There is an increasing need to enforce multiple, often competing, measures of fairness within automated decision systems. The appropriate weighting of these fairness objectives is typically unknown a priori, may change over time and, in our setting, must be learned adaptively through sequential interactions. In this work, we address this challenge in a bandit setting, where decisions are made with graph-structured feedback.
@article{arxiv.2508.14311,
title = {Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback},
author = {Quan Zhou and Jakub Marecek and Robert Shorten},
journal= {arXiv preprint arXiv:2508.14311},
year = {2026}
}
Comments
Published in Transactions on Machine Learning Research (TMLR), 2026. OpenReview: https://openreview.net/forum?id=y8iWuDZtEw