67 citations · 189 across the 24 of their papers we have counts for
24 papers
Reliably Detecting Model Failures in Deployment Without Labels
Viet Nguyen, Changjian Shui, Vijay Giri +4
The distribution of data changes over time; models operating in dynamic environments need retraining. But knowing when to retrain, without access to labels, is an open challenge si…
Intersectional Unfairness Discovery
Gezheng Xu, Qi Chen, Charles Ling +2
AI systems have been shown to produce unfair results for certain subgroups of population, highlighting the need to understand bias on certain sensitive attributes. Current research…
Generalizing across Temporal Domains with Koopman Operators
Qiuhao Zeng, Wei Wang, Fan Zhou +7
In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. Thi…
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…
Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
Changjian Shui, Justin Szeto, Raghav Mehta +2
Trustworthy deployment of deep learning medical imaging models into real-world clinical practice requires that they be calibrated. However, models that are well calibrated overall…
Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis
Raghav Mehta, Changjian Shui, Tal Arbel
Although deep learning (DL) models have shown great success in many medical image analysis tasks, deployment of the resulting models into real clinical contexts requires: (1) that…
On Learning Fairness and Accuracy on Multiple Subgroups
Changjian Shui, Gezheng Xu, Qi Chen +5
We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenar…
Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors
Anjun Hu, Jean-Pierre R. Falet, Brennan S. Nichyporuk +4
We propose a hierarchically structured variational inference model for accurately disentangling observable evidence of disease (e.g. brain lesions or atrophy) from subject-specific…
Information Gain Sampling for Active Learning in Medical Image Classification
Raghav Mehta, Changjian Shui, Brennan Nichyporuk +1
Large, annotated datasets are not widely available in medical image analysis due to the prohibitive time, costs, and challenges associated with labelling large datasets. Unlabelled…
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…
Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis
Qi Chen, Changjian Shui, Mario Marchand
We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. Concretely, our analysis proposes a generic understanding of both the c…
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…
Interventional Domain Adaptation
Jun Wen, Changjian Shui, Kun Kuang +4
Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability through d…
Beyond -Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence
Changjian Shui, Qi Chen, Jun Wen +3
We reveal the incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on -divergence. Conc…
Domain Generalization via Optimal Transport with Metric Similarity Learning
Fan Zhou, Zhuqing Jiang, Changjian Shui +2
Generalizing knowledge to unseen domains, where data and labels are unavailable, is crucial for machine learning models. We tackle the domain generalization problem to learn from m…
Discriminative Active Learning for Domain Adaptation
Fan Zhou, Changjian Shui, Bincheng Huang +2
Domain Adaptation aiming to learn a transferable feature between different but related domains has been well investigated and has shown excellent empirical performances. Previous w…
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…
Toward Metrics for Differentiating Out-of-Distribution Sets
Mahdieh Abbasi, Changjian Shui, Arezoo Rajabi +2
Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, som…
A Principled Approach for Learning Task Similarity in Multitask Learning
Changjian Shui, Mahdieh Abbasi, Louis-Émile Robitaille +2
Multitask learning aims at solving a set of related tasks simultaneously, by exploiting the shared knowledge for improving the performance on individual tasks. Hence, an important…
Accumulating Knowledge for Lifelong Online Learning
Changjian Shui, Ihsen Hedhli, Christian Gagné
Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called k…
Diversity regularization in deep ensembles
Changjian Shui, Azadeh Sadat Mozafari, Jonathan Marek +2
Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it has been report…