Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity
ACM Journal on Responsible Computing · 2024
DOI: 10.1145/3677173 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Journal on Responsible Computing, 2024. Verfasst von Kacper Sokol und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Estonian Research Council, Dora Plus programme, European Regional Development Fund and Estonian government.
Themen: Ethik in der Pflege
Abstract (Originalsprache)
While data-driven predictive models are a strictly technological construct, they may operate within a social context in which benign engineering choices entail implicit, indirect, and unexpected real-life consequences. Fairness of such systems—pertaining both to individuals and groups—is one relevant consideration in this space; algorithms can discriminate people across various protected characteristics, regardless of whether these properties are included in the data or discernible through proxy variables. To date, this notion has predominantly been studied for a fixed model, often under different classification thresholds, striving to identify and eradicate undesirable, discriminative, and possibly unlawful aspects of its operation. Here, we backtrack on this fixed model assumption to propose and explore a novel definition of cross-model fairness where individuals can be harmed when one predictor is chosen ad hoc from a group of equally well-performing models, i.e., in view of utility-based model multiplicity . Since a person may be classified differently across models that are otherwise considered equivalent, this individual could argue for a predictor granting them the most favourable outcome, employing which may have adverse effects on other people. We introduce this scenario with a two-dimensional example and linear classification; then, we present a comprehensive empirical study based on real-life predictive models and datasets that are popular with the algorithmic fairness community; finally, we investigate analytical properties of cross-model fairness and its ramifications in a broader context. Our findings suggest that such unfairness can be readily found in real life, and it may be difficult to mitigate by technical means alone, as doing so is likely to degrade predictive performance.
Förderung
- Estonian Research Council
- Dora Plus programme
- European Regional Development Fund and Estonian government
- ARC Centre of Excellence for Automated Decision-making and Society
- Australian Research Council
- Hasler Foundation
Zitieren
APA
Sokol, K., Kull, M., Chan, J., & Salim, F. (2024). Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity. ACM Journal on Responsible Computing. https://doi.org/10.1145/3677173
Vancouver
Sokol K, Kull M, Chan J, Salim F. Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity. ACM Journal on Responsible Computing. 2024. doi:10.1145/3677173
BibTeX
@article{Sokol2024,
author = {Sokol, Kacper and Kull, Meelis and Chan, Jeffrey and Salim, Flora},
title = {Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity},
journal = {ACM Journal on Responsible Computing},
year = {2024},
doi = {10.1145/3677173}
}
EUVIMED