{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T02:18:14Z","timestamp":1778984294791,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572187"],"award-info":[{"award-number":["62572187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472168"],"award-info":[{"award-number":["62472168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Foundation of Education Bureau of Hunan Province, China","award":["25B0452"],"award-info":[{"award-number":["25B0452"]}]},{"name":"Hunan Provincial Major Science and Technology Project","award":["2025QK2008"],"award-info":[{"award-number":["2025QK2008"]}]},{"name":"Joint Key Project of the National Natural Science Foundation of China","award":["U2468205"],"award-info":[{"award-number":["U2468205"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tkde.2026.3668991","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T20:00:14Z","timestamp":1774036814000},"page":"2995-3008","source":"Crossref","is-referenced-by-count":3,"title":["Not All Data are What You Need: A Data-Efficient Training Method Using Heterogeneous Hardware"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6581-7511","authenticated-orcid":false,"given":"Zulong","family":"Diao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0336-2426","authenticated-orcid":false,"given":"Mingyu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Network Technology Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8639-3818","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, State University of New York at Stony Brook, Stony Brook, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2789-1723","authenticated-orcid":false,"given":"Guangxing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Network Technology Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5074-1363","authenticated-orcid":false,"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5009-578X","authenticated-orcid":false,"given":"Jianguo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-Sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9288-4787","authenticated-orcid":false,"given":"Changhua","family":"Pei","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7408-2203","authenticated-orcid":false,"given":"Yanbiao","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9959-1124","authenticated-orcid":false,"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Network Technology Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4964-1135","authenticated-orcid":false,"given":"Gaogang","family":"Xie","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"issue":"120","key":"ref2","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2020","author":"Brown"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101997"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3067825"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC51483.2021.9679362"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00043"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3132413"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3432728"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2921926"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526134"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/724"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.14778\/3659437.3659453"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577528"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441585"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14778\/3648160.3648167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622822"},{"key":"ref18","article-title":"Hardware acceleration of sampling algorithms in sample and aggregate graph neural networks","author":"Gui","year":"2022"},{"key":"ref19","first-page":"1","article-title":"PruneTrain: Fast neural network training by dynamic sparse model reconfiguration","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Lym","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16950"},{"key":"ref21","first-page":"7021","article-title":"Group Fisher pruning for practical network compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01941"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0864-7"},{"key":"ref24","first-page":"1","article-title":"Stochastic optimization with importance sampling for regularized loss minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao","year":"2015"},{"key":"ref25","article-title":"ScreenerNet: Learning Curriculum for Neural Networks","author":"Kim","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2970917"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2951388"},{"key":"ref28","first-page":"5996","article-title":"AutoAssist: A framework to accelerate training of deep neural networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2019"},{"key":"ref29","article-title":"Practical coreset constructions for machine learning","author":"Bachem","year":"2017"},{"key":"ref30","first-page":"14879","article-title":"Coresets via bilevel optimization for continual learning and streaming","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Borsos","year":"2020"},{"key":"ref31","first-page":"14488","article-title":"RETRIEVE: Coreset selection for efficient and robust semi-supervised learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Killamsetty","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16988"},{"key":"ref33","first-page":"4080","article-title":"Coresets for scalable Bayesian logistic regression","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Huggins","year":"2016"},{"key":"ref34","first-page":"20556","article-title":"Deep learning on a data diet: Finding important examples early in training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Paul","year":"2021"},{"key":"ref35","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mirzasoleiman","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.324"},{"key":"ref37","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Pawan Kumar","year":"2010"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"ref39","first-page":"2078","article-title":"Self-paced learning with diversity","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/info14070420"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref43","article-title":"An empirical study of example forgetting during deep neural network learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Toneva","year":"2019"},{"key":"ref44","first-page":"5827","article-title":"A tail-index analysis of stochastic gradient noise in deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Simsekli","year":"2019"},{"key":"ref45","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref46","first-page":"1917","article-title":"\u201cMeta-weight-Net: Learning an explicit mapping for sample weighting","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Shu","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_22"},{"key":"ref48","article-title":"Approximation with artificial neural networks","author":"Cs\u00e1ji","year":"2001"},{"key":"ref49","article-title":"The Mnist Database of Handwritten Digits","author":"LeCun","year":"1998"},{"key":"ref50","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","first-page":"15630","article-title":"Prioritized training on points that are learnable, worth learning, and not yet learnt","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mindermann","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5220\/0006105602530262"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","article-title":"Reformer: The Efficient Transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kitaev","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11479420\/11449457.pdf?arnumber=11449457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:22:28Z","timestamp":1775881348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":56,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3668991","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}