{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:32:26Z","timestamp":1776785546045,"version":"3.51.2"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62472401"],"award-info":[{"award-number":["62472401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62132019"],"award-info":[{"award-number":["62132019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["624B2136"],"award-info":[{"award-number":["624B2136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/ton.2025.3547984","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T15:01:11Z","timestamp":1742396471000},"page":"1811-1825","source":"Crossref","is-referenced-by-count":5,"title":["PairingFL: Efficient Federated Learning With Model Splitting and Client Pairing"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2284-3323","authenticated-orcid":false,"given":"Zhiwei","family":"Yao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"given":"Ji","family":"Qi","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Company Ltd., Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0839-3892","authenticated-orcid":false,"given":"Yang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5065-2600","authenticated-orcid":false,"given":"Yunming","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-4577","authenticated-orcid":false,"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9436-7924","authenticated-orcid":false,"given":"Lun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3186936"},{"key":"ref4","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3a74"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3055679"},{"key":"ref8","article-title":"Server-side local gradient averaging and learning rate acceleration for scalable split learning","author":"Pal","year":"2021","journal-title":"arXiv:2112.05929"},{"key":"ref9","article-title":"Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performance","author":"Joshi","year":"2021","journal-title":"arXiv:2109.09246"},{"key":"ref10","article-title":"FedSL: Federated split learning on distributed sequential data in recurrent neural networks","author":"Abedi","year":"2020","journal-title":"arXiv:2011.03180"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19214-2_15"},{"key":"ref13","article-title":"Divergence-aware federated self-supervised learning","author":"Zhuang","year":"2022","journal-title":"arXiv:2204.04385"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2820899"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392686"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512153"},{"key":"ref20","first-page":"1","article-title":"Accelerating federated learning with split learning on locally generated losses","volume-title":"Proc. ICML Workshop Federated Learn. User Privacy Data Confidentiality. ICML Board","author":"Han"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3299851"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3053588"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref25","article-title":"On the convergence of FedAvg on non-IID data","author":"Li","year":"2019","journal-title":"arXiv:1907.02189"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517017"},{"key":"ref27","first-page":"19","article-title":"Oort: Efficient federated learning via guided participant selection","volume-title":"Proc. 15th {USENIX} Symp. Operat. Syst. Design Implement. ({OSDI})","author":"Lai"},{"key":"ref28","article-title":"Optimal client sampling for federated learning","author":"Chen","year":"2020","journal-title":"arXiv:2010.13723"},{"key":"ref29","first-page":"1","article-title":"Diverse client selection for federated learning via submodular maximization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Balakrishnan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413655"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3036157"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761315"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3025446"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796818"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00049"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"key":"ref37","article-title":"Split learning for collaborative deep learning in healthcare","author":"Poirot","year":"2019","journal-title":"arXiv:1912.12115"},{"key":"ref38","article-title":"Split learning for health: Distributed deep learning without sharing raw patient data","author":"Vepakomma","year":"2018","journal-title":"arXiv:1812.00564"},{"key":"ref39","article-title":"Detailed comparison of communication efficiency of split learning and federated learning","author":"Singh","year":"2019","journal-title":"arXiv:1909.09145"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS51746.2020.00017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3135752"},{"key":"ref42","article-title":"Parallel training of deep networks with local updates","author":"Laskin","year":"2020","journal-title":"arXiv:2012.03837"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref44","first-page":"1","article-title":"Federated learning\u2019s blessing: Fedavg has linear speedup","volume-title":"Proc. ICLR-Workshop Distrib. Private Mach. Learn. (DPML)","author":"Qu"},{"key":"ref45","article-title":"Client selection in federated learning: Convergence analysis and power-of-choice selection strategies","author":"Jee Cho","year":"2020","journal-title":"arXiv:2010.01243"},{"key":"ref46","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018","journal-title":"arXiv:1805.09767"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426691"},{"key":"ref48","first-page":"4447","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Stich"},{"key":"ref49","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (PMLR)","author":"Mirzasoleiman"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796982"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/bfb0006528"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/s0167-5060(08)70732-5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9486"},{"key":"ref55","article-title":"Practical defences against model inversion attacks for split neural networks","author":"Titcombe","year":"2021","journal-title":"arXiv:2104.05743"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW51313.2020.00134"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD53861.2021.00038"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3274391"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.522"},{"key":"ref60","article-title":"A federated learning framework for healthcare IoT devices","author":"Yuan","year":"2020","journal-title":"arXiv:2005.05083"},{"key":"ref61","article-title":"FedLite: A scalable approach for federated learning on resource-constrained clients","author":"Wang","year":"2022","journal-title":"arXiv:2201.11865"},{"key":"ref62","first-page":"1","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621351"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690665"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3492140"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3370961"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref68","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv:1804.03209"},{"key":"ref69","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Harry Hsu","year":"2019","journal-title":"arXiv:1909.06335"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11131549\/10934144.pdf?arnumber=10934144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:08Z","timestamp":1755910328000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10934144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":69,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3547984","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}