{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:20:14Z","timestamp":1783059614663,"version":"3.54.6"},"reference-count":202,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376014"],"award-info":[{"award-number":["62376014"]}],"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":["61876012"],"award-info":[{"award-number":["61876012"]}],"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":["621720229"],"award-info":[{"award-number":["621720229"]}],"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":["U19B2039"],"award-info":[{"award-number":["U19B2039"]}],"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":["62441232"],"award-info":[{"award-number":["62441232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4202003"],"award-info":[{"award-number":["4202003"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation for China University Industry-University-Research Innovation","award":["2021JQR023"],"award-info":[{"award-number":["2021JQR023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tkde.2026.3675811","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:08:50Z","timestamp":1773950930000},"page":"4674-4693","source":"Crossref","is-referenced-by-count":0,"title":["Self-Knowledge Distillation and Its Application: A Survey"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4334-2444","authenticated-orcid":false,"given":"Kai","family":"Xu","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4977-0183","authenticated-orcid":false,"given":"Lichun","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2024.3349602"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122836"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref8","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285213"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3438074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01142"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3171571"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"ref16","first-page":"2765","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01052"},{"key":"ref18","first-page":"1","article-title":"Large scale distributed neural network training through online distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Anil"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3657282"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3294416"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358085"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17225"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01164"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110422"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015565"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2024.3453763"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16885"},{"key":"ref33","first-page":"4694","article-title":"When does label smoothing help?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"M\u00fcller"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/208"},{"key":"ref36","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00297"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015628"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/s21082792"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089942"},{"key":"ref42","article-title":"Self-distillation with batch knowledge ensembling improves imageNet classification","author":"Ge","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00716"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3067100"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119859"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00198"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26351-4_25"},{"key":"ref49","first-page":"5714","article-title":"Self-supervised label augmentation via input transformations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25937"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01576"},{"key":"ref53","article-title":"Logit-based losses limit the effectiveness of feature knowledge distillation","author":"Cooper","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2025.3552326"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.104"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892575"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_20"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120586"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746529"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.12.014"},{"key":"ref61","first-page":"5171","article-title":"On variational bounds of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Poole"},{"key":"ref62","article-title":"On mutual information maximization for representation learning","author":"Tschannen","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096778"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_31"},{"key":"ref65","first-page":"1","article-title":"\u201dmixup: Beyond empirical risk management","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3400368"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446387"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3390\/app14167022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106215"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124629"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_10"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01103"},{"key":"ref74","article-title":"Large scale distributed neural network training through online distillation","author":"Anil","year":"2018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.101"},{"key":"ref76","first-page":"1","article-title":"Knowledge distillation by on-the-fly native ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222013"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414664"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412615"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257878"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3212733"},{"key":"ref83","first-page":"2006","article-title":"Feature-map-level online adversarial knowledge distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chung"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022859003006"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_20"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17234"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152732"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01932"},{"key":"ref89","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"ref90","article-title":"Tiny imageNet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231 N"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref92","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref94","first-page":"806","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Khosla"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref96","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref98","article-title":"CINIC-10 is not ImageNet or CIFAR-10","author":"Darlow","year":"2018"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_5"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124135"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3370731"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29519"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194549"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3125249"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3343521"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00092"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20240"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104314"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00631"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343397"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3251371"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3375789"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111504"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01065"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3386778"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358697"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111762"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104681"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387754"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231122"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19973"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00149"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107876"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112503"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-024-01420-1"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3298798"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3431916"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109312"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107597"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00060"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232021"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29147"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-024-01633-0"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3386470"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1930"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-056-4_050"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-021-1119-0"},{"key":"ref140","first-page":"1","article-title":"Trans-encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref141","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.385"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.145"},{"key":"ref144","article-title":"Unmemorization in large language models via self-distillation and deliberate imagination","author":"Dong","year":"2024"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.58"},{"key":"ref146","article-title":"STaR: Self-taught reasoner bootstrapping reasoning with reasoning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zelikman"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.523"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.67"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.603"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.7"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3606231"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref153","article-title":"OmniQuant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28052"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3384060"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111724"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01369"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531922"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570423"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30678-5_38"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645590"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/3711121"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/314"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512209"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389706"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28737"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124138"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3374773"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3303885"},{"key":"ref171","article-title":"Teaching yourself: C graph self-distillation on neighborhood for node classification","author":"Wu","year":"2022"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3124599"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3174394"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.11.292"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2787"},{"key":"ref176","article-title":"Local-global knowledge distillation in heterogeneous federated learning with non-IID data","author":"Yao","year":"2021"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3327757"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3189703"},{"key":"ref179","first-page":"1","article-title":"Class-wise adaptive self distillation for heterogeneous federated learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"He"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3225185"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107851"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3330514"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05444-8"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110942"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29004"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3087731"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00520"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16839"},{"key":"ref189","article-title":"Switchable precision neural networks","author":"Guerra","year":"2020"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3553162"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3561046"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01622-8"},{"key":"ref193","first-page":"1","article-title":"Long-tailed recognition by routing diverse distribution-aware experts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-024-03086-z"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17237-1"},{"key":"ref196","first-page":"1","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Allen-Zhu"},{"key":"ref197","article-title":"ResNet strikes back: An improved training procedure in timm","author":"Wightman","year":"2021"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"ref199","first-page":"1","article-title":"In search of lost domain generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gulrajani","year":"2021"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.513"},{"key":"ref201","article-title":"Smoothing out hallucinations: Mitigating LLM hallucination with smoothed knowledge distillation","author":"Nguyen","year":"2025"},{"key":"ref202","article-title":"LLM-NEO: Parameter efficient knowledge distillation for large language models","author":"Yang","year":"2024"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11538062\/11443225.pdf?arnumber=11443225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:45:35Z","timestamp":1783057535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":202,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3675811","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":[[2026,7]]}}}