{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T01:39:34Z","timestamp":1768354774059,"version":"3.49.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T00:00:00Z","timestamp":1767484800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T00:00:00Z","timestamp":1767484800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11432-025-4576-9","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T10:19:10Z","timestamp":1768299550000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TransTS: an adaptive post-hoc method for probability calibration under label noise"],"prefix":"10.1007","volume":"69","author":[{"given":"Yuefei","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghua","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"4576_CR1","volume-title":"Proceedings of IJCAI","author":"Z Zhang","year":"2023","unstructured":"Zhang Z, Shi B, Zhang H, et al. Nerco: a contrastive learning based two-stage Chinese ner method. In: Proceedings of IJCAI, 2023"},{"key":"4576_CR2","volume-title":"Proceedings of CVPR","author":"R Zhao","year":"2024","unstructured":"Zhao R, Shi B, Ruan J, et al. Estimating noisy class posterior with part-level labels for noisy label learning. In: Proceedings of CVPR, 2024"},{"key":"4576_CR3","doi-asserted-by":"crossref","first-page":"2539","DOI":"10.1109\/TKDE.2021.3049692","volume":"34","author":"Z Peng","year":"2022","unstructured":"Peng Z, Luo M, Li J, et al. A deep multi-view framework for anomaly detection on attributed networks. IEEE Trans Knowl Data Eng, 2022, 34: 2539\u20132552","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"4576_CR4","volume-title":"Proceedings of ICLR","author":"L Tao","year":"2024","unstructured":"Tao L, Zhu Y, Guo H, et al. A benchmark study on calibration. In: Proceedings of ICLR, 2024"},{"key":"4576_CR5","volume-title":"Proceedings of ICLR","author":"J Blasiok","year":"2024","unstructured":"Blasiok J, Nakkiran P. Smooth ECE: principled reliability diagrams via kernel smoothing. In: Proceedings of ICLR, 2024"},{"key":"4576_CR6","volume-title":"Proceedings of NeurIPS","author":"J Mukhoti","year":"2020","unstructured":"Mukhoti J, Kulharia V, Sanyal A, et al. Calibrating deep neural networks using focal loss. In: Proceedings of NeurIPS, 2020"},{"key":"4576_CR7","volume-title":"Proceedings of NeurIPS","author":"A Ghosh","year":"2022","unstructured":"Ghosh A, Schaaf T, Gormley M. Adafocal: calibration-aware adaptive focal loss. In: Proceedings of NeurIPS, 2022"},{"key":"4576_CR8","volume-title":"Proceedings of ICML","author":"L Tao","year":"2023","unstructured":"Tao L, Dong M, Xu C. Dual focal loss for calibration. In: Proceedings of ICML, 2023"},{"key":"4576_CR9","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.gpb.2017.07.003","volume":"16","author":"C Cao","year":"2018","unstructured":"Cao C, Liu F, Tan H, et al. Deep learning and its applications in biomedicine. Genomics Proteomics BioInf, 2018, 16: 17\u201332","journal-title":"Genomics Proteomics BioInf"},{"key":"4576_CR10","doi-asserted-by":"publisher","first-page":"100270","DOI":"10.1016\/j.cosrev.2020.100270","volume":"37","author":"X Huang","year":"2020","unstructured":"Huang X, Kroening D, Ruan W, et al. A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability. Comput Sci Rev, 2020, 37: 100270","journal-title":"Comput Sci Rev"},{"key":"4576_CR11","doi-asserted-by":"publisher","first-page":"106384","DOI":"10.1016\/j.asoc.2020.106384","volume":"93","author":"A M Ozbayoglu","year":"2020","unstructured":"Ozbayoglu A M, Gudelek M U, Sezer O B. Deep learning for financial applications: a survey. Appl Soft Comput, 2020, 93: 106384","journal-title":"Appl Soft Comput"},{"key":"4576_CR12","volume-title":"Proceedings of ICML","author":"C Guo","year":"2017","unstructured":"Guo C, Pleiss G, Sun Y, et al. On calibration of modern neural networks. In: