{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:11:20Z","timestamp":1767337880959,"version":"3.41.0"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,2,28]]},"abstract":"<jats:p>\n            With the increasing penetration of machine learning applications in critical decision-making areas, calls for algorithmic fairness are more prominent. Although there have been various modalities to improve algorithmic fairness through learning with fairness constraints, their performance does not generalize well in the test set. A performance-promising fair algorithm with better generalizability is needed. This article proposes a novel adaptive reweighing method to eliminate the impact of the distribution shifts between training and test data on model generalizability. Most previous reweighing methods propose to assign a unified weight for each (sub)group. Rather, our method granularly models the distance from the sample predictions to the decision boundary. Our adaptive reweighing method prioritizes samples closer to the decision boundary and assigns a higher weight to improve the generalizability of fair classifiers. Extensive experiments are performed to validate the generalizability of our adaptive priority reweighing method for accuracy and fairness measures (i.e., equal opportunity, equalized odds, and demographic parity) in tabular benchmarks. We also highlight the performance of our method in improving the fairness of language and vision models. The code is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"url\" xlink:href=\"https:\/\/github.com\/che2198\/APW\">https:\/\/github.com\/che2198\/APW<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3665895","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T15:19:49Z","timestamp":1716477589000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Boosting Fair Classifier Generalization through Adaptive Priority Reweighing"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9123-6743","authenticated-orcid":false,"given":"Zhihao","family":"Hu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2001-4096","authenticated-orcid":false,"given":"Yiran","family":"Xu","sequence":"additional","affiliation":[{"name":"Warwick Business School, University of Warwick, Coventry, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1614-6069","authenticated-orcid":false,"given":"Mengnan","family":"Du","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, Newark, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0574-0129","authenticated-orcid":false,"given":"Jindong","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5952-8753","authenticated-orcid":false,"given":"Xinmei","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5584-2385","authenticated-orcid":false,"given":"Fengxiang","family":"He","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,2,15]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012412"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011418"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3429447"},{"key":"e_1_3_1_5_2","first-page":"254","volume-title":"Ethics of Data and Analytics","author":"Angwin Julia","year":"2016","unstructured":"Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias. In Ethics of Data and Analytics, Kirsten Martin (Ed.). Auerbach Publications, 254\u2013264."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/554131"},{"key":"e_1_3_1_7_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Baharlouei Sina","year":"2019","unstructured":"Sina Baharlouei, Maher Nouiehed, Ahmad Beirami, and Meisam Razaviyayn. 2019. R\u00e9nyi fair inference. In International Conference on Learning Representations, 1\u201314."},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Peter L. Bartlett Olivier Bousquet and Shahar Mendelson. 2005. Local Rademacher complexities. arXiv:math\/0508275. Retrieved from https:\/\/arxiv.org\/abs\/math\/0508275","DOI":"10.1214\/009053605000000282"},{"key":"e_1_3_1_9_2","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett Peter L.","year":"2002","unstructured":"Peter L. Bartlett and Shahar Mendelson. 2002. Rademacher and Gaussian complexities: Risk bounds and structural results. Journal of Machine Learning Research 3, November (2002), 463\u2013482.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_10_2","unstructured":"Richard Berk Hoda Heidari Shahin Jabbari Matthew Joseph Michael Kearns Jamie Morgenstern Seth Neel and Aaron Roth. 2017. A convex framework for fair regression. arXiv:1706.02409. Retrieved from https:\/\/arxiv.org\/abs\/1706.02409"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330745"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Su Lin Blodgett Lisa Green and Brendan O\u2019Connor. 