Avoiding Disparity Amplification under Different Worldviews

TitleAvoiding Disparity Amplification under Different Worldviews
Publication TypeConference Paper
Year of Publication2021
AuthorsYeom, S., & Tschantz M.
Published inFAccT '21: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency
Page(s)273-283
Date PublishedMarch 2021
Abstract

We mathematically compare four competing definitions of group-level nondiscrimination: demographic parity, equalized odds, predictive parity, and calibration. Using the theoretical framework of Friedler et al., we study the properties of each definition under various worldviews, which are assumptions about how, if at all, the observed data is biased. We argue that different worldviews call for different definitions of fairness, and we specify the worldviews that, when combined with the desire to avoid a criterion for discrimination that we call disparity amplification, motivate demographic parity and equalized odds. We also argue that predictive parity and calibration are insufficient for avoiding disparity amplification because predictive parity allows an arbitrarily large inter-group disparity and calibration is not robust to post-processing. Finally, we define a worldview that is more realistic than the previously considered ones, and we introduce a new notion of fairness that corresponds to this worldview.

URLhttps://dl.acm.org/doi/10.1145/3442188.3445892
DOI10.1145/3442188.3445892