Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees

TL;DR

This paper introduces a versatile meta-algorithm for fair classification that handles multiple fairness constraints with provable guarantees, unifying prior approaches and enabling fairness metrics previously unaddressed.

Contribution

It presents a new meta-algorithm that reduces complex fairness-constrained classification problems to convex constraint problems with theoretical guarantees.

Findings

Achieves near-perfect fairness on various metrics

Maintains high accuracy with fairness constraints

Unifies and extends prior fair classification methods

Abstract

Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification algorithms in various social contexts. Several recent works have focused on fairness with respect to a specific metric, modeled the corresponding fair classification problem as a constrained optimization problem, and developed tailored algorithms to solve them. Despite this, there still remain important metrics for which we do not have fair classifiers and many of the aforementioned algorithms do not come with theoretical guarantees; perhaps because the resulting optimization problem is non-convex. The main contribution of this paper is a new meta-algorithm for classification that takes as input a large class of fairness constraints, with respect to multiple non-disjoint sensitive attributes, and which comes with provable guarantees. This is achieved by first developing a meta-algorithm for a large family of classification problems with convex constraints, and then showing that classification problems with general types of fairness constraints can be reduced to those in this family. We present empirical results that show that our algorithm can achieve near-perfect fairness with respect to various fairness metrics, and that the loss in accuracy due to the imposed fairness constraints is often small. Overall, this work unifies several prior works on fair classification, presents a practical algorithm with theoretical guarantees, and can handle fairness metrics that were previously not possible.