Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback

Abstract

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.

Cite

Text

Zhou et al. "Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback." Transactions on Machine Learning Research, 2026.

Markdown

[Zhou et al. "Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback." Transactions on Machine Learning Research, 2026.](https://mlanthology.org/tmlr/2026/zhou2026tmlr-online/)

BibTeX

@article{zhou2026tmlr-online,
  title     = {{Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback}},
  author    = {Zhou, Quan and Marecek, Jakub and Shorten, Robert Noel},
  journal   = {Transactions on Machine Learning Research},
  year      = {2026},
  url       = {https://mlanthology.org/tmlr/2026/zhou2026tmlr-online/}
}