DROPS

Document

DOI: 10.4230/LIPIcs.CP.2026.15

Fairness of Classifiers in the Presence of Constraints Between Features

Authors: Martin C. Cooper and Imane Bousdira

Published in: LIPIcs, Volume 379, 32nd International Conference on Principles and Practice of Constraint Programming (CP 2026)

Abstract

In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as gender. Unfortunately, when constraints exist between features, such dependencies can be obscured by the constraints. To avoid this problem, we propose that a decision be considered fair if it has a fair explanation. We define a fair explanation as a prime-implicant reason for the decision that does not contain any protected feature (where the constraints are taken into account in the definition of prime-implicant). Surprisingly, ignoring constraints can completely change the fairness of a decision (according to this definition) even in the absence of constraints between protected and unprotected features. Three possible definitions of fairness of a classifier are that for all its decisions (1) there are only fair explanations, (2) there is at least one fair explanation, or (3) changing protected features does not change the outcome. We identify the relationships between these different definitions of fairness and study the computational complexity of testing fairness of classifiers.

Cite as

Martin C. Cooper and Imane Bousdira. Fairness of Classifiers in the Presence of Constraints Between Features. In 32nd International Conference on Principles and Practice of Constraint Programming (CP 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 379, pp. 15:1-15:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{cooper_et_al:LIPIcs.CP.2026.15,
  author =	{Cooper, Martin C. and Bousdira, Imane},
  title =	{{Fairness of Classifiers in the Presence of Constraints Between Features}},
  booktitle =	{32nd International Conference on Principles and Practice of Constraint Programming (CP 2026)},
  pages =	{15:1--15:18},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-432-1},
  ISSN =	{1868-8969},
  year =	{2026},
  volume =	{379},
  editor =	{Beldiceanu, Nicolas},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2026.15},
  URN =		{urn:nbn:de:0030-drops-266480},
  doi =		{10.4230/LIPIcs.CP.2026.15},
  annote =	{Keywords: fairness, constraints, abductive explanation, computational complexity}
}

Search Results

Documents authored by Bousdira, Imane

Fairness of Classifiers in the Presence of Constraints Between Features

Abstract

Cite as

Thanks for your feedback!

Could not send message