Beyond Demographic Parity: Redefining Equal Treatment

arXiv (Cornell University)

Abstract

Liberalism-oriented political philosophy reasons that all individuals should be treated equally independently of their protected characteristics. Related work in machine learning has translated the concept of \emph{equal treatment} into terms of \emph{equal outcome} and measured it as \emph{demographic parity} (also called \emph{statistical parity}). Our analysis reveals that the two concepts of equal outcome and equal treatment diverge; therefore, demographic parity does not faithfully represent the notion of \emph{equal treatment}. We propose a new formalization for equal treatment by (i) considering the influence of feature values on predictions, such as computed by Shapley values decomposing predictions across its features, (ii) defining distributions of explanations, and (iii) comparing explanation distributions between populations with different protected characteristics. We show the theoretical properties of our notion of equal treatment and devise a classifier two-sample test based on the AUC of an equal treatment inspector. We study our formalization of equal treatment on synthetic and natural data. We release \texttt{explanationspace}, an open-source Python package with methods and tutorials.

Authors 4

1. Carlos Mougan

   University of Southampton

   Affiliation as printed

   University of Southampton United Kingdom

2. Laura State

   University of Pisa · Scuola Normale Superiore

   Affiliation as printed

   Scuola Normale Superiore University of Pisa , Italy

3. Salvatore Ruggieri

   University of Pisa

   Affiliation as printed

   University of Pisa Italy

4. Steffen Staab

   University of Stuttgart · University of Southampton

   Affiliation as printed

   University of Southampton University of Stuttgart , Germany