Show Summary Details

Page of

PRINTED FROM OXFORD HANDBOOKS ONLINE (www.oxfordhandbooks.com). © Oxford University Press, 2018. All Rights Reserved. Under the terms of the licence agreement, an individual user may print out a PDF of a single chapter of a title in Oxford Handbooks Online for personal use (for details see Privacy Policy and Legal Notice).

date: 07 May 2021

Abstract and Keywords

This chapter provides an alternate source of intuition about fairness criteria using probabilistic directed acyclic graphical models. A substantial portion of the literature on fairness in algorithms proposes, analyzes, and operationalizes simple formulaic criteria for assessing fairness. Two of these criteria—Equalized Odds and Calibration by Group—have gained significant attention not only for their simplicity and intuitive appeal but also for their incompatibility. Graphical models have been used to motivate and expose fairness criteria in other works, especially those which work with explicitly causal criteria for fairness. The chapter then argues that graphical models provide an invaluable source of intuition even in noncausal scenarios and reveal the weakness of Equalized Odds.

Keywords: fairness criteria, graphical models, algorithms, Equalized Odds, Calibration by Group, causality, noncausal scenarios

Access to the complete content on Oxford Handbooks Online requires a subscription or purchase. Public users are able to search the site and view the abstracts and keywords for each book and chapter without a subscription.

Please subscribe or login to access full text content.

If you have purchased a print title that contains an access token, please see the token for information about how to register your code.

For questions on access or troubleshooting, please check our FAQs, and if you can''t find the answer there, please contact us.