{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T18:10:52Z","timestamp":1759947052594,"version":"build-2065373602"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"Maritime AI Research Programme","doi-asserted-by":"publisher","award":["SMI-2022-MTP-06"],"award-info":[{"award-number":["SMI-2022-MTP-06"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["DTC-RGC-04"],"award-info":[{"award-number":["DTC-RGC-04"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3586609","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T17:43:02Z","timestamp":1752601382000},"page":"18005-18019","source":"Crossref","is-referenced-by-count":0,"title":["Alpha and Prejudice: Improving \u03b1-Sized Worst Case Fairness via Intrinsic Reweighting"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7584-1240","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"first","affiliation":[{"name":"Technology and Research (A*STAR), Center for Frontier AI Research and the Institute of High-Performance Computing, Agency for Science, Connexis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3204-0739","authenticated-orcid":false,"given":"Yinghua","family":"Yao","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR), Center for Frontier AI Research and the Institute of High-Performance Computing, Agency for Science, Connexis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7950-4900","authenticated-orcid":false,"given":"Yuangang","family":"Pan","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR), Center for Frontier AI Research and the Institute of High-Performance Computing, Agency for Science, Connexis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4496-6939","authenticated-orcid":false,"given":"Xuanqian","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2211-8176","authenticated-orcid":false,"given":"Ivor W.","family":"Tsang","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR), Center for Frontier AI Research and the Institute of High-Performance Computing, Agency for Science, Connexis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6673-1098","authenticated-orcid":false,"given":"Xiuju","family":"Fu","sequence":"additional","affiliation":[{"name":"Technology and Research, Institute of High-Performance Computing, Agency for Science, Connexis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the web\u2019s cutting edge, anonymity in name only","volume":"4","author":"Steel","year":"2010","journal-title":"Wall Street J."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aao5580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2021.9937"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2023.103261"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1356"},{"key":"ref6","first-page":"962","article-title":"Fairness constraints: Mechanisms for fair classification","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"Zafar"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052660"},{"key":"ref8","first-page":"43","article-title":"Inherent trade-offs in the fair determination of risk scores","volume-title":"Proc. 8th Innov. Theor. Comput. Sci. Conf. (ITCS)","volume":"67","author":"Kleinberg"},{"key":"ref9","first-page":"60","article-title":"A reductions approach to fair classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-022-00183-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"ref12","first-page":"325","article-title":"Learning fair representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zemel"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"ref14","first-page":"585","article-title":"Controllable invariance through adversarial feature learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20738-9_128"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3187165"},{"key":"ref17","first-page":"3315","article-title":"Equality of opportunity in supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hardt"},{"key":"ref18","first-page":"1","article-title":"Blackbox post-processing for multiclass fairness","volume-title":"Proc. Workshop Artif. Intell. Saf. (SafeAI) 36th AAAI Conf. Artif. Intell. (AAAI)","author":"Putzel"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20657"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv31xf5v0"},{"key":"ref21","first-page":"7492","article-title":"Blind Pareto fairness and subgroup robustness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mart\u00ednez"},{"key":"ref22","first-page":"80908","article-title":"Towards harmless rawlsian fairness regardless of demographic prior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.2477899"},{"key":"ref24","first-page":"10976","article-title":"The price of fair PCA: One extra dimension","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Samadi"},{"key":"ref25","first-page":"1","article-title":"Distributionally robust fair principal components via geodesic descents","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Vu"},{"key":"ref26","first-page":"1866","article-title":"Understanding and mitigating accuracy disparity in regression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chi"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/2053951717743530"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411980"},{"key":"ref30","first-page":"43258","article-title":"Weak proxies are sufficient and preferable for fairness with missing sensitive attributes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/98"},{"key":"ref32","article-title":"County-level algorithmic audit of racial bias in Twitter\u2019s home timeline","author":"Belli","year":"2022","journal-title":"arXiv:2211.08667"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2004"},{"key":"ref34","first-page":"12345","article-title":"DORO: Distributional and outlier robust optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhai"},{"key":"ref35","article-title":"Outlier-robust group inference via gradient space clustering","author":"Zeng","year":"2022","journal-title":"arXiv:2210.06759"},{"key":"ref36","first-page":"27100","article-title":"Self-supervised fair representation learning without demographics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chai"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref38","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709160"},{"key":"ref40","first-page":"1929","article-title":"Fairness without demographics in repeated loss minimization","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Hashimoto"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287584"},{"key":"ref42","first-page":"728","article-title":"Fairness without demographics through adversarially reweighted learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lahoti"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-042720-125902"},{"key":"ref44","article-title":"Fairly accurate: Fairness-aware multi-group target detection in online discussion","author":"Gupta","year":"2024","journal-title":"arXiv:2407.11933"},{"key":"ref45","first-page":"6781","article-title":"Just train twice: Improving group robustness without training group information","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu"},{"article-title":"Conditional learning of fair representations","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Zhao","key":"ref46"},{"key":"ref47","first-page":"6755","article-title":"Minimax Pareto fairness: A multi objective perspective","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Martinez"},{"key":"ref48","article-title":"Practical bias mitigation through proxy sensitive attribute label generation","author":"Chaudhary","year":"2023","journal-title":"arXiv:2312.15994"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2009.83"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.72"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3514105.3514120"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00070"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-019-0558-x"},{"key":"ref54","first-page":"2975","article-title":"Variance-based regularization with convex objectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Duchi"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/090756090"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-83670-2_15"},{"key":"ref57","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659014"},{"key":"ref59","first-page":"19152","article-title":"Fairness without demographics through knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chai"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1806\/table-3"},{"article-title":"Lsac national longitudinal bar passage study. LSAC research report series","year":"1998","author":"Wightman","key":"ref61"},{"key":"ref62","article-title":"ProPublica\u2019s COMPAS data revisited","author":"Barenstein","year":"2019","journal-title":"arXiv:1906.04711"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref64","first-page":"1","article-title":"Robust optimization for non-convex objectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref65","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"Sagawa","year":"2019","journal-title":"arXiv:1911.08731"},{"key":"ref66","first-page":"16049","article-title":"How does information bottleneck help deep learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kawaguchi"},{"key":"ref67","first-page":"5708","article-title":"On the variance of the Fisher information for deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Soen"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3273249"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3002567"},{"key":"ref70","first-page":"361","article-title":"Achieving equalized odds by resampling sensitive attributes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Romano"},{"key":"ref71","first-page":"1","article-title":"Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"An"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3384181"},{"key":"ref73","first-page":"2564","article-title":"Preventing fairness gerrymandering: Auditing and learning for subgroup fairness","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Kearns"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3329249"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3263594"},{"key":"ref76","first-page":"11492","article-title":"To be robust or to be fair: Towards fairness in adversarial training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233093"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11080484.pdf?arnumber=11080484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:39:02Z","timestamp":1759945142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11080484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":77,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3586609","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}