{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:09Z","timestamp":1780949229478,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62406219"],"award-info":[{"award-number":["62406219"]}],"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":["U23B2049"],"award-info":[{"award-number":["U23B2049"]}],"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":["62376194"],"award-info":[{"award-number":["62376194"]}],"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":["62436001"],"award-info":[{"award-number":["62436001"]}],"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":["62272252"],"award-info":[{"award-number":["62272252"]}],"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":["62272253"],"award-info":[{"award-number":["62272253"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3661421","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:52:22Z","timestamp":1770411142000},"page":"9010-9022","source":"Crossref","is-referenced-by-count":0,"title":["FedRSL: Representation Subspace Learning in Model-Heterogeneous Federated Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6236-3673","authenticated-orcid":false,"given":"Liping","family":"Yi","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Machine Learning, College of Artificial Intelligence, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6893-8650","authenticated-orcid":false,"given":"Han","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4533-7108","authenticated-orcid":false,"given":"Wenrui","family":"Wang","sequence":"additional","affiliation":[{"name":"TMCC, SysNet, DISSec, GTIISC, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0387-2501","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"TMCC, SysNet, DISSec, GTIISC, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9010-3278","authenticated-orcid":false,"given":"Xiaoguang","family":"Liu","sequence":"additional","affiliation":[{"name":"TMCC, SysNet, DISSec, GTIISC, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8095","authenticated-orcid":false,"given":"Qinghua","family":"Hu","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Machine Learning, College of Artificial Intelligence, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277135"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3408463"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3105723"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3116976"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407131"},{"key":"ref8","first-page":"25501","article-title":"QSFL: A two-level uplink communication optimization framework for federated learning","volume-title":"Proc. ICML","volume":"162","author":"Yi"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3455098"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3374706"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111633"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281983"},{"key":"ref13","first-page":"1","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","volume-title":"Proc. ICLR","author":"Diao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611781"},{"key":"ref15","article-title":"Federated model heterogeneous Matryoshka representation learning","author":"Yi","year":"2024","journal-title":"arXiv:2406.00488"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/594"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3625558"},{"key":"ref18","article-title":"Advances and open challenges in federated foundation models","author":"Ren","year":"2024","journal-title":"arXiv:2404.15381"},{"key":"ref19","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Collins"},{"key":"ref20","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Pu Liang","year":"2020","journal-title":"arXiv:2001.01523"},{"key":"ref21","article-title":"Federated mutual learning","author":"Shen","year":"2020","journal-title":"arXiv:2006.16765"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29763-x"},{"key":"ref23","first-page":"1","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data","volume-title":"Proc. NeurIPS Workshop Mach. Learn. Phone Consum. Devices","author":"Jeong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref25","article-title":"ReFT: Representation finetuning for language models","author":"Wu","year":"2024","journal-title":"arXiv:2404.03592"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2152"},{"issue":"1","key":"ref27","first-page":"1","article-title":"Revisiting sparsity hunting in federated learning: Why does sparsity consensus matter?","volume":"1","author":"Babakniya","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref28","first-page":"1","article-title":"Internal cross-layer gradients for extending homogeneity to heterogeneity in federated learning","volume-title":"Proc. ICLR","author":"Chan"},{"key":"ref29","first-page":"12876","article-title":"FjORD: Fair and accurate federated learning under heterogeneous targets with ordered dropout","volume-title":"Proc. NIPS","volume":"34","author":"Horv\u00e1th"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3110908"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467309"},{"key":"ref32","first-page":"27504","article-title":"Resilient and communication efficient learning for heterogeneous federated systems","volume-title":"Proc. ICML","volume":"162","author":"Zhu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00146"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3672"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482345"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/nu11020343"},{"key":"ref38","first-page":"17716","article-title":"Federated learning with partial model personalization","volume-title":"Proc. ICML","volume":"162","author":"Pillutla"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545073"},{"key":"ref40","article-title":"Completely heterogeneous federated learning","author":"Liu","year":"2022","journal-title":"arXiv:2210.15865"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673133"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977172.52"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-38569-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599344"},{"key":"ref45","first-page":"1","article-title":"Cronus: Robust and heterogeneous collaborative learning with black-box knowledge transfer","volume-title":"Proc. NeurIPS Workshop","author":"Chang"},{"key":"ref46","article-title":"FedGEMS: Federated learning of larger server models via selective knowledge fusion","author":"Cheng","year":"2021","journal-title":"arXiv:2110.11027"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/399"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548764"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00990"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3070013"},{"key":"ref51","first-page":"1","article-title":"FedMD: Heterogenous federated learning via model distillation","volume-title":"Proc. NeurIPS Workshop","author":"Li"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/205"},{"key":"ref53","first-page":"1","article-title":"Ensemble distillation for robust model fusion in federated learning","volume-title":"Proc. NeurIPS","author":"Lin"},{"key":"ref54","first-page":"14860","article-title":"Architecture agnostic federated learning for neural networks","volume-title":"Proc. ICML","author":"Makhija"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3626325"},{"key":"ref56","first-page":"27132","article-title":"Towards understanding ensemble distillation in federated learning","volume-title":"Proc. ICML","volume":"202","author":"Park"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129371"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3081748"},{"key":"ref59","first-page":"13","article-title":"Towards personalized federated learning via heterogeneous model reassembly","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref60","article-title":"Enhancing heterogeneous federated learning with knowledge extraction and multi-model fusion","author":"Phuong Nguyen","year":"2022","journal-title":"arXiv:2208.07978"},{"key":"ref61","first-page":"10092","article-title":"Parameterized knowledge transfer for personalized federated learning","volume-title":"Proc. NeurIPS","author":"Jie"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30209"},{"key":"ref63","first-page":"1","article-title":"DFRD: Data-free robustness distillation for heterogeneous federated learning","volume-title":"Proc. NeurIPS","author":"Luo"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3272801"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00094"},{"key":"ref66","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2019.8904164"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053448"},{"key":"ref69","first-page":"1","article-title":"Group knowledge transfer: Federated learning of large CNNs at the edge","volume-title":"Proc. NeurIPS","author":"He"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29617"},{"key":"ref71","first-page":"8792","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. NeurIPS","volume":"31","author":"Zhang"},{"key":"ref72","first-page":"137:1","article-title":"Implicit bias of gradient descent for mean squared error regression with two-layer wide neural networks","author":"Jin","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref73","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref74","article-title":"A downsampled variant of ImageNet as an alternative to the CIFAR datasets","author":"Chrabaszcz","year":"2017","journal-title":"arXiv:1707.08819"},{"key":"ref75","first-page":"20461","article-title":"On large-cohort training for federated learning","volume-title":"Proc. NeurIPS","volume":"34","author":"Charles"},{"key":"ref76","first-page":"9489","article-title":"Personalized federated learning using hypernetworks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shamsian"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11373170.pdf?arnumber=11373170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:57Z","timestamp":1780948497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11373170\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":76,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3661421","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}