eprintid: 10130186 rev_number: 23 eprint_status: archive userid: 608 dir: disk0/10/13/01/86 datestamp: 2021-06-25 16:50:20 lastmod: 2021-11-10 01:57:10 status_changed: 2021-11-05 16:10:35 type: proceedings_section metadata_visibility: show creators_name: Hort, M creators_name: Zhang, J creators_name: Sarro, F creators_name: Harman, M title: Fairea: A Model Behaviour Mutation Approach to Benchmarking Bias Mitigation Methods ispublished: inpress divisions: UCL divisions: B04 divisions: C05 divisions: F48 note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: The increasingly wide uptake of Machine Learning (ML) has raised the significance of the problem of tackling bias (i.e., unfairness), making it a primary software engineering concern. In this paper, we introduce Fairea, a model behaviour mutation approach to benchmarking ML bias mitigation methods. We also report on a large-scale empirical study to test the effectiveness of 12 widely-studied bias mitigation methods. Our results reveal that, surprisingly, bias mitigation methods have a poor effectiveness in 49% of the cases. In particular, 15% of the mitigation cases have worse fairness-accuracy trade-offs than the baseline established by Fairea; 34% of the cases have a decrease in accuracy and an increase in bias. Fairea has been made publicly available for software engineers and researchers to evaluate their bias mitigation methods. date: 2021-08-23 date_type: published publisher: Association for Computing Machinery official_url: https://doi.org/10.6084/m9.figshare.13712827.v2 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1872514 doi: 10.6084/m9.figshare.13712827.v2 lyricists_name: Harman, Mark lyricists_name: Hort, Max lyricists_name: Sarro, Federica lyricists_id: MHARM36 lyricists_id: MBHOR72 lyricists_id: FSSAR72 actors_name: Hort, Max actors_id: MBHOR72 actors_role: owner full_text_status: public place_of_pub: New York, NY, United States pagerange: 994-1006 event_title: ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering institution: ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering book_title: ESEC/FSE 2021: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering citation: Hort, M; Zhang, J; Sarro, F; Harman, M; (2021) Fairea: A Model Behaviour Mutation Approach to Benchmarking Bias Mitigation Methods. In: ESEC/FSE 2021: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. (pp. pp. 994-1006). Association for Computing Machinery: New York, NY, United States. (In press). Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10130186/1/Fairea-rps.pdf