activity
20242026
collaborators

5 papers

cs.CV2026

SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence

Bowei Tian, Yexiao He, Ziyao Wang +3

Deep learning models exhibit fairness concerns when predictions are inadvertently influenced by sensitive attributes. However, existing attempts to make Path-Specific Counterfactua…

cs.LG2026

FairSAM: Fair Classification on Corrupted Image Data Through Sharpness-Aware Minimization

Yucong Dai, Jie Ji, Xiaolong Ma +1

Image classification models trained on clean data often degrade sharply when exposed to corrupted test or deployment data, such as images with impulse noise, Gaussian noise, or env…

cs.LG2025

Integrating Fairness and Model Pruning Through Bi-level Optimization

Yucong Dai, Gen Li, Feng Luo +2

Deep neural networks have achieved exceptional results across a range of applications. As the demand for efficient and sparse deep learning models escalates, the significance of mo…

cs.LG2025

Towards counterfactual fairness through auxiliary variables

Bowei Tian, Ziyao Wang, Shwai He +5

The challenge of balancing fairness and predictive accuracy in machine learning models, especially when sensitive attributes such as race, gender, or age are considered, has motiva…

cs.CL2024

SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning

Yexiao He, Ziyao Wang, Zheyu Shen +5

The pre-trained Large Language Models (LLMs) can be adapted for many downstream tasks and tailored to align with human preferences through fine-tuning. Recent studies have discover…