{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:11:00Z","timestamp":1783527060697,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council under the European Union\u2019s Horizon 2020 research and innovation program\/ERC Advanced Grant E-DUALITY","doi-asserted-by":"publisher","award":["787960"],"award-info":[{"award-number":["787960"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004040","name":"Research Council KU Leuven: Optimization framework for deep kernel machines","doi-asserted-by":"publisher","award":["C14\/18\/068"],"award-info":[{"award-number":["C14\/18\/068"]}],"id":[{"id":"10.13039\/501100004040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"The Research Foundation\u2013Flanders (FWO) projects: GOA4917N (Deep Restricted kernel Machines: Methods and Foundations), Ph.D.\/Postdoctoral grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011878","name":"Flemish Government","doi-asserted-by":"publisher","award":["EU H2020 ICT-48"],"award-info":[{"award-number":["EU H2020 ICT-48"]}],"id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Network TAILOR (Foundations of Trustworthy AI-Integrating Reasoning, Learning and Optimization), Leuven.AI Institute"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tnnls.2022.3186930","type":"journal-article","created":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T19:24:40Z","timestamp":1657308280000},"page":"2124-2138","source":"Crossref","is-referenced-by-count":22,"title":["Compressing Features for Learning With Noisy Labels"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5571-9050","authenticated-orcid":false,"given":"Yingyi","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering (ESAT), KU Leuven, Leuven, STADIUS, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shell Xu","family":"Hu","sequence":"additional","affiliation":[{"name":"Samsung AI Center, Cambridge, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Shen","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunrong","family":"Ai","sequence":"additional","affiliation":[{"name":"School of Management and Economics, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-6352","authenticated-orcid":false,"given":"Johan A. K.","family":"Suykens","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering (ESAT), KU Leuven, Leuven, STADIUS, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"issue":"56","key":"ref2","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","first-page":"1746","article-title":"Learning ordered representations with nested dropout","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"32","author":"Rippel"},{"key":"ref4","first-page":"8536","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref6","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Song"},{"key":"ref7","article-title":"WebVision database: Visual learning and understanding from web data","author":"Li","year":"2017","journal-title":"arXiv:1708.02862"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/9781601983237"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116829"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116251"},{"key":"ref12","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.","volume":"80","author":"Jiang"},{"key":"ref13","first-page":"960","article-title":"Decoupling \u2018when to update\u2019 from \u2018how to update","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Malach"},{"key":"ref14","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref17","first-page":"1196","article-title":"Learning with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Natarajan"},{"key":"ref18","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed","year":"2014","journal-title":"arXiv:1412.6596"},{"key":"ref19","article-title":"Training deep neural-networks using a noise adaptation layer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Goldberger"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref22","article-title":"Learning with feature-dependent label noise: A progressive approach","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00138"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2918794"},{"key":"ref25","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref26","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1142\/5089"},{"key":"ref28","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. NeurIPS","volume":"33","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00302"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3152527"},{"key":"ref31","article-title":"A survey of label-noise representation learning: Past, present and future","author":"Han","year":"2020","journal-title":"arXiv:2011.04406"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI51738.2020.00010"},{"key":"ref33","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref34","first-page":"3355","article-title":"Dimensionality-driven learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Ma"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00046"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00793"},{"key":"ref37","first-page":"1002","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":"ref38","first-page":"17044","article-title":"Identifying mislabeled data using the area under the margin ranking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Pleiss"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1100.0854"},{"key":"ref40","first-page":"10","article-title":"Learning with symmetric label noise: The importance of being unhinged","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"van Rooyen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"issue":"3","key":"ref42","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1018628609742","article-title":"Least squares support vector machine classifiers","volume":"9","author":"Suykens","year":"1999","journal-title":"Neural Process. Lett."},{"key":"ref43","first-page":"12912","article-title":"Clusterability as an alternative to anchor points when learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref44","article-title":"MixMatch: A holistic approach to semi-supervised learning","author":"Berthelot","year":"2019","journal-title":"arXiv:1905.02249"},{"key":"ref45","article-title":"Learning sparse networks using targeted dropout","author":"Gomez","year":"2019","journal-title":"arXiv:1905.13678"},{"key":"ref46","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Kumar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","article-title":"The information bottleneck method","author":"Tishby","year":"2000","journal-title":"arXiv:physics\/0004057"},{"key":"ref50","article-title":"Unpacking information bottlenecks: Unifying information-theoretic objectives in deep learning","author":"Kirsch","year":"2020","journal-title":"arXiv:2003.12537"},{"key":"ref51","article-title":"Deep variational information bottleneck","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Alemi"},{"key":"ref52","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0099421"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1976.10479175"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref56","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00519"},{"key":"ref58","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arazo"},{"key":"ref59","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref61","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref62","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref63","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"37","author":"Ioffe"},{"key":"ref64","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref65","article-title":"A bias-variance decomposition for Bayesian deep learning","volume-title":"Proc. NeurIPS Workshop","author":"Brofos"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10422842\/09819959.pdf?arnumber=9819959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:09:40Z","timestamp":1708110580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9819959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3186930","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}