Schloss Dagstuhl - Leibniz-Zentrum für Informatik GmbH Schloss Dagstuhl - Leibniz-Zentrum für Informatik GmbH scholarly article en Yang, Ke; Loftus, Joshua R.; Stoyanovich, Julia https://www.dagstuhl.de/lipics License: Creative Commons Attribution 4.0 license (CC BY 4.0)
when quoting this document, please refer to the following
DOI:
URN: urn:nbn:de:0030-drops-138756
URL:

; ;

Causal Intersectionality and Fair Ranking

pdf-format:


Abstract

In this paper we propose a causal modeling approach to intersectional fairness, and a flexible, task-specific method for computing intersectionally fair rankings. Rankings are used in many contexts, ranging from Web search to college admissions, but causal inference for fair rankings has received limited attention. Additionally, the growing literature on causal fairness has directed little attention to intersectionality. By bringing these issues together in a formal causal framework we make the application of intersectionality in algorithmic fairness explicit, connected to important real world effects and domain knowledge, and transparent about technical limitations. We experimentally evaluate our approach on real and synthetic datasets, exploring its behavior under different structural assumptions.

BibTeX - Entry

@InProceedings{yang_et_al:LIPIcs.FORC.2021.7,
  author =	{Yang, Ke and Loftus, Joshua R. and Stoyanovich, Julia},
  title =	{{Causal Intersectionality and Fair Ranking}},
  booktitle =	{2nd Symposium on Foundations of Responsible Computing (FORC 2021)},
  pages =	{7:1--7:20},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-187-0},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{192},
  editor =	{Ligett, Katrina and Gupta, Swati},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2021/13875},
  URN =		{urn:nbn:de:0030-drops-138756},
  doi =		{10.4230/LIPIcs.FORC.2021.7},
  annote =	{Keywords: fairness, intersectionality, ranking, causality}
}

Keywords: fairness, intersectionality, ranking, causality
Seminar: 2nd Symposium on Foundations of Responsible Computing (FORC 2021)
Issue date: 2021
Date of publication: 31.05.2021
Supplementary Material: Software (Source Code): https://github.com/DataResponsibly/CIFRank archived at: https://archive.softwareheritage.org/swh:1:dir:d16d7e476bfacf0d8c562f2f96b0ead488ad7138


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI