Fairness and Unfairness in Binary and Multiclass Classification: Quantifying, Calculating, and Bounding

원문 초록

We propose a new interpretable measure of unfairness, that allows providing a quantitative analysis of classifier fairness, beyond a dichotomous fair/unfair distinction. We show how this measure can be calculated when the classifier's conditional confusion matrices are known. We further propose methods for auditing classifiers for their fairness when the confusion matrices cannot be obtained or even estimated. Our approach lower-bounds the unfairness of a classifier based only on aggregate statistics, which may be provided by the owner of the classifier or collected from freely available data. We use the equalized odds criterion, which we generalize to the multiclass case. We report experiments on data sets representing diverse applications, which demonstrate the effectiveness and the wide range of possible uses of the proposed methodology. An implementation of the procedures proposed in this paper and as the code for running the experiments are provided in https://github.com/sivansabato/unfairness.