Efficient Fairness-Performance Pareto Front Computation

Mark Kozdoba, Binyamin Perets, Shie Mannor

Keywords: Fairness, fair Representations, Fairness-Performance Pareto Front, Pareto Front, convex concave optimization

TL;DR: This paper evaluates the fairness-performance Pareto front of "fair representations" via concave optimization.

Abstract:

There is a well known intrinsic trade-off between the fairness of a representation and the performance of classifiers derived from the representation.
Due to the complexity of optimisation algorithms in most modern representation learning approaches, for a given method it may be non-trivial to decide whether the obtained fairness-performance curve of the method is optimal, i.e., whether it is close to the true Pareto front for these quantities for the underlying data distribution.

In this paper we propose a new method to compute the optimal Pareto front,
which does not require the training of complex representation models. We show that optimal fair representations possess several useful structural properties, and that these properties enable a reduction of the computation of the Pareto Front to a compact discrete problem. We then also show that these compact approximating problems can be efficiently solved via off-the shelf concave-convex programming methods. Finally, in addition to representations, we show that the new methods may also be used to directly compute the Pareto front of fair classification problems.

Since our approach is independent of the specific model of representations, it may be used as the benchmark to which representation learning algorithms, or classifiers, may be compared. We experimentally evaluate the approach on a number of real world benchmark datasets.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

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/2025/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: 6353