{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T20:24:31Z","timestamp":1792268671534,"version":"4.4.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:00:00Z","timestamp":1750291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Research Foundation Singapore and DSO National Laboratories","award":["AISG2-RP-2020-019"],"award-info":[{"award-number":["AISG2-RP-2020-019"]}]},{"name":"National Research Foundation Singapore and Cyber Security Agency","award":["NCRP25-P04-TAICeN"],"award-info":[{"award-number":["NCRP25-P04-TAICeN"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Prime Minister?s Office, Singapore","doi-asserted-by":"crossref","award":["CREATE"],"award-info":[{"award-number":["CREATE"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2025,6,19]]},"abstract":"<jats:p>Fairness is a critical requirement for Machine Learning (ML) software, driving the development of numerous bias mitigation methods. Previous research has identified a leveling-down effect in bias mitigation for computer vision and natural language processing tasks, where fairness is achieved by lowering performance for all groups without benefiting the unprivileged group. However, it remains unclear whether this effect applies to bias mitigation for tabular data tasks, a key area in fairness research with significant real-world applications. This study evaluates eight bias mitigation methods for tabular data, including both widely used and cutting- edge approaches, across 44 tasks using five real-world datasets and four common ML models. Contrary to earlier findings, our results show that these methods operate in a zero-sum fashion, where improvements for unprivileged groups are related to reduced benefits for traditionally privileged groups. However, previous research indicates that the perception of a zero-sum trade-off might complicate the broader adoption of fairness policies. To explore alternatives, we investigate an approach that applies the state-of-the-art bias mitigation method solely to unprivileged groups, showing potential to enhance benefits of unprivileged groups without negatively affecting privileged groups or overall ML performance. Our study highlights potential pathways for achieving fairness improvements without zero-sum trade-offs, which could help advance the adoption of bias mitigation methods.<\/jats:p>","DOI":"10.1145\/3729350","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T11:15:34Z","timestamp":1750331734000},"page":"1780-1801","source":"Crossref","is-referenced-by-count":4,"title":["Software Fairness Dilemma: Is Bias Mitigation a Zero-Sum Game?"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4765-1893","authenticated-orcid":false,"given":"Zhenpeng","family":"Chen","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4058-6733","authenticated-orcid":false,"given":"Xinyue","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0481-7264","authenticated-orcid":false,"given":"Jie M.","family":"Zhang","sequence":"additional","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9236-8264","authenticated-orcid":false,"given":"Weisong","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8624-5740","authenticated-orcid":false,"given":"Ying","family":"Xiao","sequence":"additional","affiliation":[{"name":"King's College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2207-1622","authenticated-orcid":false,"given":"Tianlin","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4066-3365","authenticated-orcid":false,"given":"Yiling","family":"Lou","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-9215","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,19]]},"reference":[{"key":"e_1_3_1_1_2","unstructured":"2025. Replication package. https:\/\/github.com\/chenzhenpengl8\/FSE25-ZeroSum"},{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2023.3244713"},{"key":"e_1_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Kwabena Ebo Bennin Jacky Keung Akito Monden Passakorn Phannachitta and Solomon Mensah. 2017. The significant effects of data sampling approaches on software defect prioritization and classification. In Proceedings of the 2017 ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement ESEM 2017. 364\u2013373.","DOI":"10.1109\/ESEM.2017.50"},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Sumon Biswas and Hridesh Rajan. 2020. Do the machine learning models on a crowd sourced platform exhibit bias? An empirical study on model fairness. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2020. 642\u2013653.","DOI":"10.1145\/3368089.3409704"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Sumon Biswas and Hridesh Rajan. 2021. Fair preprocessing: Towards understanding compositional fairness of data transformers in machine learning pipeline. In Proceedings of the 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2021. 981\u2013993.","DOI":"10.1145\/3468264.3468536"},{"issue":"18","key":"e_1_3_1_6_2","doi-asserted-by":"crossref","first-page":"eabm2385","DOI":"10.1126\/sciadv.abm2385","article-title":"If you rise, I fall: Equality is prevented by the misperception that it harms advantaged groups","volume":"8","author":"Brown N Derek","year":"2022","unstructured":"N Derek Brown, Drew S Jacoby-Senghor, and Isaac Raymundo. 