{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:27:02Z","timestamp":1772908022215,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["2022YFA1003900"],"award-info":[{"award-number":["2022YFA1003900"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20190813171003723"],"award-info":[{"award-number":["JCYJ20190813171003723"]}]},{"name":"Shenzhen Science and Technology Program","award":["RCJC20210609104448114"],"award-info":[{"award-number":["RCJC20210609104448114"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC, China","doi-asserted-by":"publisher","award":["62071409"],"award-info":[{"award-number":["62071409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC, China","doi-asserted-by":"publisher","award":["62231019"],"award-info":[{"award-number":["62231019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021B1515120008"],"award-info":[{"award-number":["2021B1515120008"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Big Data Computing"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tnnls.2023.3323302","type":"journal-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T18:21:15Z","timestamp":1698862875000},"page":"1692-1706","source":"Crossref","is-referenced-by-count":25,"title":["Why Batch Normalization Damage Federated Learning on Non-IID Data?"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5423-0990","authenticated-orcid":false,"given":"Yanmeng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0507-9080","authenticated-orcid":false,"given":"Qingjiang","family":"Shi","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1349-2764","authenticated-orcid":false,"given":"Tsung-Hui","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095399"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118436"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126081"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3166101"},{"key":"ref5","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","volume":"2","author":"Li"},{"key":"ref6","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. ICML","author":"Karimireddy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3213187"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3145850"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5465\/amproc.2023.365bp"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041388"},{"key":"ref12","article-title":"FedAT: A communication-efficient federated learning method with asynchronous tiers under non-IID data","author":"Chai","year":"2020","journal-title":"arXiv:2010.05958"},{"key":"ref13","first-page":"1","article-title":"How does batch normalization help optimization?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Santurkar"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","first-page":"1","article-title":"FedBN: Federated learning on non-IID features via local batch normalization","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref17","first-page":"4387","article-title":"The non-IID data quagmire of decentralized machine learning","volume-title":"Proc. ICML","author":"Hsieh"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3565010.3569062"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60548-3_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3098467"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI52525.2021.00138"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86486-6_44"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119159"},{"key":"ref24","first-page":"1","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","volume-title":"Proc. ICLR","author":"Diao"},{"key":"ref25","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref27","first-page":"1","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref28","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Reisizadeh"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref30","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. NeurIPS","volume":"33","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00089"},{"key":"ref32","article-title":"Batch group normalization","author":"Zhou","year":"2020","journal-title":"arXiv:2012.02782"},{"key":"ref33","first-page":"5336","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. NeurIPS","author":"Lian"},{"key":"ref34","article-title":"Why batch normalization damage federated learning on non-IID data?","author":"Wang","year":"2023","journal-title":"arXiv:2301.02982"},{"key":"ref35","first-page":"7232","article-title":"Evaluating gradient inversion attacks and defenses in federated learning","volume-title":"Proc. NeurIPS","volume":"34","author":"Huang"},{"key":"ref36","article-title":"Making batch normalization great in federated deep learning","author":"Zhong","year":"2023","journal-title":"arXiv:2303.06530"},{"key":"ref37","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref39","first-page":"2066","article-title":"Geodesic flow kernel for unsupervised domain adaptation","volume-title":"Proc. CVPR","author":"Gong"},{"key":"ref40","volume-title":"Proper ResNet Implementation for CIFAR10\/CIFAR100 in PyTorch","author":"Idelbayev","year":"2021"},{"key":"ref41","volume-title":"Practice on CIFAR-100 Using PyTorch","author":"Weiaicunzai","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00982"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref44","first-page":"22619","article-title":"Passport-aware normalization for deep model protection","volume-title":"Proc. NeurIPS","volume":"33","author":"Zhang"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10832116\/10304290.pdf?arnumber=10304290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T20:15:03Z","timestamp":1743797703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10304290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3323302","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}