Changjian Shui

alt text

Ph.D.
Université Laval, Mila
E-mail: changjian DOT shui AT mail DOT mcgill DOT ca
[Google Scholar] [Twitter]

About me

I completed my Postdoc in McGill University/Mila, under the supervision of Prof. Tal Arbel. I obtained Ph.D. degree from Université Laval, under the supervision of Prof. Christian Gagné and Prof. Boyu Wang.

Research Interests Learning limited labeled data (transfer learning, meta-learning, multitask learning, active learning); Trustworthy machine learning (algorithmic fairness, robustness, out-of-distribution generalization); Applied machine learning (data-mining, healthcare).

Recent news

  • [Sep 2023] Our paper “On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm” has been accepted in NeurIPS 2023.

  • [Jul 2023] I am selected as an Expert Reviewer in TMLR (Transactions on Machine Learning Research)!

  • [May 2023] Our paper “Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis” has been accepted in MICCAI (Early acceptance, 14% of submissions).

  • [Mar 2023] Our paper “Towards More General Loss and Setting in Unsupervised Domain Adaptation” has been accepted in IEEE Transactions on Knowledge and Data Engineering (TKDE).

  • [Oct 2022] Our paper “On Learning Fairness and Accuracy on Multiple Subgroups” has been accepted in NeurIPS 2022 (Spotlight presentation).

  • [May 2022] Our paper “Fair Representation Learning through Implicit Path Alignment” has been accepted in ICML 2022. See our blog for details!