2022. If you rise, I fall: Equality is prevented by the misperception that it harms advantaged groups. Science Advances 8, 18 (2022), eabm2385.","journal-title":"Science Advances"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Yuriy Brun and Alexandra Meliou. 2018. Software fairness. In Proceedings of the 2018 ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2018. 754\u2013759.","DOI":"10.1145\/3236024.3264838"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199401)45:1<12::AID-ASI2>3.0.CO;2-L"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Joymallya Chakraborty Suvodeep Majumder and Tim Menzies. 2021. Bias in machine learning software: Why? How? What to do?. In Proceedings of the 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2021. 429\u2013440.","DOI":"10.1145\/3468264.3468537"},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Joymallya Chakraborty Suvodeep Majumder Zhe Yu and Tim Menzies. 2020. Fairway: A way to build fair ML software. In Proceedings of the 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2020. 654\u2013665.","DOI":"10.1145\/3368089.3409697"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652155"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Zhenpeng Chen Jie M. Zhang Federica Sarro and Mark Harman. 2022. MAAT: A novel ensemble approach to addressing fairness and performance bugs for machine learning software. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2022. 1122\u20131134.","DOI":"10.1145\/3540250.3549093"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583561"},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Zhenpeng Chen Jie M. Zhang Federica Sarro and Mark Harman. 2024. Fairness improvement with multiple protected attributes: How far are we?. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering ICSE2024. 160:1\u2013160:13.","DOI":"10.1145\/3597503.3639083"},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Sorelle A. Friedler Carlos Scheidegger Suresh Venkatasubramanian Sonam Choudhary Evan P. Hamilton and Derek Roth. 2019. A comparative study of fairness-enhancing interventions in machine learning. In Proceedings of the Conference on Fairness Accountability and Transparency FAT 2019. 329\u2013338.","DOI":"10.1145\/3287560.3287589"},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Xuanqi Gao Juan Zhai Shiqing Ma Chao Shen Yufei Chen and Qian Wang. 2022. Fairneuron: Improving deep neural network fairness with adversary games on selective neurons. In Proceedings of the 44th IEEE\/ACM International Conference on Software Engineering ICSE 2022. 921\u2013933.","DOI":"10.1145\/3510003.3510087"},{"key":"e_1_3_1_17_2","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s10677-004-2217-0","article-title":"Welfare, justice, and Pareto efficiency","volume":"7","author":"Hansson Sven Ove","year":"2004","unstructured":"Sven Ove Hansson. 2004. Welfare, justice, and Pareto efficiency. Ethical Theory and Moral Practice 7 (2004), 361\u2013380.","journal-title":"Ethical Theory and Moral Practice"},{"key":"e_1_3_1_18_2","unstructured":"Moritz Hardt Eric Price and Nati Srebro. 2016. Equality of opportunity in supervised learning. In Proceedings of the Annual Conference on Neural Information Processing Systems 2016 NIPS 2016. 3315\u20133323."},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Jennifer Horkoff. 2019. Non-Functional requirements for machine learning: Challenges and new directions. In Proceedings of the 27th IEEE International Requirements Engineering Conference RE 2019. 386\u2013391.","DOI":"10.1109\/RE.2019.00050"},{"issue":"2","key":"e_1_3_1_20_2","first-page":"11:1","article-title":"Bias mitigation for machine learning classifiers: A comprehensive survey","volume":"1","author":"Hort Max","year":"2024","unstructured":"Max Hort, Zhenpeng Chen, Jie M. Zhang, Mark Harman, and Federica Sarro. 2024. Bias mitigation for machine learning classifiers: A comprehensive survey. ACM Journal on Responsible Computing 1, 2 (2024), 11:1\u201311:52.","journal-title":"ACM Journal on Responsible Computing"},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Max Hort Jie M. Zhang Federica Sarro and Mark Harman. 2021. Fairea: A model behaviour mutation approach to benchmarking bias mitigation methods. In Proceedings of the 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2021. 994\u20131006.","DOI":"10.1145\/3468264.3468565"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-016-9437-5"},{"key":"e_1_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Yanhui Li Linghan Meng Lin Chen Li Yu Di Wu Yuming Zhou and Baowen Xu. 2022. Training data debugging for the fairness of machine learning software. In Proceedings of the 44th IEEE\/ACM International Conference on Software Engineering ICSE 2022. 2215\u20132227.","DOI":"10.1145\/3510003.3510091"},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Gaurav Maheshwari Aur\u00e9lien Bellet Pascal Denis and Mikaela Keller. 2023. Fair without leveling down: A new intersectional fairness definition. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing EMNLP 2023. 9018\u20139032.","DOI":"10.18653\/v1\/2023.emnlp-main.558"},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Patrick E McKnight and Julius Najab. 