On Disentangled and Locally Fair Representations

TL;DR

This paper introduces a method for fair classification by learning disentangled representations that are locally fair, ensuring neighborhood balance in sensitive attributes while maintaining accuracy.

Contribution

It proposes a novel approach combining disentangled and local fairness constraints to improve fair classification in sensitive contexts.

Findings

Effective in balancing sensitive attributes locally

Improves fairness in income and re-incarceration predictions

Demonstrates necessity of disentanglement and local fairness

Abstract

We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. This problem is tackled through the lens of disentangled and locally fair representations. We learn a locally fair representation, such that, under the learned representation, the neighborhood of each sample is balanced in terms of the sensitive attribute. For instance, when a decision is made to hire an individual, we ensure that the $K$ most similar hired individuals are racially balanced. Crucially, we ensure that similar individuals are found based on attributes not correlated to their race. To this end, we disentangle the embedding space into two representations. The first of which is correlated with the sensitive attribute while the second is not. We apply our local fairness objective only to the second, uncorrelated, representation. Through a set of experiments, we demonstrate the necessity of both disentangled and local fairness for obtaining fair and accurate representations. We evaluate our method on real-world settings such as predicting income and re-incarceration rate and demonstrate the advantage of our method.