2016. Demographic dialectal variation in social media: A case study of African-American English. arXiv:1608.08868. Retrieved from https:\/\/arxiv.org\/abs\/1608.08868","DOI":"10.18653\/v1\/D16-1120"},{"key":"e_1_3_1_13_2","first-page":"2853","volume-title":"International Conference on Machine Learning","author":"Chai Junyi","year":"2022","unstructured":"Junyi Chai and Xiaoqian Wang. 2022. Fairness with adaptive weights. In International Conference on Machine Learning. PMLR, 2853\u20132866."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0047"},{"key":"e_1_3_1_16_2","first-page":"4010","volume-title":"International Conference on Machine Learning","author":"Chu Xu","year":"2022","unstructured":"Xu Chu, Yujie Jin, Wenwu Zhu, Yasha Wang, Xin Wang, Shanghang Zhang, and Hong Mei. 2022. DNA: Domain generalization with diversified neural averaging. In International Conference on Machine Learning. PMLR, 4010\u20134034."},{"key":"e_1_3_1_17_2","unstructured":"Ching-Yao Chuang and Youssef Mroueh. 2021. Fair mixup: Fairness via interpolation. arXiv:2103.06503. Retrieved from https:\/\/arxiv.org\/abs\/2103.06503"},{"key":"e_1_3_1_18_2","unstructured":"Michele Donini Luca Oneto Shai Ben-David John S Shawe-Taylor and Massimiliano Pontil. 2018. Empirical risk minimization under fairness constraints. Advances in Neural Information Processing Systems 31 2796\u20132806."},{"key":"e_1_3_1_19_2","unstructured":"Rachel K. E. Bellamy Kuntal Dey Michael Hind Samuel C. Hoffman Stephanie Houde Kalapriya Kannan Pranay Lohia Jacquelyn Martino Sameep Mehta Aleksandra Mojsilovic Seema Nagar Karthikeyan Natesan Ramamurthy John Richards Diptikalyan Saha Prasanna Sattigeri Moninder Singh Kush R. Varshney and Yunfeng Zhang 2018. AI fairness 360: An extensible toolkit for detecting understanding and mitigating unwanted algorithmic bias. arXiv:1810.01943. Retrieved from https:\/\/arxiv.org\/abs\/1810.01943"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1169"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1137\/1.9781611974348.17","volume-title":"Proceedings of the 2016 SIAM International Conference on Data Mining, SIAM","author":"Fish Benjamin","year":"2016","unstructured":"Benjamin Fish, Jeremy Kun, and \u00c1d\u00e1m D. Lelkes. 2016. A confidence-based approach for balancing fairness and accuracy. In Proceedings of the 2016 SIAM International Conference on Data Mining, SIAM. 144\u2013152."},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467349"},{"key":"e_1_3_1_25_2","first-page":"11335","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Han Xudong","year":"2022","unstructured":"Xudong Han, Timothy Baldwin, and Trevor Cohn. 2022. Balancing out bias: Achieving fairness through balanced training. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 11335\u201311350."},{"key":"e_1_3_1_26_2","first-page":"3315","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In Advances in Neural Information Processing Systems, Vol. 29, 3315\u20133323."},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16965"},{"key":"e_1_3_1_29_2","first-page":"702","volume-title":"International Conference on Artificial Intelligence and Statistics, PMLR","author":"Jiang Heinrich","year":"2020","unstructured":"Heinrich Jiang and Ofir Nachum. 2020. Identifying and correcting label bias in machine learning. In International Conference on Artificial Intelligence and Statistics, PMLR. 702\u2013712."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"e_1_3_1_31_2","first-page":"4171","volume-title":"Proceedings of NAACL-HLT","author":"Kenton Jacob Devlin Ming-Wei Chang","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186133"},{"key":"e_1_3_1_33_2","first-page":"12917","volume-title":"International Conference on Machine Learning, PMLR","author":"Li Peizhao","year":"2022","unstructured":"Peizhao Li and Hongfu Liu. 2022. Achieving fairness at no utility cost via data reweighing with influence. In International Conference on Machine Learning, PMLR. 12917\u201312930."},{"key":"e_1_3_1_34_2","unstructured":"Kevin Bache and Moshe Lichman. 2013. UCI Machine Learning Repository 2013. Retrieved from http:\/\/archive.ics.uci.edu\/ml"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"e_1_3_1_36_2","first-page":"3384","volume-title":"International Conference on Machine Learning, PMLR","author":"Madras David","year":"2018","unstructured":"David Madras, Elliot Creager, Toniann Pitassi, and Richard Zemel. 2018. Learning adversarially fair and transferable representations. In International Conference on Machine Learning, PMLR. 3384\u20133393."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.5555\/3360093"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-24628-9_37"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295319"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Sreeraj Ramachandran and Ajita Rattani. 2022. Deep generative views to mitigate gender classification bias across gender-race groups. arXiv:2208.08382. Retrieved from https:\/\/arxiv.org\/abs\/2208.08382","DOI":"10.1007\/978-3-031-37731-0_40"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Shauli Ravfogel Yanai Elazar Hila Gonen Michael Twiton and Yoav Goldberg. 