Walk a Mile in Their Shoes: a New Fairness Criterion for Machine Learning
This addresses fairness issues in ML for applications like criminal justice, though it appears incremental by extending existing counterfactual fairness concepts to group-level analysis.
The paper tackles fairness in machine learning by proposing a new group-level counterfactual fairness criterion, which evaluates how nonprotected groups would fare under conditions of protected groups, and demonstrates its application across different datasets.
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.