Proceedings of ICML, 2017"},{"key":"4576_CR13","volume-title":"Proceedings of ICLR","author":"M Chidambaram","year":"2024","unstructured":"Chidambaram M, Ge R. On the limitations of temperature scaling for distributions with overlaps. In: Proceedings of ICLR, 2024"},{"key":"4576_CR14","unstructured":"Wang T, Wang Y, Zhou J, et al. From aleatoric to epistemic: exploring uncertainty quantification techniques in artificial intelligence. ArXiv:2501.03282"},{"key":"4576_CR15","volume-title":"Proceedings of ICML","author":"J Zhang","year":"2020","unstructured":"Zhang J, Kailkhura B, Han T Y J. Mix-n-match: ensemble and compositional methods for uncertainty calibration in deep learning. In: Proceedings of ICML, 2020"},{"key":"4576_CR16","volume-title":"Proceedings of ECCV","author":"C Tomani","year":"2022","unstructured":"Tomani C, Cremers D, Buettner F. Parameterized temperature scaling for boosting the expressive power in post-hoc uncertainty calibration. In: Proceedings of ECCV, 2022"},{"key":"4576_CR17","unstructured":"Gupta K, Rahimi A M, Ajanthan T, et al. Calibration of neural networks using splines. ArXiv:2006.12800"},{"key":"4576_CR18","volume-title":"Proceedings of NeurIPS","author":"A L Coz","year":"2024","unstructured":"Coz A L, Herbin S, Adjed F. Confidence calibration of classifiers with many classes. In: Proceedings of NeurIPS, 2024"},{"key":"4576_CR19","volume-title":"Proceedings of AISTATS","author":"S Park","year":"2020","unstructured":"Park S, Bastani O, Weimer J, et al. Calibrated prediction with covariate shift via unsupervised domain adaptation. In: Proceedings of AISTATS, 2020"},{"key":"4576_CR20","volume-title":"Proceedings of CVPR","author":"B Liu","year":"2022","unstructured":"Liu B, Ben Ayed I, Galdran A, et al. The devil is in the margin: margin-based label smoothing for network calibration. In: Proceedings of CVPR, 2022"},{"key":"4576_CR21","volume-title":"Proceedings of CVPR","author":"J Cheng","year":"2022","unstructured":"Cheng J, Vasconcelos N. Calibrating deep neural networks by pairwise constraints. In: Proceedings of CVPR, 2022"},{"key":"4576_CR22","volume-title":"Proceedings of ICLR","author":"L Hui","year":"2021","unstructured":"Hui L, Belkin M. Evaluation of neural architectures trained with square loss vs cross-entropy in classification tasks. In: Proceedings of ICLR, 2021"},{"key":"4576_CR23","volume-title":"Proceedings of AAAI","author":"D Neo","year":"2024","unstructured":"Neo D, Winkler S, Chen T. Maxent loss: constrained maximum entropy for calibration under out-of-distribution shift. In: Proceedings of AAAI, 2024"},{"key":"4576_CR24","doi-asserted-by":"publisher","first-page":"8135","DOI":"10.1109\/TNNLS.2022.3152527","volume":"34","author":"H Song","year":"2023","unstructured":"Song H, Kim M, Park D, et al. Learning from noisy labels with deep neural networks: a survey. IEEE Trans Neural Netw Learn Syst, 2023, 34: 8135\u20138153","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4576_CR25","volume-title":"Proceedings of CVPR","author":"Q Wei","year":"2023","unstructured":"Wei Q, Feng L, Sun H, et al. Fine-grained classification with noisy labels. In: Proceedings of CVPR, 2023"},{"key":"4576_CR26","volume-title":"Proceedings of CVPR","author":"Z Huang","year":"2023","unstructured":"Huang Z, Zhang J, Shan H. Twin contrastive learning with noisy labels. In: Proceedings of CVPR, 2023"},{"key":"4576_CR27","volume-title":"Proceedings of NeurIPS","author":"S Li","year":"2022","unstructured":"Li S, Xia X, Zhang H, et al. Estimating noise transition matrix with label correlations for noisy multi-label learning. In: Proceedings of NeurIPS, 2022"},{"key":"4576_CR28","volume-title":"Proceedings of NeurIPS","author":"X Xia","year":"2019","unstructured":"Xia X, Liu T, Wang N, et al. Are anchor points really indispensable in label-noise