2020. Null it out: Guarding protected attributes by iterative nullspace projection. arXiv:2004.07667. Retrieved from https:\/\/arxiv.org\/abs\/2004.07667","DOI":"10.18653\/v1\/2020.acl-main.647"},{"key":"e_1_3_1_42_2","first-page":"8147","volume-title":"International Conference on Machine Learning","author":"Roh Yuji","year":"2020","unstructured":"Yuji Roh, Kangwook Lee, Steven Whang, and Changho Suh. 2020a. Fr-train: A mutual information-based approach to fair and robust training. In International Conference on Machine Learning. PMLR, 8147\u20138157."},{"key":"e_1_3_1_43_2","first-page":"815","article-title":"Sample selection for fair and robust training","volume":"34","author":"Roh Yuji","year":"2021","unstructured":"Yuji Roh, Kangwook Lee, Steven Whang, and Changho Suh. 2021. Sample selection for fair and robust training. Advances in Neural Information Processing Systems 34 (2021), 815\u2013827.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_44_2","volume-title":"International Conference on Learning Representations","author":"Roh Yuji","year":"2020","unstructured":"Yuji Roh, Kangwook Lee, Steven Euijong Whang, and Changho Suh. 2020b. FairBatch: Batch selection for model fairness. In International Conference on Learning Representations."},{"key":"e_1_3_1_45_2","volume-title":"The Nature of Statistical Learning Theory","author":"Vapnik Vladimir","year":"1999","unstructured":"Vladimir Vapnik. 1999. The Nature of Statistical Learning Theory. Springer Science & Business Media."},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551390"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00541"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512255"},{"key":"e_1_3_1_49_2","first-page":"1920","volume-title":"Conference on Learning Theory","author":"Woodworth Blake","year":"2017","unstructured":"Blake Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, and Nathan Srebro. 2017. Learning non-discriminatory predictors. In Conference on Learning Theory. PMLR, 1920\u20131953."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367032.3367238"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622525"},{"key":"e_1_3_1_52_2","first-page":"7333","article-title":"Modeling tabular data using conditional GAN","volume":"32","author":"Xu Lei","year":"2019","unstructured":"Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, and Kalyan Veeramachaneni. 2019a. Modeling tabular data using conditional GAN. In Advances in Neural Information Processing Systems, Vol. 32, 7333\u20137343.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_53_2","first-page":"962","volume-title":"Artificial Intelligence and Statistics, PMLR","author":"Zafar Muhammad Bilal","year":"2017","unstructured":"Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rogriguez, and Krishna P. Gummadi. 2017. Fairness constraints: Mechanisms for fair classification. In Artificial Intelligence and Statistics, PMLR. 962\u2013970."},{"key":"e_1_3_1_54_2","first-page":"325","volume-title":"International Conference on Machine Learning, PMLR","author":"Zemel Rich","year":"2013","unstructured":"Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. 2013. Learning fair representations. In International Conference on Machine Learning, PMLR. 325\u2013333."},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"issue":"4","key":"e_1_3_1_56_2","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.1109\/TKDE.2020.3002567","article-title":"Fairness in semi-supervised learning: Unlabeled data help to reduce discrimination","volume":"34","author":"Zhang Tao","year":"2020","unstructured":"Tao Zhang, Tianqing Zhu, Jing Li, Mengde Han, Wanlei Zhou, and S. Yu Philip. 2020. Fairness in semi-supervised learning: Unlabeled data help to reduce discrimination. IEEE Transactions on Knowledge and Data Engineering 34, 4 (2020), 1763\u20131774.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.463"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467102"},{"key":"e_1_3_1_60_2","first-page":"27203","volume-title":"International Conference on Machine Learning, PMLR","author":"Zhou Xiao","year":"2022","unstructured":"Xiao Zhou, Yong Lin, Renjie Pi, Weizhong Zhang, Renzhe Xu, Peng Cui, and Tong Zhang. 2022. Model agnostic sample reweighting for out-of-distribution learning. In International Conference on Machine Learning, PMLR. 27203\u201327221."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665895","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:27Z","timestamp":1750290267000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,15]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.1145\/3665895"],"URL":"https:\/\/doi.org\/10.1145\/3665895","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2025,2,15]]},"assertion":[{"value":"2023-09-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}