{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T11:36:01Z","timestamp":1780486561585,"version":"3.54.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"STI 2030\u2014Major Projects","award":["2022ZD0209600"],"award-info":[{"award-number":["2022ZD0209600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201058"],"award-info":[{"award-number":["62201058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012236","name":"Beijing Institute of Technology Research Fund Program for Young Scholars","doi-asserted-by":"publisher","award":["6120210047"],"award-info":[{"award-number":["6120210047"]}],"id":[{"id":"10.13039\/501100012236","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M700399"],"award-info":[{"award-number":["2021M700399"]}],"id":[{"id":"10.13039\/501100002858","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":[[2025,2]]},"DOI":"10.1109\/tnnls.2023.3347633","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T14:52:40Z","timestamp":1704725560000},"page":"3730-3743","source":"Crossref","is-referenced-by-count":67,"title":["Cognition-Driven Structural Prior for Instance-Dependent Label Transition Matrix Estimation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5460-7196","authenticated-orcid":false,"given":"Ruiheng","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Electromechanical Dynamic Control, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1556-8058","authenticated-orcid":false,"given":"Zhe","family":"Cao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electromechanical Dynamic Control, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6145-0150","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"Faculty of Electronic and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingyu","family":"Si","sequence":"additional","affiliation":[{"name":"Science and Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyang","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electromechanical Dynamic Control, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8215-6663","authenticated-orcid":false,"given":"Lixin","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Electromechanical Dynamic Control, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3546-6305","authenticated-orcid":false,"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/792538.792543"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2890148"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref5","first-page":"870","article-title":"Adversarial label flips attack on support vector machines","volume-title":"Proc. ECAI","author":"Xiao"},{"key":"ref6","first-page":"17556","article-title":"Label noise in adversarial training: A novel perspective to study robust overfitting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3209992"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3212900"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202752"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3093590"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3067107"},{"key":"ref14","article-title":"A survey of label-noise representation learning: Past, present and future","author":"Han","year":"2020","journal-title":"arXiv:2011.04406"},{"key":"ref15","article-title":"Decoupling \u2018when to update\u2019 from \u2018how to update","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Malach"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref17","first-page":"4006","article-title":"SIGUA: Forgetting may make learning with noisy labels more robust","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Han"},{"key":"ref18","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Song"},{"key":"ref19","first-page":"5739","article-title":"Learning with bad training data via iterative trimmed loss minimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Shen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00674"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.696"},{"key":"ref22","article-title":"Masking: A new perspective of noisy supervision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Han"},{"key":"ref23","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hendrycks"},{"key":"ref24","article-title":"Robust early-learning: Hindering the memorization of noisy labels","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xia"},{"key":"ref25","first-page":"4313","article-title":"Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Li"},{"key":"ref26","first-page":"7978","article-title":"Open-set label noise can improve robustness against inherent label noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wei"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2699783"},{"key":"ref29","article-title":"Active bias: Training more accurate neural networks by emphasizing high variance samples","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Chang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref31","first-page":"3355","article-title":"Dimensionality-driven learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ma"},{"key":"ref32","article-title":"Reliable label correction is a good booster when learning with extremely noisy labels","author":"Wang","year":"2022","journal-title":"arXiv:2205.00186"},{"key":"ref33","first-page":"1","article-title":"Training deep neural-networks using a noise adaptation layer","volume-title":"Proc. ICLR","author":"Goldberger"},{"key":"ref34","article-title":"Learning with confident examples: Rank pruning for robust classification with noisy labels","author":"Northcutt","year":"2017","journal-title":"arXiv:1705.01936"},{"key":"ref35","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zhang"},{"key":"ref36","article-title":"Robustness of conditional GANs to noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Thekumparampil"},{"key":"ref37","first-page":"308","article-title":"Robust active label correction","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kremer"},{"key":"ref38","first-page":"6226","article-title":"Peer loss functions: Learning from noisy labels without knowing noise rates","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_5"},{"key":"ref41","article-title":"L_DMI: A novel information-theoretic loss function for training deep nets robust to label noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Xu"},{"key":"ref42","first-page":"7597","article-title":"Part-dependent label noise: Towards instance-dependent label noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xia"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17363"},{"key":"ref44","first-page":"25302","article-title":"Estimating instance-dependent Bayes-label transition matrix using a deep neural network","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3301876"},{"key":"ref46","first-page":"7260","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Yao"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01613"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3270040"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCES57224.2023.10192616"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-25679-z"},{"key":"ref51","first-page":"9109","article-title":"Robustness to spurious correlations via human annotations","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Srivastava"},{"issue":"34","key":"ref52","first-page":"900","article-title":"Adversarial label flips attack on support vector machines","volume-title":"Proc. ECAI","volume":"34","author":"Xiao"},{"key":"ref53","first-page":"97","article-title":"Support vector machines under adversarial label noise","volume":"20","author":"Biggio","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","article-title":"Learning with noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Natarajan"},{"key":"ref55","first-page":"1789","article-title":"Learning with bounded instance and label-dependent label noise","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Cheng"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00019"},{"key":"ref58","first-page":"6543","article-title":"Normalized loss functions for deep learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ma"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00014"},{"key":"ref60","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yu"},{"key":"ref61","first-page":"4409","article-title":"Instance-dependent label-noise learning under a structural causal model","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Yao","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/340"},{"key":"ref63","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref64","first-page":"6403","article-title":"Provably end-to-end label-noise learning without anchor points","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref65","first-page":"825","article-title":"Confidence scores make instance-dependent label-noise learning possible","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Berthon"},{"key":"ref66","article-title":"Are anchor points really indispensable in label-noise learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Xia"},{"key":"ref67","volume-title":"Machine Learning: An Artificial Intelligence Approach","author":"Michalski","year":"2013"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3025871"},{"key":"ref69","first-page":"2940","article-title":"Cognitive psychology for deep neural networks: A shape bias case study","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ritter"},{"key":"ref70","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref71","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref72","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer","year":"2011"},{"key":"ref73","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref76","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Jiang"},{"key":"ref77","first-page":"10789","article-title":"Searching to exploit memorization effect in learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yao"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10877690\/10382538.pdf?arnumber=10382538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:25Z","timestamp":1764959965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":77,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3347633","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}