LGAIAug 19, 2025

Learning Time-Varying Convexifications of Multiple Fairness Measures

arXiv:2508.14311v1h-index: 5
Originality Incremental advance
AI Analysis

This addresses the challenge of balancing multiple fairness notions in machine learning models, which is incremental as it builds on existing fairness regularization approaches.

The paper tackles the problem of learning time-varying convex combinations of multiple fairness measures with limited graph-structured feedback, and proposes a method to adaptively adjust fairness regularizer weights on the fly.

There is an increasing appreciation that one may need to consider multiple measures of fairness, e.g., considering multiple group and individual fairness notions. The relative weights of the fairness regularisers are a priori unknown, may be time varying, and need to be learned on the fly. We consider the learning of time-varying convexifications of multiple fairness measures with limited graph-structured feedback.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes