{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:45:49Z","timestamp":1773193549659,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB4701400\/4701402"],"award-info":[{"award-number":["2022YFB4701400\/4701402"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62293545"],"award-info":[{"award-number":["62293545"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62576364"],"award-info":[{"award-number":["62576364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Basic Research Project","doi-asserted-by":"publisher","award":["62576364"],"award-info":[{"award-number":["62576364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Basic Research Key Project","award":["JCYJ20241202124430041"],"award-info":[{"award-number":["JCYJ20241202124430041"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2026.3656454","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:39:30Z","timestamp":1768941570000},"page":"3782-3791","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Partial Model Personalization With Guaranteed Nonconvex Convergence"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6364-9558","authenticated-orcid":false,"given":"Yifan","family":"Shi","sequence":"first","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5029-4287","authenticated-orcid":false,"given":"Yingqi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2271-252X","authenticated-orcid":false,"given":"Yan","family":"Sun","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Lin","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3542-0593","authenticated-orcid":false,"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence and Robotics, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-12833-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/Blockchain55522.2022.00020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3138848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3178378"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.3014385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS51040.2020.00083"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279714"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196503"},{"key":"ref9","first-page":"31269","article-title":"Improving the model consistency of decentralized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shi"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref11","first-page":"17716","article-title":"Federated learning with partial model personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pillutla"},{"key":"ref12","article-title":"Federated learning with personalization layers","author":"Ghuhan Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref13","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Collins"},{"key":"ref14","article-title":"Decentralized SGD and average-direction SAM are asymptotically equivalent","author":"Zhu","year":"2023","journal-title":"arXiv:2306.02913"},{"key":"ref15","article-title":"Decentralized federated learning: Fundamentals, state of the art, frameworks, trends, and challenges","author":"Beltr\u00e1n","year":"2022","journal-title":"arXiv:2211.08413"},{"key":"ref16","article-title":"BrainTorrent: A peer-to-peer environment for decentralized federated learning","author":"Guha Roy","year":"2019","journal-title":"arXiv:1905.06731"},{"key":"ref17","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":"ref18","first-page":"4587","article-title":"DisPFL: Towards communication-efficient personalized federated learning via decentralized sparse training","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Dai"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejco.2022.100041"},{"key":"ref20","article-title":"FedBABU: Towards enhanced representation for federated image classification","author":"Oh","year":"2021","journal-title":"arXiv:2106.06042"},{"key":"ref21","article-title":"On bridging generic and personalized federated learning for image classification","author":"Chen","year":"2021","journal-title":"arXiv:2107.00778"},{"key":"ref22","article-title":"Sharper convergence guarantees for federated learning with partial model personalization","author":"Chen","year":"2023","journal-title":"arXiv:2309.17409"},{"key":"ref23","article-title":"Gossip training for deep learning","author":"Blot","year":"2016","journal-title":"arXiv:1611.09726"},{"key":"ref24","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lian"},{"key":"ref25","first-page":"18308","article-title":"Decentralized accelerated proximal gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ye"},{"issue":"238","key":"ref26","first-page":"1","article-title":"Deepca: Decentralized exact pca with linear convergence rate","volume":"22","author":"Ye","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3138977"},{"key":"ref28","first-page":"1662","article-title":"Communication-efficient distributed optimization in networks with gradient tracking and variance reduction","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist.","volume":"108","author":"Li","year":"2020"},{"key":"ref29","article-title":"Quasi-global momentum: Accelerating decentralized deep learning on heterogeneous data","author":"Lin","year":"2021","journal-title":"arXiv:2102.04761"},{"key":"ref30","first-page":"4387","article-title":"The non-iid data quagmire of decentralized machine learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hsieh"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00954"},{"key":"ref32","first-page":"27479","article-title":"Topology-aware generalization of decentralized sgd","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref34","first-page":"18250","article-title":"Generalized federated learning via sharpness aware minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qu"},{"key":"ref35","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Andriushchenko"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01204"},{"key":"ref37","first-page":"30950","article-title":"Make sharpness-aware minimization stronger: A sparsified perturbation approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mi"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01552"},{"key":"ref39","article-title":"FedSpeed: Larger local interval, less communication round, and higher generalization accuracy","author":"Sun","year":"2023","journal-title":"arXiv:2302.10429"},{"key":"ref40","article-title":"AdaSAM: Boosting sharpness-aware minimization with adaptive learning rate and momentum for training deep neural networks","author":"Sun","year":"2023","journal-title":"arXiv:2303.00565"},{"key":"ref41","article-title":"Towards the flatter landscape and better generalization in federated learning under client-level differential privacy","author":"Shi","year":"2023","journal-title":"arXiv:2305.00873"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02352"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00386"},{"key":"ref47","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Li"},{"key":"ref48","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref49","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_38"},{"key":"ref52","first-page":"6357","article-title":"Ditto: Fair and robust federated learning through personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC61105.2024.00081"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11359328.pdf?arnumber=11359328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:21:42Z","timestamp":1773120102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359328\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/ton.2026.3656454","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}