Learning Fair Representations with High-Confidence Guarantees

Yuhong Luo, Austin Hoag, Philip S. Thomas

Keywords: Fairness, Representation Learning, High-Confidence Fairness Guarantees

TL;DR: We introduce a representation learning framework that provides high-confidence fairness guarantees.

Abstract:

Representation learning is increasingly employed to generate representations that are predictive across multiple downstream tasks.
The development of representation learning algorithms that provide strong fairness guarantees is thus important because it can prevent unfairness towards disadvantaged groups for $all$ downstream prediction tasks.
In this paper, we formally define the problem of learning representations that are fair with high confidence.
We then introduce the $\textbf{F}$air $\textbf{R}$epresentation learning with high-confidence $\textbf{G}$uarantees (FRG) framework, which provides high-confidence guarantees for limiting unfairness across all downstream models and tasks, with user-defined upper bounds.
After proving that FRG ensures fairness for all downstream models and tasks with high probability, we present empirical evaluations that demonstrate FRG's effectiveness at upper bounding unfairness for multiple downstream models and tasks.

Primary Area: societal considerations including fairness, safety, privacy

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5987