Everything is Relative: Understanding Fairness with Optimal Transport

TL;DR

This paper introduces an optimal transport-based framework for analyzing fairness in automated decision systems, providing interpretable insights into bias and discrimination beyond traditional binary fairness metrics.

Contribution

It presents a novel approach using optimal transport to explore and quantify bias, enabling detailed analysis of individual, subgroup, and group fairness.

Findings

Recovers known discrimination examples

Detects unfairness missed by other metrics

Explores recourse opportunities for affected individuals

Abstract

To study discrimination in automated decision-making systems, scholars have proposed several definitions of fairness, each expressing a different fair ideal. These definitions require practitioners to make complex decisions regarding which notion to employ and are often difficult to use in practice since they make a binary judgement a system is fair or unfair instead of explaining the structure of the detected unfairness. We present an optimal transport-based approach to fairness that offers an interpretable and quantifiable exploration of bias and its structure by comparing a pair of outcomes to one another. In this work, we use the optimal transport map to examine individual, subgroup, and group fairness. Our framework is able to recover well known examples of algorithmic discrimination, detect unfairness when other metrics fail, and explore recourse opportunities.