learning? In: Proceedings of NeurIPS, 2019"},{"key":"4576_CR29","volume-title":"Proceedings of ICLR","author":"J Li","year":"2020","unstructured":"Li J, Socher R, Hoi S C. Dividemix: learning with noisy labels as semi-supervised learning. In: Proceedings of ICLR, 2020"},{"key":"4576_CR30","volume-title":"Proceedings of NIPS","author":"D B Wang","year":"2021","unstructured":"Wang D B, Zhang M L. Rethinking calibration of deep neural networks: do not be afraid of overconfidence. In: Proceedings of NIPS, 2021"},{"key":"4576_CR31","volume-title":"Proceedings of ICML","author":"D B Wang","year":"2024","unstructured":"Wang D B, Zhang M L. Calibration bottleneck: over-compressed representations are less calibratable. In: Proceedings of ICML, 2024"},{"key":"4576_CR32","volume-title":"Proceedings of AAAI","author":"M P Naeini","year":"2015","unstructured":"Naeini M P, Cooper G, Hauskrecht M. Obtaining well calibrated probabilities using Bayesian binning. In: Proceedings of AAAI, 2015"},{"key":"4576_CR33","first-page":"3047","volume":"45","author":"X Xia","year":"2023","unstructured":"Xia X, Han B, Wang N, et al. Extended: learning with mixed closed-set and open-set noisy labels. IEEE Trans Pattern Anal Mach Intell, 2023, 45: 3047\u20133058","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4576_CR34","volume-title":"Proceedings of CVPR","author":"D Cheng","year":"2022","unstructured":"Cheng D, Liu T, Ning Y, et al. Instance-dependent label-noise learning with manifold-regularized transition matrix estimation. In: Proceedings of CVPR, 2022"},{"key":"4576_CR35","volume-title":"Proceedings of ICML","author":"S Yang","year":"2022","unstructured":"Yang S, Yang E, Han B, et al. Estimating instance-dependent Bayes-label transition matrix using a deep neural network. In: Proceedings of ICML, 2022"},{"key":"4576_CR36","volume-title":"Proceedings of NeurIPS","author":"B Han","year":"2018","unstructured":"Han B, Yao J, Niu G, et al. Masking: a new perspective of noisy supervision. In: Proceedings of NeurIPS, 2018"},{"key":"4576_CR37","volume-title":"Proceedings of NeurIPS","author":"B Han","year":"2018","unstructured":"Han B, Yao Q, Yu X, et al. Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Proceedings of NeurIPS, 2018"},{"key":"4576_CR38","first-page":"125","volume-title":"Proceedings of International Conference on Machine Learning","author":"A Menon","year":"2015","unstructured":"Menon A, van Rooyen B, Ong C S, et al. Learning from corrupted binary labels via class-probability estimation. In: Proceedings of International Conference on Machine Learning, 2015. 125\u2013134"},{"key":"4576_CR39","volume-title":"Proceedings of CVPR","author":"G Patrini","year":"2017","unstructured":"Patrini G, Rozza A, Krishna Menon A, et al. Making deep neural networks robust to label noise: a loss correction approach. In: Proceedings of CVPR, 2017"},{"key":"4576_CR40","volume-title":"Proceedings of NeurIPS","author":"Y Yao","year":"2020","unstructured":"Yao Y, Liu T, Han B, et al. Dual T: reducing estimation error for transition matrix in label-noise learning. In: Proceedings of NeurIPS, 2020"},{"key":"4576_CR41","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky A, Hinton G, et al. Learning multiple layers of features from tiny images. 