Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback

Quan Zhou, Jakub Marecek, Robert Noel Shorten

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.

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

Changes Since Last Submission:

In this camera-ready version, no technical changes have been made to the manuscript. The following updates were implemented:

1. A link to the GitHub repository for the experimental code has been added.
2. All previously highlighted revision text has been changed back to black.
3. Author information and acknowledgments have been updated.

Code: https://github.com/Quan-Zhou/graph-feedback-fair-online-learning

Assigned Action Editor: ~Ian_A._Kash1

Submission Number: 6264