretrained representations are increasingly popular, we find that convolutional neural networks pretrained in a supervised manner on large datasets often perform best. Our analysis both confirms and challenges prior design assumptions, highlighting promising research directions and offering practical guidance.

2025-09-29

NeurIPS.cc/2025/Workshop/Reliable_ML (publié)

doi.org

High-order Component Attribution via Kolmogorov-Arnold Networks

Samy Mammeri

Component attribution methods provide insight into how parts of deep learning models, such as convolutional filters and attention heads, inf… (voir plus)luence model predictions. Despite their successes, existing attribution approaches typically assume component effects are additive and independent, neglecting complex interactions among components. Capturing these relations between components is crucial for a better mechanistic understanding of these models. In this work, we improve component attribution (COAR) by replacing the linear counterfactual estimator with a Kolmogorov–Arnold Network (KAN) surrogate fitted to example‑wise perturbation–response data. Then, a symbolic approximation of the learned KAN lets us compute mixed partial derivatives that captures and makes explicit high‑order component interactions that linear methods are missing. These symbolic expressions facilitate future integration with formal verification methods, enabling richer counterfactual analyses of internal model behavior. Preliminary results on standard image classification models demonstrate that our approach improves the accuracy of predicted counterfactuals and enable extraction of higher-order component interactions compared to linear attribution methods.

2025-09-29

NeurIPS.cc/2025/Workshop/MechInterp (poster)

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

Sabyasachi Sahoo

Yann Batiste Pequignot

Frederic Precioso

Fine-tuning pretrained models is the standard approach in current machine learning practice, but simultaneously achieving adversarial robust… (voir plus)ness to adversarial examples remains a challenge. Despite the abundance of non-robust pretrained models in open-source repositories, their use for Robust Fine-Tuning (RFT) remains understudied. This work aims to bridge this knowledge gap by systematically examining RFT from such models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub \emph{suboptimal transfer}. In fact, we find that fine-tuning using a robust objective impedes task alignment at the beginning of training and eventually prevents optimal transfer. To promote optimal transfer, we propose \emph{Epsilon-Scheduling}, a simple heuristic scheduling over perturbation strength. Additionally, we introduce \emph{expected robustness}, a metric that measures performance across a range of perturbations. Experiments on six pretrained models and five datasets show that \emph{Epsilon-Scheduling} prevents \emph{suboptimal transfer} and consistently improves the expected robustness.

2025-09-29

NeurIPS.cc/2025/Workshop/Reliable_ML (publié)

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling

Sabyasachi Sahoo

Yann Batiste Pequignot

Ola Ahmad

Audrey Durand

Frederic Precioso

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims… (voir plus) to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples, remains challenging. Despite the abundance of non-robust pretrained models in open-source repositories, their potential for RFT is less understood. We address this knowledge gap by systematically examining RFT from such non-robust models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub \emph{suboptimal transfer}. In challenging scenarios (eg, difficult tasks, high perturbation), the resulting performance can be so low that it may be considered a transfer failure. We find that fine-tuning using a robust objective impedes task adaptation at the beginning of training and eventually prevents optimal transfer. However, we propose a novel heuristic, \emph{Epsilon-Scheduling}, a schedule over perturbation strength used during training that promotes optimal transfer. Additionally, we introduce \emph{expected robustness}, a metric that captures performance across a range of perturbations, providing a more comprehensive evaluation of the accuracy-robustness trade-off for diverse models at test time. Extensive experiments on a wide range of configurations (six pretrained models and five datasets) show that \emph{Epsilon-Scheduling} successfully prevents \emph{suboptimal transfer} and consistently improves expected robustness.

2025-09-27

ArXiv (prépublication)

doi.org

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling

Sabyasachi Sahoo

Yann Batiste Pequignot

Ola Ahmad

Audrey Durand

Frederic Precioso

2025-09-27

ArXiv (prépublication)

Conditional Adversarial Random Forest for Synthetic Electronic Health Record Generation

Cynthia García Ybarra

2025-09-22

NeurIPS.cc/2025/Workshop/WiML (publié)

A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy

Rishika Bhagwatkar

Yann Batiste Pequignot

Ola Ahmad

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations … (voir plus)was pursued by training models from scratch (i.e., with random initializations) using specialized loss objectives. Recently, robust fine-tuning has emerged as a more efficient alternative: instead of training from scratch, pretrained models are adapted to maximize predictive performance and robustness. To conduct robust fine-tuning, practitioners design an optimization strategy that includes the model update protocol (e.g., full or partial) and the specialized loss objective. Additional design choices include the architecture type and size, and the pretrained representation. These design choices affect robust generalization, which is the model's ability to maintain performance when exposed to new and unseen perturbations at test time. Understanding how these design choices influence generalization remains an open question with significant practical implications. In response, we present an empirical study spanning 6 datasets, 40 pretrained architectures, 2 specialized losses, and 3 adaptation protocols, yielding 1,440 training configurations and 7,200 robustness measurements across five perturbation types. To our knowledge, this is the most diverse and comprehensive benchmark of robust fine-tuning to date. While attention-based architectures and robust pretrained representations are increasingly popular, we find that convolutional neural networks pretrained in a supervised manner on large datasets often perform best. Our analysis both confirms and challenges prior design assumptions, highlighting promising research directions and offering practical guidance.

2025-08-12

ArXiv (prépublication)

doi.org

Enhancing STED Microscopy via Fluorescence Lifetime Unmixing and Filtering in Two-Species SPLIT-STED

Andréanne Deschênes

Antoine Ollier

Marie Lafontaine

Albert Michaud-Gagnon

Jeffrey-Gabriel Steavan Santiague

Anthony Bilodeau