2009. https:\/\/api.semanticscholar.org\/CorpusID:18268744"},{"key":"4576_CR42","volume-title":"Proceedings of ICML","author":"H Song","year":"2019","unstructured":"Song H, Kim M, Lee J G. SELFIE: refurbishing unclean samples for robust deep learning. In: Proceedings of ICML, 2019"},{"key":"4576_CR43","volume-title":"Proceedings of CVPR","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of CVPR, 2016"},{"key":"4576_CR44","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv:2010.11929"},{"key":"4576_CR45","unstructured":"Zagoruyko S, Komodakis N. Wide residual networks. ArXiv:1605.07146"},{"key":"4576_CR46","volume-title":"Proceedings of CVPR","author":"G Huang","year":"2017","unstructured":"Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks. In: Proceedings of CVPR, 2017"},{"key":"4576_CR47","volume-title":"Proceedings of ICML","author":"A Kumar","year":"2018","unstructured":"Kumar A, Sarawagi S, Jain U. Trainable calibration measures for neural networks from kernel mean embeddings. In: Proceedings of ICML, 2018"},{"key":"4576_CR48","volume-title":"Proceedings of ICML","author":"B Zadrozny","year":"2001","unstructured":"Zadrozny B, Elkan C. Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers. In: Proceedings of ICML, 2001"},{"key":"4576_CR49","volume-title":"Proceedings of ICCV","author":"Y Zou","year":"2023","unstructured":"Zou Y, Deng W, Zheng L. Adaptive calibrator ensemble: navigating test set difficulty in out-of-distribution scenarios. In: Proceedings of ICCV, 2023"},{"key":"4576_CR50","volume-title":"Proceedings of the 29th European Signal Processing Conference (EUSIPCO)","author":"L Frenkel","year":"2021","unstructured":"Frenkel L, Goldberger J. Network calibration by class-based temperature scaling. In: Proceedings of the 29th European Signal Processing Conference (EUSIPCO), 2021"},{"key":"4576_CR51","volume-title":"Proceedings of ICML","author":"S Jung","year":"2023","unstructured":"Jung S, Seo S, Jeong Y, et al. Scaling of class-wise training losses for post-hoc calibration. In: Proceedings of ICML, 2023"},{"key":"4576_CR52","volume-title":"Proceedings of ICML","author":"H Wei","year":"2023","unstructured":"Wei H, Zhuang H, Xie R, et al. Mitigating memorization of noisy labels by clipping the model prediction. In: Proceedings of ICML, 2023"},{"key":"4576_CR53","volume-title":"Proceedings of ICLR","author":"H Bae","year":"2024","unstructured":"Bae H, Shin S, Na B, et al. Dirichlet-based per-sample weighting by transition matrix for noisy label learning. In: Proceedings of ICLR, 2024"},{"key":"4576_CR54","unstructured":"Nguyen K, O\u2019Connor B. Posterior calibration and exploratory analysis for natural language processing models. ArXiv:1508.05154"},{"key":"4576_CR55","volume-title":"Proceedings of NeurIPS","author":"M Kull","year":"2019","unstructured":"Kull M, Perello Nieto M, K\u00e4ngsepp M, et al. Beyond temperature scaling: obtaining well-calibrated multi-class probabilities with Dirichlet calibration. In: Proceedings of NeurIPS, 2019"},{"key":"4576_CR56","volume-title":"Proceedings of CVPR","author":"B Liu","year":"2023","unstructured":"Liu B, Rony J, Galdran A, et al. Class adaptive network calibration. In: Proceedings of CVPR, 2023"},{"key":"4576_CR57","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"H Wei","year":"2020","unstructured":"Wei H, Feng L, Chen X, et al. Combating noisy labels by agreement: a joint training method with co-regularization. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020"},{"key":"4576_CR58","volume-title":"Proceedings of AAAI","author":"C C Zong","year":"2024","unstructured":"Zong C C, Wang Y W, Xie M K, et al. Dirichlet-based prediction calibration for learning with noisy labels. In: Proceedings of AAAI, 2024"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-025-4576-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-025-4576-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-025-4576-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T12:03:38Z","timestamp":1768305818000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-025-4576-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,4]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["4576"],"URL":"https:\/\/doi.org\/10.1007\/s11432-025-4576-9","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,4]]},"assertion":[{"value":"12 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"122105"}}