17 citations · 103 across the 24 of their papers we have counts for
13 papers · 1 filter
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
Jonas Ngnawé, Maxime Heuillet, Sabyasachi Sahoo +5
Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to…
A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
Maxime Heuillet, Rishika Bhagwatkar, Jonas Ngnawé +6
Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scra…
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
Jonas Ngnawé, Sabyasachi Sahoo, Yann Pequignot +2
Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to impe…
Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
Jiaqi Li, Yuanhao Lai, Rui Wang +7
Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Ran…
Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Thomas Philippon, Christian Gagné
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this pa…
Evolving Domain Generalization
William Wei Wang, Gezheng Xu, Ruizhi Pu +6
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any…
Fair Representation Learning through Implicit Path Alignment
Changjian Shui, Qi Chen, Jiaqi Li +2
We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-group…
Gap Minimization for Knowledge Sharing and Transfer
Boyu Wang, Jorge Mendez, Changjian Shui +5
Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order to successfully transfer information fro…
Aggregating From Multiple Target-Shifted Sources
Changjian Shui, Zijian Li, Jiaqi Li +3
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different…
On the benefits of representation regularization in invariance based domain generalization
Changjian Shui, Boyu Wang, Christian Gagné
A crucial aspect in reliable machine learning is to design a deployable system in generalizing new related but unobserved environments. Domain generalization aims to alleviate such…
Meta Learning Black-Box Population-Based Optimizers
Hugo Siqueira Gomes, Benjamin Léger, Christian Gagné
The no free lunch theorem states that no model is better suited to every problem. A question that arises from this is how to design methods that propose optimizers tailored to spec…
Deep Active Learning: Unified and Principled Method for Query and Training
Changjian Shui, Fan Zhou, Christian Gagné +1
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. We are providing theoretical insights fr…
Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks
Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Wilson Leão +2
Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making application…