{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:08:14Z","timestamp":1770739694963,"version":"3.49.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62525212"],"award-info":[{"award-number":["62525212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236008"],"award-info":[{"award-number":["62236008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441232"],"award-info":[{"award-number":["62441232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025604"],"award-info":[{"award-number":["62025604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406305"],"award-info":[{"award-number":["62406305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2051"],"award-info":[{"award-number":["U23B2051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476068"],"award-info":[{"award-number":["62476068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471013"],"award-info":[{"award-number":["62471013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0680201"],"award-info":[{"award-number":["XDB0680201"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["E4EQ1101"],"award-info":[{"award-number":["E4EQ1101"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M743441"],"award-info":[{"award-number":["2023M743441"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771492"],"award-info":[{"award-number":["2025M771492"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20240729"],"award-info":[{"award-number":["GZB20240729"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3637063","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T18:28:44Z","timestamp":1764095324000},"page":"3482-3498","source":"Crossref","is-referenced-by-count":0,"title":["Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0148-8306","authenticated-orcid":false,"given":"Yangbangyan","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3512-7277","authenticated-orcid":false,"given":"Qianqian","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5908-2130","authenticated-orcid":false,"given":"Huiyang","family":"Shao","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4409-4999","authenticated-orcid":false,"given":"Zhiyong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4336-8900","authenticated-orcid":false,"given":"Shilong","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3554729"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02171-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2608882"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00318"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00131"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1113.003.0010"},{"key":"ref10","first-page":"313","article-title":"AUC optimization vs. error rate minimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cortes"},{"key":"ref11","first-page":"848","article-title":"Optimizing classifier performance via an approximation to the Wilcoxon-Mann-Whitney statistic","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102399"},{"key":"ref13","first-page":"451","article-title":"Stochastic online AUC maximization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref14","article-title":"Deep AUC maximization for medical image classification: Challenges and opportunities","author":"Yang","year":"2021"},{"key":"ref15","first-page":"1","article-title":"Compositional training for end-to-end deep AUC maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yuan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512178"},{"key":"ref17","first-page":"516","article-title":"A structural SVM based approach for optimizing partial AUC","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Narasimhan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00303"},{"key":"ref19","first-page":"27548","article-title":"When AUC meets DRO: Optimizing partial AUC for deep learning with non-convex convergence guarantee","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref20","first-page":"31239","article-title":"Large-scale optimization of partial AUC in a range of false positive rates","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref21","first-page":"11820","article-title":"When all we need is a piece of the pie: A generic framework for optimizing two-way partial AUC","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref22","first-page":"38667","article-title":"Asymptotically unbiased instance-wise regularized partial AUC optimization: Theory and algorithm","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357814"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/1541-0420.00071"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00972"},{"key":"ref26","first-page":"5861","article-title":"Implicit rate-constrained optimization of non-decomposable objectives","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185311"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3215702"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165627"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1113.003.0010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/1.2.123"},{"key":"ref32","first-page":"933","article-title":"An efficient boosting algorithm for combining preferences","volume":"4","author":"Freund","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","first-page":"71","article-title":"Optimizing area under ROC curve with SVMs","volume-title":"Proc. ROCAI","author":"Rakotomamonjy","year":"2004"},{"key":"ref34","first-page":"3710","article-title":"Stochastic proximal algorithms for AUC maximization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Natole"},{"key":"ref35","first-page":"1","article-title":"Stochastic AUC maximization with deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00303"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3141095"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3641285"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599316"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303934"},{"key":"ref41","first-page":"29552","article-title":"Multi-block min-max bilevel optimization with applications in multi-task deep AUC maximization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015660"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303943"},{"key":"ref44","first-page":"11934","article-title":"FeDXL: Provable federated learning for deep X-risk optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref45","first-page":"43205","article-title":"Provable multi-instance deep AUC maximization with stochastic pooling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref46","article-title":"AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714638"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3208419"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319431"},{"key":"ref50","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02461"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3400041"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381835"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00939"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462100"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33446"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00714"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1177\/0272989x8900900307"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxq052"},{"key":"ref60","first-page":"694","article-title":"Online and stochastic gradient methods for non-decomposable loss functions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kar"},{"key":"ref61","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2018"},{"key":"ref62","first-page":"393","article-title":"Generalization bounds for the area under the ROC curve","volume":"6","author":"Agarwal","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","first-page":"1","article-title":"A data-dependent generalisation error bound for the AUC","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Usunier"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3101125"},{"key":"ref65","first-page":"21236","article-title":"Sharper generalization bounds for pairwise learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref66","article-title":"Generalization guarantee of SGD for pairwise learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1177\/0962280217718866"},{"key":"ref68","first-page":"497","article-title":"Learning with average top-k loss","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref69","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3934\/cpaa.2020188"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1137\/21M1462428"},{"key":"ref73","first-page":"21668","article-title":"SAPD+: An accelerated stochastic method for nonconvex-concave minimax problems","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"issue":"36","key":"ref74","first-page":"1","article-title":"Accelerated zeroth-order and first-order momentum methods from mini to minimax optimization","volume":"23","author":"Huang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/BF00939081"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0846-1"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003851"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1214\/009053605000000282"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.08.074"},{"key":"ref80","first-page":"1","article-title":"Generalization bounds for deep convolutional neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Long"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/1315245.1315291"},{"key":"ref82","first-page":"1","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref83","first-page":"3864","article-title":"Communication-efficient distributed stochastic AUC maximization with deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11268965.pdf?arnumber=11268965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:06:16Z","timestamp":1770671176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11268965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":83,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3637063","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}