Disparate Conditional Prediction in Multiclass Classifiers

TL;DR

This paper introduces methods to audit multiclass classifiers for fairness by estimating deviations from equalized odds, generalizing the Disparate Conditional Prediction measure to multiclass settings and providing local-optimization estimation techniques.

Contribution

It extends the DCP fairness measure to multiclass classifiers and develops new local-optimization methods for estimating fairness deviations under different data access regimes.

Findings

Methods accurately estimate multiclass DCP.

Techniques detect classifiers with significant unfair treatment.

Experiments validate the effectiveness of the proposed methods.

Abstract

We propose methods for auditing multiclass classifiers for fairness under multiclass equalized odds,by estimating the deviation from equalized odds when the classifier is not completely fair. We generalize to multiclass classifiers the measure of Disparate Conditional Prediction (DCP), originally suggested by Sabato & Yom-Tov (2020) for binary classifiers. DCP is defined as the fraction of the population for which the classifier predicts with conditional prediction probabilities that differ from the closest common baseline. We provide new local-optimization methods for estimating the multiclass DCPunder two different regimes,one in which the conditional confusion matrices for each protected sub-population are known, and one in which these cannot be estimated, for instance, because the classifier is inaccessible or because good-quality individual-level data is not available. These methods can be used to detect classifiers that likely treat a significant fraction of the population unfairly. Experiments demonstrate the accuracy of the methods. Code is provided at https://github.com/sivansabato/DCPmulticlass.