Reranking Individuals: The Effect of Fair Classification Within-Groups
ACM Journal on Responsible Computing · 30.06.2026 · 3 (2) · 1-27
DOI: 10.1145/3802540 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Journal on Responsible Computing, online erschienen am 13.04.2026. Verfasst von Sofie Goethals und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben.
Abstract (Originalsprache)
Artificial Intelligence (AI) finds widespread application across various domains, but it sparks concerns about fairness in its deployment. The prevailing discourse in classification often emphasizes outcome-based metrics comparing sensitive subgroups without consideration of the differential impacts within subgroups. Bias mitigation techniques do not only affect the ranking of pairs of instances across sensitive groups, but often also significantly affect the ranking of instances within these groups. Such changes are hard to explain and raise concerns regarding the validity of the intervention. Unfortunately, these effects remain under the radar in the accuracy-fairness evaluation framework that is usually applied. In this article, we illustrate the effect of several popular bias mitigation methods, and how their output often does not reflect real-world scenarios.
Zitieren
APA
Goethals, S., Favier, M., & Calders, T. (2026). Reranking Individuals: The Effect of Fair Classification Within-Groups. ACM Journal on Responsible Computing, 3(2), 1-27. https://doi.org/10.1145/3802540
Vancouver
Goethals S, Favier M, Calders T. Reranking Individuals: The Effect of Fair Classification Within-Groups. ACM Journal on Responsible Computing. 2026;3(2):1-27. doi:10.1145/3802540
BibTeX
@article{Goethals2026,
author = {Goethals, Sofie and Favier, Marco and Calders, Toon},
title = {Reranking Individuals: The Effect of Fair Classification Within-Groups},
journal = {ACM Journal on Responsible Computing},
year = {2026},
volume = {3},
number = {2},
pages = {1--27},
doi = {10.1145/3802540}
}
EUVIMED