{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:28:48Z","timestamp":1778347728749,"version":"3.51.4"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["62372028"],"award-info":[{"award-number":["62372028"]}],"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":["62372027"],"award-info":[{"award-number":["62372027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3585927","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T18:44:10Z","timestamp":1753296250000},"page":"18613-18627","source":"Crossref","is-referenced-by-count":4,"title":["The Diversity Bonus: Learning From Dissimilar Clients in Personalized Federated Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6987-3972","authenticated-orcid":false,"given":"Xinghao","family":"Wu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3946-5107","authenticated-orcid":false,"given":"Jianwei","family":"Niu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2705-8731","authenticated-orcid":false,"given":"Xuefeng","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6381-1420","authenticated-orcid":false,"given":"Guogang","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9261-5210","authenticated-orcid":false,"given":"Shaojie","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Management Science and Systems, School of Management, Center for AI Business Innovation, University at Buffalo, Getzville, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7328-8039","authenticated-orcid":false,"given":"Wanyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2725-2529","authenticated-orcid":false,"given":"Jiannong","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2016","article-title":"Regulation (Eu) 2016\/679 of the European parliament and of the council","volume":"679","author":"Regulation","year":"2016","journal-title":"Regulation"},{"key":"ref2","volume-title":"Federated Learning: Collaborative Machine Learning Without Centralized Training Data","author":"McMahan","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3223144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3297103"},{"key":"ref5","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. 3rd Mach. Learn. Syst. Conf.","author":"Li"},{"key":"ref6","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Karimireddy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3336957"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3405190"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3409159"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.2996612"},{"key":"ref12","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. NeurIPS Conf.","volume":"33","author":"Fallah"},{"key":"ref13","first-page":"21","article-title":"Debiasing model updates for improving personalized federated training","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Acar"},{"key":"ref14","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","volume-title":"Proc. NIPS","author":"Dinh"},{"key":"ref15","first-page":"6357","article-title":"Ditto: Fair and robust federated learning through personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/301"},{"key":"ref18","article-title":"Preservation of the global knowledge by not-true distillation in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3349400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/223"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015958"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01046-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.141"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3192506"},{"key":"ref26","first-page":"43097","article-title":"Structured federated learning through clustered additive modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ma"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889428"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3252599"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20785"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612217"},{"key":"ref31","article-title":"Federated meta-learning with fast convergence and efficient communication","author":"Chen","year":"2018","journal-title":"arXiv:1802.07876"},{"key":"ref32","article-title":"Improving federated learning personalization via model agnostic meta learning","author":"Jiang","year":"2019","journal-title":"arXiv:1909.12488"},{"key":"ref33","first-page":"14818","article-title":"FedL2P: Federated learning to personalize","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref34","article-title":"Federated learning of a mixture of global and local models","author":"Hanzely","year":"2020","journal-title":"arXiv:2002.05516"},{"key":"ref35","article-title":"Federated learning with personalization layers","author":"Ghuhan Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref36","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Collins"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01139"},{"key":"ref38","article-title":"FedBN: Federated learning on non-IID features via local batch normalization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3098467"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3323302"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3269062"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3498460"},{"key":"ref43","first-page":"23309","article-title":"PartialFed: Cross-domain personalized federated learning via partial initialization","volume-title":"Proc. 34th Annu. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00985"},{"key":"ref45","article-title":"Federated mutual learning","author":"Shen","year":"2020","journal-title":"arXiv:2006.16765"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3225185"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref48","article-title":"Personalized federated learning with first order model optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/311"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/357"},{"key":"ref51","first-page":"39801","article-title":"Personalized federated learning with inferred collaboration graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ye"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671702"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.003.0006"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01775"},{"key":"ref55","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref56","volume-title":"CIFAR-10 (Canadian Institute for Advanced Research)","author":"Krizhevsky","year":"2010"},{"key":"ref57","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434062"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref60","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":"ref61","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Harry Hsu","year":"2019","journal-title":"arXiv:1909.06335"},{"key":"ref62","article-title":"Ensemble distillation for robust model fusion in federated learning","volume-title":"Proc. NeurIPS","author":"Lin"},{"key":"ref63","first-page":"11058","article-title":"Multi-level branched regularization for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Kim"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00068"},{"key":"ref65","volume-title":"MNIST Handwritten Digit Database","author":"LeCun","year":"2010"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/34.291440"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref69","article-title":"On bridging generic and personalized federated learning for image classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref73","volume-title":"Microsoft DeepSpeed"},{"key":"ref74","volume-title":"What\u2019s the Backward-Forward Flop Ratio for Neural Networks?","author":"Hobbhahn","year":"2021"},{"key":"ref75","first-page":"15216","article-title":"Efficient neural network training via forward and backward propagation sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref76","article-title":"Differentially private federated learning: A client level perspective","author":"Geyer","year":"2017","journal-title":"arXiv:1712.07557"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3056991"},{"key":"ref78","first-page":"72181","article-title":"Dynamic personalized federated learning with adaptive differential privacy","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11091509.pdf?arnumber=11091509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:39:18Z","timestamp":1759945158000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11091509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":78,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3585927","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}