Bounding the fairness and accuracy of classifiers from population statistics

Sivan Sabato, Elad Yom-Tov

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We consider the study of a classification model whose properties are impossible to estimate using a validation set, either due to the absence of such a set or because access to the classifier, even as a black-box, is impossible. Instead, only aggregate statistics on the rate of positive predictions in each of several sub-populations are available, as well as the true rates of positive labels in each of these sub-populations. We show that these aggregate statistics can be used to lowerbound the discrepancy of a classifier, which is a measure that balances inaccuracy and unfairness. To this end, we define a new measure of unfairness, equal to the fraction of the population on which the classifier behaves differently, compared to its global, ideally fair behavior, as defined by the measure of equalized odds. We propose an efficient and practical procedure for finding the best possible lower bound on the discrepancy of the classifier, given the aggregate statistics, and demonstrate in experiments the empirical tightness of this lower bound, as well as its possible uses on various types of problems, ranging from estimating the quality of voting polls to measuring the effectiveness of patient identification from internet search queries. The code and data are available at https://github.com/ sivansabato/bfa.

Original languageEnglish
Title of host publication37th International Conference on Machine Learning, ICML 2020
EditorsHal Daume, Aarti Singh
PublisherInternational Machine Learning Society (IMLS)
Pages8286-8295
Number of pages10
ISBN (Electronic)9781713821120
StatePublished - 1 Jan 2020
Event37th International Conference on Machine Learning, ICML 2020 - Virtual, Online
Duration: 13 Jul 202018 Jul 2020

Publication series

Name37th International Conference on Machine Learning, ICML 2020
VolumePartF168147-11

Conference

Conference37th International Conference on Machine Learning, ICML 2020
CityVirtual, Online
Period13/07/2018/07/20

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Human-Computer Interaction
  • Software

Fingerprint

Dive into the research topics of 'Bounding the fairness and accuracy of classifiers from population statistics'. Together they form a unique fingerprint.

Cite this