{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:15:35Z","timestamp":1774419335166,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889047","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Learning from Ambiguous Data with Hard Labels"],"prefix":"10.1109","author":[{"given":"Zeke","family":"Xie","sequence":"first","affiliation":[{"name":"HKUST(GZ),Guangzhou,China"}]},{"given":"Zheng","family":"He","sequence":"additional","affiliation":[{"name":"University of British Columbia,Vancouver,Canada"}]},{"given":"Nan","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Tübingen,Tübingen,Germany"}]},{"given":"Lichen","family":"Bai","sequence":"additional","affiliation":[{"name":"HKUST(GZ),Guangzhou,China"}]},{"given":"Bao","family":"Li","sequence":"additional","affiliation":[{"name":"HKUST(GZ),Guangzhou,China"}]},{"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Mingming","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Institute of Mathematical Sciences and Applications,Beijing,China"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"VecML Inc.,Seattle,Washington,U.S.A."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2946162"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2535242"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-016-9491-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5412-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.696"},{"key":"ref6","first-page":"8634","article-title":"Evaluating machine accuracy on imagenet","volume-title":"International Conference on Machine Learning","author":"Shankar"},{"key":"ref7","article-title":"Learning with noisy labels revisited: A study using real-world human annotations","volume-title":"The Tenth International Conference on Learning Representations, ICLR","author":"Wei"},{"key":"ref8","article-title":"Pervasive label errors in test sets destabilize machine learning benchmarks","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Northcutt"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2689998"},{"key":"ref10","article-title":"Learning soft labels via meta learning","author":"Vyas","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00971"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00237"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01403"},{"key":"ref14","first-page":"11448","article-title":"Positive-negative momentum: Manipulating stochastic gradient noise to improve generalization","volume-title":"International Conference on Machine Learning","author":"Xie"},{"key":"ref15","article-title":"Beyond hard labels: Investigating data label distributions","author":"Grossmann","year":"2022"},{"key":"ref16","first-page":"8635","article-title":"Sparse double descent: Where network pruning aggravates overfitting","volume-title":"International Conference on Machine Learning","author":"He"},{"key":"ref17","article-title":"A survey of label-noise representation learning: Past, present and future","author":"Han","year":"2020"},{"key":"ref18","article-title":"Analysis of learning from positive and unlabeled data","volume-title":"Advances in neural information processing systems","volume":"27","author":"Du Plessis"},{"key":"ref19","first-page":"1386","article-title":"Convex formulation for learning from positive and unlabeled data","volume-title":"International Conference on machine learning","author":"Du Plessis"},{"key":"ref20","article-title":"Positiveunlabeled learning with non-negative risk estimator","volume-title":"Advances in neural information processing systems","volume":"30","author":"Kiryo"},{"key":"ref21","article-title":"Theoretical comparisons of positive-unlabeled learning against positive-negative learning","volume-title":"Advances in neural information processing systems","volume":"29","author":"Niu"},{"key":"ref22","first-page":"125","article-title":"Learning from corrupted binary labels via class-probability estimation","volume-title":"International Conference on machine learning","author":"Menon"},{"key":"ref23","article-title":"Estimating the class prior and posterior from noisy positives and unlabeled data","volume-title":"Advances in neural information processing systems","volume":"29","author":"Jain"},{"key":"ref24","first-page":"221","article-title":"Class-prior estimation for learning from positive and unlabeled data","volume-title":"Asian Conference on Machine Learning","author":"Christoffel"},{"key":"ref25","article-title":"Rethinking class-prior estimation for positive-unlabeled learning","volume-title":"International Conference on Learning Representations","author":"Yao"},{"key":"ref26","article-title":"Generalized jensen-shannon divergence loss for learning with noisy labels","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Englesson"},{"key":"ref27","article-title":"mixup: Beyond empirical risk minimization","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings","author":"Zhang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed","year":"2014"},{"key":"ref31","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Advances in neural information processing systems","volume":"31","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref33","article-title":"L_dmi: A novel informationtheoretic loss function for training deep nets robust to label noise","volume-title":"Advances in neural information processing systems","volume":"32","author":"Xu"},{"key":"ref34","article-title":"Co-teaching: Robust training of deep neural networkswith extremely noisy labels","volume-title":"Advances in neural information processing systems","volume":"31","author":"Han"},{"key":"ref35","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"International Conference on Machine Learning","author":"Yu"},{"key":"ref36","article-title":"Robust early-learning: Hindering the memorization of noisy labels","volume-title":"International Conference on learning representations","author":"Xia"},{"key":"ref37","first-page":"20331","article-title":"Earlylearning regularization prevents memorization of noisy labels","volume-title":"Advances in neural information processing systems","volume":"33","author":"Liu"},{"key":"ref38","article-title":"Dividemix: Learning with noisy labels as semi-supervised learning","volume-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020","author":"Li"},{"key":"ref39","article-title":"Understanding and improving early stopping for learning with noisy labels","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Bai"},{"key":"ref40","first-page":"596","article-title":"Fixmatch: Simplifying semisupervised learning with consistency and confidence","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Sohn"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889047.pdf?arnumber=10889047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:20Z","timestamp":1774416140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889047","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}