{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T15:04:38Z","timestamp":1789311878013,"version":"build-2803163510"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004281","name":"National Science Centre Poland","doi-asserted-by":"publisher","award":["ARTIQ\/0004\/2021"],"award-info":[{"award-number":["ARTIQ\/0004\/2021"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004281","name":"National Science Centre Poland","doi-asserted-by":"publisher","award":["2024\/53\/N\/ST6\/02844"],"award-info":[{"award-number":["2024\/53\/N\/ST6\/02844"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004281","name":"National Science Centre Poland","doi-asserted-by":"publisher","award":["UMO-2021\/01\/2\/ST6\/00004"],"award-info":[{"award-number":["UMO-2021\/01\/2\/ST6\/00004"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.knosys.2026.116676","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:48:08Z","timestamp":1784537288000},"page":"116676","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Improving noisy label learning via transition matrix estimation from feature embeddings"],"prefix":"10.1016","volume":"351","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1024-374X","authenticated-orcid":false,"given":"Mateusz","family":"Wojtulewicz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7182-1349","authenticated-orcid":false,"given":"Piotr","family":"Duda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6960-9525","authenticated-orcid":false,"given":"Leszek","family":"Rutkowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116676_b1","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2233","article-title":"Making deep neural networks robust to label noise: A loss correction approach","author":"Patrini","year":"2017"},{"issue":"11","key":"10.1016\/j.knosys.2026.116676_b2","doi-asserted-by":"crossref","first-page":"8135","DOI":"10.1109\/TNNLS.2022.3152527","article-title":"Learning from noisy labels with deep neural networks: A survey","volume":"34","author":"Song","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116676_b3","series-title":"Advances in Neural Information Processing Systems","article-title":"Part-dependent label noise: Towards instance-dependent label noise","author":"Xia","year":"2020"},{"key":"10.1016\/j.knosys.2026.116676_b4","first-page":"1501","article-title":"Learning from partial labels","volume":"12","author":"Cour","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116676_b5","doi-asserted-by":"crossref","unstructured":"Y. Wang, W. Liu, X. Ma, J. Bailey, H. Zha, L. Song, S.-T. Xia, Iterative Learning with Open-Set Noisy Labels, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8688\u20138696.","DOI":"10.1109\/CVPR.2018.00906"},{"issue":"12","key":"10.1016\/j.knosys.2026.116676_b6","doi-asserted-by":"crossref","first-page":"9940","DOI":"10.1109\/TNNLS.2022.3162316","article-title":"Trusted-data-guided label enhancement on noisy labels","volume":"34","author":"Xu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"11","key":"10.1016\/j.knosys.2026.116676_b7","doi-asserted-by":"crossref","first-page":"6558","DOI":"10.1109\/TNNLS.2021.3082496","article-title":"Learning from crowds with multiple noisy label distribution propagation","volume":"33","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116676_b8","article-title":"Knowledge distillation meets label noise learning: Ambiguity-guided mutual label refinery","author":"Jiang","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"10.1016\/j.knosys.2026.116676_b9","doi-asserted-by":"crossref","first-page":"3758","DOI":"10.1109\/TNNLS.2024.3352285","article-title":"Partial multilabel learning using noise-tolerant broad learning system with label enhancement and dimensionality reduction","volume":"36","author":"Qian","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116676_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113670","article-title":"Open set label noise learning with robust sample selection and margin-guided module","volume":"321","author":"Zhao","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"6","key":"10.1016\/j.knosys.2026.116676_b11","doi-asserted-by":"crossref","first-page":"2568","DOI":"10.1109\/TNNLS.2017.2699783","article-title":"Multiclass learning with partially corrupted labels","volume":"29","author":"Wang","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116676_b12","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"vol. 31","author":"Zhang","year":"2018"},{"key":"10.1016\/j.knosys.2026.116676_b13","first-page":"7260","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","volume":"vol. 33","author":"Yao","year":"2020"},{"issue":"11","key":"10.1016\/j.knosys.2026.116676_b14","doi-asserted-by":"crossref","first-page":"6275","DOI":"10.1109\/TNNLS.2021.3073248","article-title":"Learning with noisy labels via self-reweighting from class centroids","volume":"33","author":"Ma","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"4","key":"10.1016\/j.knosys.2026.116676_b15","doi-asserted-by":"crossref","first-page":"5170","DOI":"10.1109\/TNNLS.2022.3202752","article-title":"A convergence path to deep learning on noisy labels","volume":"35","author":"Liu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116676_b16","article-title":"Cognition-driven structural prior for instance-dependent label transition matrix estimation","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116676_b17","first-page":"7597","article-title":"Part-dependent label noise: Towards instance-dependent label noise","volume":"vol. 33","author":"Xia","year":"2020"},{"key":"10.1016\/j.knosys.2026.116676_b18","first-page":"120549","article-title":"Learning the latent causal structure for modeling label noise","volume":"vol. 37","author":"Lin","year":"2024"},{"key":"10.1016\/j.knosys.2026.116676_b19","doi-asserted-by":"crossref","unstructured":"S. Kim, D. Lee, S. Kang, S. Chae, S. Jang, H. Yu, Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 22477\u201322487.","DOI":"10.1109\/CVPR52733.2024.02121"},{"key":"10.1016\/j.knosys.2026.116676_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113783","article-title":"RACE: Robust adaptive and clustering elimination for noisy labels in continual learning","volume":"324","author":"Yang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116676_b21","first-page":"8527","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume":"vol. 31","author":"Han","year":"2018"},{"key":"10.1016\/j.knosys.2026.116676_b22","unstructured":"H. Song, M. Kim, J.-G. Lee, SELFIE: Refurbishing Unclean Samples for Robust Deep Learning, in: Proceedings of the 36th International Conference on Machine Learning, ICML, 2019, pp. 5907\u20135915."},{"issue":"4","key":"10.1016\/j.knosys.2026.116676_b23","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","article-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","volume":"42","author":"Malkov","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.knosys.2026.116676_b24","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2021","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.knosys.2026.116676_b25","series-title":"Annoy: Approximate nearest neighbors in C++\/Python","author":"Bernhardsson","year":"2013"},{"key":"10.1016\/j.knosys.2026.116676_b26","series-title":"Similarity Search and Applications: 8th International Conference, SISAP 2015, Proceedings 8","first-page":"262","article-title":"Brute-force k-nearest neighbors search on the GPU","author":"Li","year":"2015"},{"key":"10.1016\/j.knosys.2026.116676_b27","series-title":"International Conference on Machine Learning","first-page":"27633","article-title":"Beyond images: Label noise transition matrix estimation for tasks with lower-quality features","author":"Zhu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116676_b28","series-title":"International Conference on Machine Learning","first-page":"12912","article-title":"Clusterability as an alternative to anchor points when learning with noisy labels","author":"Zhu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116676_b29","unstructured":"Y. Liu, Identifiability of Label Noise Transition Matrix, in: Proceedings of the International Conference on Machine Learning, ICML, 2023."},{"key":"10.1016\/j.knosys.2026.116676_b30","series-title":"The MNIST database of handwritten digits","author":"LeCun","year":"1998"},{"key":"10.1016\/j.knosys.2026.116676_b31","series-title":"EMNIST: An extension of MNIST to handwritten letters","author":"Cohen","year":"2017"},{"key":"10.1016\/j.knosys.2026.116676_b32","series-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.knosys.2026.116676_b33","series-title":"Neural Information Processing Systems (NeurIPS) Workshop on Machine Learning for Creativity and Design","article-title":"Deep learning for classical Japanese literature","author":"Clanuwat","year":"2018"},{"key":"10.1016\/j.knosys.2026.116676_b34","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.knosys.2026.116676_b35","series-title":"International Conference on Learning Representations","article-title":"Learning with noisy labels revisited: A study using real-world human annotations","author":"Wei","year":"2022"},{"key":"10.1016\/j.knosys.2026.116676_b36","series-title":"Pytorch image models","author":"Wightman","year":"2019"},{"key":"10.1016\/j.knosys.2026.116676_b37","first-page":"369","article-title":"Super-convergence: Very fast training of neural networks using large learning rates","volume":"vol. 11006","author":"Smith","year":"2019"},{"key":"10.1016\/j.knosys.2026.116676_b38","doi-asserted-by":"crossref","unstructured":"Y. Wang, X. Ma, Z. Chen, Y. Luo, J. Yi, J. Bailey, Symmetric Cross Entropy for Robust Learning with Noisy Labels, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2019, pp. 322\u2013330.","DOI":"10.1109\/ICCV.2019.00041"},{"key":"10.1016\/j.knosys.2026.116676_b39","doi-asserted-by":"crossref","unstructured":"H. Wei, L. Feng, X. Chen, B. An, Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 13726\u201313735.","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"10.1016\/j.knosys.2026.116676_b40","unstructured":"J. Li, R. Socher, S.C.H. Hoi, DivideMix: Learning with Noisy Labels as Semi-supervised Learning, in: International Conference on Learning Representations, ICLR, 2020."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126014024?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126014024?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T14:45:56Z","timestamp":1789310756000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126014024"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":40,"alternative-id":["S0950705126014024"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116676","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improving noisy label learning via transition matrix estimation from feature embeddings","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116676","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116676"}}