2010. Mann-Whitney U test. The Corsini Encyclopedia of Psychology (2010) 1\u20131.","DOI":"10.1002\/9780470479216.corpsy0524"},{"key":"e_1_3_1_27_2","unstructured":"Aditya Krishna Menon and Robert C. Williamson. 2018. The cost of fairness in binary classification. In Proceedings of the Conference on Fairness Accountability and Transparency FAT 2018. 107\u2013118."},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Brent Mittelstadt Sandra Wachter and Chris Russell. 2023. The unfairness of fair machine learning: Levelling down and strict egalitarianism by default. arXiv preprint arXiv:2302.02404 (2023).","DOI":"10.36645\/mtlr.30.1.unfairness"},{"key":"e_1_3_1_29_2","unstructured":"Jerome L Myers Arnold D Well and Robert F LorchJr. 2013. Research design and statistical analysis. Routledge."},{"issue":"3","key":"e_1_3_1_30_2","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1177\/1745691611406922","article-title":"Whites see racism as a zero-sum game that they are now losing","volume":"6","author":"Norton Michael I","year":"2011","unstructured":"Michael I Norton and Samuel R Sommers. 2011. Whites see racism as a zero-sum game that they are now losing. Perspectives on Psychological science 6, 3 (2011), 215\u2013218.","journal-title":"Perspectives on Psychological science"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3220713"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Hung Viet Pham Shangshu Qian Jiannan Wang Thibaud Lutellier Jonathan Rosenthal Lin Tan Yaoliang Yu and Nachiappan Nagappan. 2020. Problems and opportunities in training deep learning software systems: an analysis of variance. In Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering ASE 2020. 771\u2013783.","DOI":"10.1145\/3324884.3416545"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Saeid Tizpaz-Niari Ashish Kumar Gang Tan and Ashutosh Trivedi. 2022. Fairness-aware configuration of machine learning libraries. In Proceedings of the 44th IEEE\/ACM International Conference on Software Engineering ICSE 2022. 909\u2013920.","DOI":"10.1145\/3510003.3510202"},{"key":"e_1_3_1_34_2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1057\/9780230502185_2","volume-title":"Challenges to Democracy: Ideas, Involvement and Institutions","author":"Wolff Jonathan","year":"2001","unstructured":"Jonathan Wolff. 2001. Levelling down. In Challenges to Democracy: Ideas, Involvement and Institutions. Springer, 18\u201332."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3660801"},{"key":"e_1_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Junjie Yang Jiajun Jiang Zeyu Sun and Junjie Chen. 2024. A large-scale empirical study on improving the fairness of image classification models. In Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis ISSTA 2024. 210\u2013222.","DOI":"10.1145\/3650212.3652122"},{"key":"e_1_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Muhammad Bilal Zafar Isabel Valera Manuel Gomez-Rodriguez and Krishna P. Gummadi. 2017. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th International Conference on World Wide Web WWW 2017. 1171\u20131180.","DOI":"10.1145\/3038912.3052660"},{"key":"e_1_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Brian Hu Zhang Blake Lemoine and Margaret Mitchell. 2018. Mitigating unwanted biases with adversarial learning. In Proceedings of the 2018 AAAI\/ACM Conference on Al Ethics and Society AIES 2018. 335\u2013340.","DOI":"10.1145\/3278721.3278779"},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Jie M. Zhang and Mark Harman. 2021. Ignorance and prejudice in software fairness. In Proceedings of the 43rd IEEE\/ACM International Conference on Software Engineering ICSE 2021. 1436\u20131447.","DOI":"10.1109\/ICSE43902.2021.00129"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2962027"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Mengdi Zhang and Jun Sun. 2022. Adaptive fairness improvement based on causality analysis. In Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC\/FSE 2022. 6\u201317.","DOI":"10.1145\/3540250.3549103"},{"key":"e_1_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Haibin Zheng Zhiqing Chen Tianyu Du Xuhong Zhang Yao Cheng Shouling Ji Jingyi Wang Yue Yu and Jinyin Chen. 2022. NeuronFair: Interpretable white-box fairness testing through biased neuron identification. In Proceedings of the 44th IEEE\/ACM International Conference on Software Engineering ICSE 2022. 1519\u20131531.","DOI":"10.1145\/3510003.3510123"},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Dominik Zietlow Michael Lohaus Guha Balakrishnan Matth\u00e4us Kleindessner Francesco Locatello Bernhard Sch\u00f6lkopf and Chris Russell. 2022. Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2022. 10400\u201310411.","DOI":"10.1109\/CVPR52688.2022.01016"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3729350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T11:02:10Z","timestamp":1787482930000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3729350"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,19]]},"references-count":43,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2025,6,19]]}},"alternative-id":["10.1145\/3729350"],"URL":"https:\/\/doi.org\/10.1145\/3729350","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,19]]}}}