{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:12:41Z","timestamp":1777655561500,"version":"3.51.4"},"reference-count":84,"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":"am","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":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1908711"],"award-info":[{"award-number":["1908711"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2143197"],"award-info":[{"award-number":["2143197"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore, under its Strategic Capability Research Centers Funding Initiative","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","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.2024.3361375","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:50:06Z","timestamp":1707850206000},"page":"2593-2607","source":"Crossref","is-referenced-by-count":9,"title":["Learning to Predict Gradients for Semi-Supervised Continual Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5135-0316","authenticated-orcid":false,"given":"Yan","family":"Luo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, MN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1239-4428","authenticated-orcid":false,"given":"Yongkang","family":"Wong","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Computing Drive, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Computing Drive, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3054-8934","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, MN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Continual learning in reinforcement environments","author":"Ring","year":"1994"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1994.407413"},{"key":"ref3","first-page":"496","article-title":"A case study of incremental concept induction","volume-title":"Proc. AAAI","volume":"86","author":"Schlimmer"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref5","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref6","first-page":"2990","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref7","article-title":"Variational continual learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nguyen"},{"key":"ref8","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Riemer"},{"key":"ref9","first-page":"4555","article-title":"Overcoming catastrophic forgetting with hard attention to the task","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Serra"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00040"},{"key":"ref12","article-title":"Efficient lifelong learning with a-GEM","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chaudhry"},{"key":"ref13","article-title":"On tiny episodic memories in continual learning","volume-title":"Proc. Workshop Multi-Task Lifelong Reinforcement Learn. ICML","author":"Chaudhry"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_23"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2963387"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref17","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"issue":"2","key":"ref18","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Workshop Challenges Represent. Learn. ICML","volume":"3","author":"Lee"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref20","first-page":"73","article-title":"Semi-supervised learning with meta-gradient","volume-title":"Proc. AISTATS","author":"Zhang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_8"},{"key":"ref22","article-title":"Large scale online learning","volume-title":"Advances in Neural Information Processing Systems","volume":"16","author":"Bottou","year":"2004"},{"issue":"15","key":"ref23","first-page":"495","article-title":"LIBOL: A library for online learning algorithms","volume":"15","author":"Hoi","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","article-title":"Three scenarios for continual learning","volume-title":"Proc. NeurIPS Continual Learn. Workshop","author":"van de Ven"},{"issue":"13","key":"ref25","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"James","year":"2017","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref27","article-title":"Continual learning in low-rank orthogonal subspaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chaudhry"},{"key":"ref28","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Buzzega"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206549"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2597444"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3228380"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3277018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3241211"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3186512"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1965.1053799"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/36.312897"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01145"},{"key":"ref39","article-title":"Not all unlabeled data are equal: Learning to weight data in semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref40","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref44","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Andrychowicz"},{"key":"ref45","first-page":"1627","article-title":"Decoupled neural interfaces using synthetic gradients","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Jaderberg"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref48","first-page":"1724","article-title":"How to escape saddle points efficiently","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/17M1114296"},{"key":"ref50","first-page":"1233","article-title":"A generic approach for escaping saddle points","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Reddi"},{"key":"ref51","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref52","volume-title":"Neural networks for machine learning. lecture 6a. overview of mini-batch gradient descent","author":"Hinton","year":"2012"},{"key":"ref53","article-title":"Adaptive gradient methods with dynamic bound of learning rate","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Luo"},{"key":"ref54","first-page":"9593","article-title":"Lookahead optimizer: K steps forward, 1 step back","author":"Zhang","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref55","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref58","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Chen"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref60","article-title":"Adaptive loss scaling for mixed precision training","author":"Zhao","year":"2019","journal-title":"arXiv:1910.12385"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref64","article-title":"Meta pseudo labels","author":"Pham","year":"2020","journal-title":"arXiv:2003.10580"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref66","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref67","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Vinyals"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref69","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NeurIPS Workshop","author":"Netzer"},{"key":"ref70","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref72","article-title":"Efficient lifelong learning with A-GEM","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chaudhry"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16861"},{"key":"ref75","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1007\/978-3-031-26409-2_3","article-title":"Class-incremental learning via knowledge amalgamation","volume-title":"Machine Learning and Knowledge Discovery in Databases","volume":"13715","author":"de Carvalho","year":"2022"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3282809"},{"key":"ref77","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01093"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00155"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00683"},{"key":"ref82","article-title":"The caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref83","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10877690\/10433526-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10877690\/10433526.pdf?arnumber=10433526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:29Z","timestamp":1764959969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10433526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":84,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3361375","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}