4 papers
Joint Distribution-Informed Shapley Values for Sparse Counterfactual Explanations
Lei You, Yijun Bian, Lele Cao
Counterfactual explanations (CE) aim to reveal how small input changes flip a model's prediction, yet many methods modify more features than necessary, reducing clarity and actiona…
FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation
Lin Zhu, Yijun Bian, Lei You
Ensuring fairness in machine learning models is critical, particularly in high-stakes domains where biased decisions can lead to serious societal consequences. Existing preprocessi…
Algorithmic Fairness: Not a Purely Technical but Socio-Technical Property
Yijun Bian, Lei You, Yuya Sasaki +2
The rapid trend of deploying artificial intelligence (AI) and machine learning (ML) systems in socially consequential domains has raised growing concerns about their trustworthines…
Towards Trustworthy Federated Learning
Alina Basharat, Yijun Bian, Ping Xu +1
This paper develops a comprehensive framework to address three critical trustworthy challenges in federated learning (FL): robustness against Byzantine attacks, fairness, and priva…