Subgroup fairness based on shared counterfactuals
Abstract CounterFair is a group counterfactual search algorithm that detects and minimizes biases among sensitive groups and identifies relevant subgroups inside these sensitive groups based on shared counterfactual instances. We investigate the latter capability, analyzing the found subgroups from the perspective of fairness based on counterfactual reasoning, in order to evaluate whether they present different biases with respect to each other and to the sensitive feature groups they belong to. We perform these measurements on the subgroups extracted by CounterFair over six binary classification datasets, providing figures and their respective analysis on the presence of bias.
Authors
- Zed Lee
- Panagiotis Papapetrou (ORCID: https://orcid.org/0000-0002-4632-4815)
- Evaggelia Pitoura (ORCID: https://orcid.org/0000-0002-3775-4995)
- Panayiotis Tsaparas (ORCID: https://orcid.org/0000-0002-3490-1507)
- Guilherme Dinis (ORCID: https://orcid.org/0000-0001-8492-761X)
- Tony Lindgren (ORCID: https://orcid.org/0000-0001-7713-1381)
- Alejandro Kuratomi
Institutions
- Stockholm University (SE)
- University of Ioannina (GR)
- Athena Research and Innovation Center In Information Communication & Knowledge Technologies (GR)
Publication Details
- Journal
- Knowledge and Information Systems
- Published
- 2025-08-18
- DOI
- https://doi.org/10.1007/s10115-025-02555-7
- Primary Topic
- Experimental Behavioral Economics Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- European Commission
- Stockholms Universitet