License: Creative Commons Attribution 3.0 Unported license (CC-BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.FORC.2020.7
URN: urn:nbn:de:0030-drops-120235
URL: https://drops.dagstuhl.de/opus/volltexte/2020/12023/
Go to the corresponding LIPIcs Volume Portal


Dwork, Cynthia ; Ilvento, Christina ; Jagadeesan, Meena

Individual Fairness in Pipelines

pdf-format:
LIPIcs-FORC-2020-7.pdf (0.7 MB)


Abstract

It is well understood that a system built from individually fair components may not itself be individually fair. In this work, we investigate individual fairness under pipeline composition. Pipelines differ from ordinary sequential or repeated composition in that individuals may drop out at any stage, and classification in subsequent stages may depend on the remaining "cohort" of individuals. As an example, a company might hire a team for a new project and at a later point promote the highest performer on the team. Unlike other repeated classification settings, where the degree of unfairness degrades gracefully over multiple fair steps, the degree of unfairness in pipelines can be arbitrary, even in a pipeline with just two stages. Guided by a panoply of real-world examples, we provide a rigorous framework for evaluating different types of fairness guarantees for pipelines. We show that naïve auditing is unable to uncover systematic unfairness and that, in order to ensure fairness, some form of dependence must exist between the design of algorithms at different stages in the pipeline. Finally, we provide constructions that permit flexibility at later stages, meaning that there is no need to lock in the entire pipeline at the time that the early stage is constructed.

BibTeX - Entry

@InProceedings{dwork_et_al:LIPIcs:2020:12023,
  author =	{Cynthia Dwork and Christina Ilvento and Meena Jagadeesan},
  title =	{{Individual Fairness in Pipelines}},
  booktitle =	{1st Symposium on Foundations of Responsible Computing (FORC 2020)},
  pages =	{7:1--7:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-142-9},
  ISSN =	{1868-8969},
  year =	{2020},
  volume =	{156},
  editor =	{Aaron Roth},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2020/12023},
  URN =		{urn:nbn:de:0030-drops-120235},
  doi =		{10.4230/LIPIcs.FORC.2020.7},
  annote =	{Keywords: algorithmic fairness, fairness under composition, pipelines}
}

Keywords: algorithmic fairness, fairness under composition, pipelines
Collection: 1st Symposium on Foundations of Responsible Computing (FORC 2020)
Issue Date: 2020
Date of publication: 18.05.2020


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