Group Fairness: Independence Revisited

TL;DR

This paper reevaluates the arguments against using independence (statistical parity) as a measure of group fairness, finding the case against it weak and highlighting its important role in fairness considerations.

Contribution

It critically revisits and challenges existing arguments against independence, emphasizing its significance in fairness measures and discussing how to balance different fairness criteria.

Findings

Arguments against independence are weaker than previously thought

Independence plays a distinctive role in fairness considerations

Balancing multiple fairness criteria is essential

Abstract

This paper critically examines arguments against independence, a measure of group fairness also known as statistical parity and as demographic parity. In recent discussions of fairness in computer science, some have maintained that independence is not a suitable measure of group fairness. This position is at least partially based on two influential papers (Dwork et al., 2012, Hardt et al., 2016) that provide arguments against independence. We revisit these arguments, and we find that the case against independence is rather weak. We also give arguments in favor of independence, showing that it plays a distinctive role in considerations of fairness. Finally, we discuss how to balance different fairness considerations.