Walk a Mile in Their Shoes: a New Fairness Criterion for Machine Learning

TL;DR

This paper introduces a new group-level fairness criterion for machine learning inspired by empathy, assessing how entire groups would fare under different protected attribute conditions, and addresses covariate correlation issues.

Contribution

It proposes a novel group-based counterfactual fairness criterion and provides an empirical framework to evaluate it across various datasets.

Findings

Introduces a group-level fairness measure based on counterfactual scenarios.

Addresses covariate correlation issues in fairness assessments.

Provides empirical results demonstrating the approach's effectiveness.

Abstract

The old empathetic adage, ``Walk a mile in their shoes,'' asks that one imagine the difficulties others may face. This suggests a new ML counterfactual fairness criterion, based on a \textit{group} level: How would members of a nonprotected group fare if their group were subject to conditions in some protected group? Instead of asking what sentence would a particular Caucasian convict receive if he were Black, take that notion to entire groups; e.g. how would the average sentence for all White convicts change if they were Black, but with their same White characteristics, e.g. same number of prior convictions? We frame the problem and study it empirically, for different datasets. Our approach also is a solution to the problem of covariate correlation with sensitive attributes.