7 papers
Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learning
Ziming Wang, Changwu Huang, Ke Tang +2
Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods have been introduced to improve…
CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness
Ziming Wang, Yinghua Yao, Changwu Huang +2
Chain-of-thought (CoT) reasoning is widely used to improve both the performance and interpretability of large language models (LLMs), yet the generated reasoning may not faithfully…
Integrating Knowledge Distillation Methods: A Sequential Multi-Stage Framework
Yinxi Tian, Changwu Huang, Ke Tang +1
Knowledge distillation (KD) transfers knowledge from large teacher models to compact student models, enabling efficient deployment on resource constrained devices. While diverse KD…
Online Regime-aware Calibration for Black-box Social Simulators via Posterior-assisted Evolutionary Dynamic Optimization
Peng Yang, Zhenhua Yang, Boquan Jiang +3
Evolutionary dynamic optimization (EDO) commonly assumes that environmental changes can be detected from fitness variations and handled through random re-initialization, historical…
On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning
Zhi Yang, Changwu Huang, Ke Tang +1
While significant progress has been made in conventional fairness-aware machine learning (ML) and differentially private ML (DPML), the fairness of privacy protection across groups…
Procedural Fairness and Its Relationship with Distributive Fairness in Machine Learning
Ziming Wang, Changwu Huang, Ke Tang +1
Fairness in machine learning (ML) has garnered significant attention in recent years. While existing research has predominantly focused on the distributive fairness of ML models, t…