Learning Time-Varying Convexifications of Multiple Fairness Measures

TMLR Paper6264 Authors

Abstract: 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 regularizers 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.

Submission Type: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission: The paper has been extensively rewritten to simplify notation and explanations, making the main contributions clear and easy to follow. Notation has been standardized throughout, and key results and algorithms are now presented more clearly. Several recent references have been added to better situate our work within the current literature. Figures and examples have been adjusted for clarity.

Assigned Action Editor: ~Ian_A._Kash1

Submission Number: 6264