FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness

Christos Fragkathoulas, Vasiliki Papanikou, Evaggelia Pitoura, Evimaria Terzi

ECML-PKDD 2025 pp. 41-59

doi:10.1007/978-3-032-06078-5_3 /ecmlpkdd/2025/fragkathoulas2025ecmlpkdd-facegroup/

Abstract

Counterfactual explanations assess unfairness by revealing how inputs must change to achieve a desired outcome. This paper introduces the first graph-based framework for generating group counterfactual explanations to audit group fairness, a key aspect of trustworthy machine learning. Our framework, FACEGroup (Feasible and Actionable Counterfactual Explanations for Group Fairness), models real-world feasibility constraints, identifies subgroups with similar counterfactuals, and captures key trade-offs in counterfactual generation, distinguishing it from existing methods. To evaluate fairness, we introduce novel metrics for both group and subgroup level analysis that explicitly account for these trade-offs. Experiments on benchmark datasets show that FACEGroup effectively generates feasible group counterfactuals while accounting for trade-offs, and that our metrics capture and quantify fairness disparities.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Fragkathoulas et al. "FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025. doi:10.1007/978-3-032-06078-5_3

Markdown

[Fragkathoulas et al. "FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025.](https://mlanthology.org/ecmlpkdd/2025/fragkathoulas2025ecmlpkdd-facegroup/) doi:10.1007/978-3-032-06078-5_3

BibTeX

@inproceedings{fragkathoulas2025ecmlpkdd-facegroup,
  title     = {{FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness}},
  author    = {Fragkathoulas, Christos and Papanikou, Vasiliki and Pitoura, Evaggelia and Terzi, Evimaria},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2025},
  pages     = {41-59},
  doi       = {10.1007/978-3-032-06078-5_3},
  url       = {https://mlanthology.org/ecmlpkdd/2025/fragkathoulas2025ecmlpkdd-facegroup/}
}