{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:08:27Z","timestamp":1785542907107,"version":"3.56.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2018AAA0100104"],"award-info":[{"award-number":["2018AAA0100104"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62125602"],"award-info":[{"award-number":["62125602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62076063"],"award-info":[{"award-number":["62076063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106028"],"award-info":[{"award-number":["62106028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chongqing Overseas Chinese Entrepreneurship and Innovation Support Program"},{"name":"CAAI-Huawei MindSpore Open Fund"},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62206050"],"award-info":[{"award-number":["62206050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M700023"],"award-info":[{"award-number":["2021M700023"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province Science Foundation for Youths","award":["BK20210220"],"award-info":[{"award-number":["BK20210220"]}]},{"name":"Young Elite Scientists Sponsorship Program of Jiangsu Association for Science and Technology","award":["TJ-2022-078"],"award-info":[{"award-number":["TJ-2022-078"]}]},{"name":"ARC Discovery Early Career Researcher","award":["DE230101116"],"award-info":[{"award-number":["DE230101116"]}]},{"name":"NVIDIA Academic Hardware Grant Program"},{"name":"JST AIP Acceleration Research","award":["JPMJCR20U3"],"award-info":[{"award-number":["JPMJCR20U3"]}]},{"name":"Institute for AI and Beyond, UTokyo"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3275249","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T17:31:12Z","timestamp":1683826272000},"page":"2569-2583","source":"Crossref","is-referenced-by-count":18,"title":["On the Robustness of Average Losses for Partial-Label Learning"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1524-1304","authenticated-orcid":false,"given":"Jiaqi","family":"Lv","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Ministry of Education), Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7004-9470","authenticated-orcid":false,"given":"Biao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Ministry of Education), Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2839-5799","authenticated-orcid":false,"given":"Lei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8336-5926","authenticated-orcid":false,"given":"Ning","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Ministry of Education), Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9409-6960","authenticated-orcid":false,"given":"Miao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information Technology and Electrical Engineering, The University of Queensland, St Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-7438","authenticated-orcid":false,"given":"Bo","family":"An","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7353-5079","authenticated-orcid":false,"given":"Gang","family":"Niu","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7729-0622","authenticated-orcid":false,"given":"Xin","family":"Geng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Ministry of Education), Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6658-6743","authenticated-orcid":false,"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511624216"},{"key":"ref3","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"issue":"11","key":"ref5","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","first-page":"5050","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/1354856507084420"},{"key":"ref8","first-page":"1230","article-title":"Structured prediction with partial labelling through the infimum loss","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Cabannes"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723401"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.52"},{"key":"ref11","article-title":"Deep learning for classical Japanese literature","author":"Clanuwat","year":"2018"},{"issue":"5","key":"ref12","first-page":"1501","article-title":"Learning from partial labels","volume":"12","author":"Cour","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref14","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref15","article-title":"What neural networks memorize and why: Discovering the long tail via influence estimation","author":"Feldman","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/318"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013542"},{"key":"ref18","first-page":"10948","article-title":"Provably consistent partial-label learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref19","first-page":"3587","article-title":"Discriminative complementary-label learning with weighted loss","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.09.081"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2669639"},{"key":"ref23","article-title":"A survey of label-noise representation learning: Past, present and future","author":"Han","year":"2020"},{"key":"ref24","first-page":"8527","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2006-10503"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23525-7_16"},{"key":"ref28","first-page":"5639","article-title":"Learning from complementary labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ishida"},{"key":"ref29","first-page":"2971","article-title":"Complementary-label learning for arbitrary losses and models","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Ishida"},{"key":"ref30","first-page":"921","article-title":"Learning with multiple labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref31","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref32","volume-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"ref33","first-page":"1","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Laine"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","first-page":"548","article-title":"A conditional multinomial mixture model for superset label learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref37","first-page":"1629","article-title":"Learnability of the superset label learning problem","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref39","first-page":"1","article-title":"On the minimal supervision for training any binary classifier from only unlabeled data","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Lu"},{"key":"ref40","first-page":"1504","article-title":"Learning from candidate labeling sets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref41","first-page":"6500","article-title":"Progressive identification of true labels for partial-label learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Lv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2933837"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2223460"},{"key":"ref45","first-page":"125","article-title":"Learning from corrupted binary labels via class-probability estimation","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Menon"},{"key":"ref46","first-page":"1","article-title":"Can gradient clipping mitigate label noise?","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Menon"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref48","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2012"},{"key":"ref49","first-page":"630","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Morgan"},{"key":"ref50","first-page":"1196","article-title":"Learning with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Natarajan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401958"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"issue":"8","key":"ref54","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI BlogAI"},{"key":"ref55","first-page":"2847","article-title":"On the expressive power of deep neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Raghu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10775"},{"key":"ref59","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref61","first-page":"11091","article-title":"Leveraged weighted loss for partial label learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Wen"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/398"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01554"},{"key":"ref64","first-page":"6838","article-title":"Are anchor points really indispensable in label-noise learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xia"},{"key":"ref65","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015557"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6959"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67661-2_28"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_5"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.97"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref73","first-page":"4048","article-title":"Solving the partial label learning problem: An instance-based approach","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Zhang"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2721942"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939788"},{"key":"ref76","first-page":"8778","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.2200\/s00196ed1v01y200906aim006"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10122995.pdf?arnumber=10122995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:31:57Z","timestamp":1712691117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":78,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3275249","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":[[2024,5]]}}}