Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification

arXiv1906.05082MaRDI QIDQ6320390

Author name not available (Why is that?)

Publication date: 12 June 2019

Abstract: We study the problem of fair binary classification using the notion of Equal Opportunity. It requires the true positive rate to distribute equally across the sensitive groups. Within this setting we show that the fair optimal classifier is obtained by recalibrating the Bayes classifier by a group-dependent threshold. We provide a constructive expression for the threshold. This result motivates us to devise a plug-in classification procedure based on both unlabeled and labeled datasets. While the latter is used to learn the output conditional probability, the former is used for calibration. The overall procedure can be computed in polynomial time and it is shown to be statistically consistent both in terms of the classification error and fairness measure. Finally, we present numerical experiments which indicate that our method is often superior or competitive with the state-of-the-art methods on benchmark datasets.

Has companion code repository: https://github.com/lucaoneto/NIPS2019_Fairness

This page was built for publication: Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6320390)