How Do the Score Distributions of Subpopulations Influence Fairness Notions?

Research output: Chapter in Book/Report/Conference proceedingConference paperResearch

Abstract

Automated decisions based on trained algorithms influence human life in an increasingly far-reaching way. In recent years, it has become clear that these decisions are often accompanied by bias and unfair treatment of different subpopulations.Meanwhile, several notions of fairness circulate in the scientific literature, with trade-offs between profit and fairness and between fairness metrics among themselves. Based on both analytical calculations and numerical simulations, we show in this study that some profit-fairness trade-offs and fairness-fairness trade-offs depend substantially on the underlying score distributions given to subpopulations and we present two complementary perspectives to visualize this influence. We further show that higher symmetry in scores of subpopulations can significantly reduce the trade-offs between fairness notions within a given acceptable strictness, even when sacrificing expressiveness. Our exploratory study may help to understand how to overcome the strict mathematical statements about the statistical incompatibility of certain fairness notions.

Original languageEnglish
Title of host publicationHow Do the Score Distributions of Subpopulations Influence Fairness Notions?
PublisherAssociation for Computing Machinery (ACM)
Pages767-776
Number of pages10
ISBN (Electronic)978-1-4503-8473-5/21/05
DOIs
Publication statusPublished - 21 Jul 2021
Event2021 AAAI/ACM Conference on AI, Ethics, and Society - Online
Duration: 19 May 202121 May 2021
https://www.aies-conference.com/2021/

Publication series

NameAIES 2021 - Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society

Conference

Conference2021 AAAI/ACM Conference on AI, Ethics, and Society
Abbreviated titleAIES 2021
Period19/05/2121/05/21
Internet address

Keywords

  • Algorithmic fairness
  • fairness trade-offs
  • score distributions
  • decisionmaking algorithms

Fingerprint

Dive into the research topics of 'How Do the Score Distributions of Subpopulations Influence Fairness Notions?'. Together they form a unique fingerprint.

Cite this