{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T22:25:41Z","timestamp":1774736741203,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["62125109"],"award-info":[{"award-number":["62125109"]}],"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":["T2122024"],"award-info":[{"award-number":["T2122024"]}],"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":["61931023"],"award-info":[{"award-number":["61931023"]}],"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":["61932022"],"award-info":[{"award-number":["61932022"]}],"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":["62120106007"],"award-info":[{"award-number":["62120106007"]}],"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":["62320106003"],"award-info":[{"award-number":["62320106003"]}],"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":["62371288"],"award-info":[{"award-number":["62371288"]}],"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":["62301299"],"award-info":[{"award-number":["62301299"]}],"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":["U24A20251"],"award-info":[{"award-number":["U24A20251"]}],"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":["62431017"],"award-info":[{"award-number":["62431017"]}],"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":["62401357"],"award-info":[{"award-number":["62401357"]}],"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":["62401366"],"award-info":[{"award-number":["62401366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Program of Shanghai Science and Technology Innovation Project","doi-asserted-by":"publisher","award":["24BC3200800"],"award-info":[{"award-number":["24BC3200800"]}],"id":[{"id":"10.13039\/501100017610","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":[[2025,6]]},"DOI":"10.1109\/tnnls.2024.3517658","type":"journal-article","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T19:33:52Z","timestamp":1735760032000},"page":"10407-10421","source":"Crossref","is-referenced-by-count":7,"title":["Federated Learning Based on Model Discrepancy and Variance Reduction"],"prefix":"10.1109","volume":"36","author":[{"given":"Hao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2888-594X","authenticated-orcid":false,"given":"Chenglin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-5778","authenticated-orcid":false,"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9694-9880","authenticated-orcid":false,"given":"Junni","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4552-0029","authenticated-orcid":false,"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. AISTATS","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref5","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. ICML","volume":"119","author":"Karimireddy"},{"key":"ref6","article-title":"Federated optimization in heterogeneous networks","author":"Li","year":"2018","journal-title":"arXiv:1812.06127"},{"key":"ref7","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. ICLR","author":"Acar"},{"key":"ref8","article-title":"Adaptive federated optimization","volume-title":"Proc. ICLR","author":"Reddi"},{"key":"ref9","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":"ref10","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","volume-title":"Proc. ICML","volume":"139","author":"Zhu"},{"key":"ref11","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. NeurIPS","volume":"33","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213777"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233093"},{"key":"ref16","article-title":"Fair resource allocation in federated learning","author":"Li","year":"2019","journal-title":"arXiv:1905.10497"},{"key":"ref17","article-title":"Robust federated learning in a heterogeneous environment","author":"Ghosh","year":"2019","journal-title":"arXiv:1906.06629"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3271859"},{"key":"ref19","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. AISTATS","volume":"108","author":"Bagdasaryan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3167482"},{"key":"ref21","first-page":"7057","article-title":"FedSplit: An algorithmic framework for fast federated optimization","volume-title":"Proc. NeurIPS","volume":"33","author":"Pathak"},{"key":"ref22","first-page":"6692","article-title":"From local SGD to local fixed-point methods for federated learning","volume-title":"Proc. ICML","volume":"119","author":"Malinovsky"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00987"},{"key":"ref24","first-page":"5972","article-title":"No fear of heterogeneity: Classifier calibration for federated learning with non-IID data","volume-title":"Proc. NeurIPS","volume":"34","author":"Luo"},{"key":"ref25","article-title":"Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms","author":"Wang","year":"2018","journal-title":"arXiv:1808.07576"},{"key":"ref26","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018","journal-title":"arXiv:1805.09767"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"issue":"1","key":"ref28","first-page":"237:1","article-title":"The error-feedback framework: Better rates for SGD with delayed gradients and compressed updates","volume":"21","author":"Stich","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. ICML","volume":"97","author":"Yu"},{"key":"ref30","article-title":"On the convergence of FedAvg on non-IID data","author":"Li","year":"2019","journal-title":"arXiv:1907.02189"},{"key":"ref31","first-page":"4519","article-title":"Tighter theory for local SGD on identical and heterogeneous data","volume-title":"Proc. AISTATS","author":"Khaled"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3224252"},{"key":"ref33","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","volume-title":"Proc. ICLR","author":"Yang"},{"key":"ref34","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"Karimireddy","year":"2020","journal-title":"arXiv:2008.03606"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref36","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2018","journal-title":"arXiv:1812.01097"},{"key":"ref37","article-title":"A field guide to federated optimization","author":"Wang","year":"2021","journal-title":"arXiv:2107.06917"},{"key":"ref38","article-title":"A stochastic gradient method with an exponential convergence rate for strongly-convex optimization with finite training sets","volume-title":"Proc. NeurIPS","volume":"25","author":"Le Roux"},{"key":"ref39","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. NeurIPS","volume":"26","author":"Johnson"},{"key":"ref40","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","volume-title":"Proc. NeurIPS","volume":"27","author":"Defazio"},{"key":"ref41","article-title":"Gradient scheduling with global momentum for non-IID data distributed asynchronous training","author":"Li","year":"2019","journal-title":"arXiv:1902.07848"},{"issue":"122","key":"ref42","first-page":"1","article-title":"Distributed stochastic variance reduced gradient methods by sampling extra data with replacement","volume":"18","author":"Lee","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0022"},{"key":"ref44","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","volume-title":"Proc. CoRR","volume":"abs\/1610.02527","author":"Kone\u010d n\u00fd"},{"key":"ref45","first-page":"1753","article-title":"On the ineffectiveness of variance reduced optimization for deep learning","volume-title":"Proc. NeurIPS","volume":"32","author":"Defazio"},{"key":"ref46","article-title":"Variance reduced local SGD with lower communication complexity","author":"Liang","year":"2019","journal-title":"arXiv:1912.12844"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref48","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"ref50","first-page":"10650","article-title":"Federated asymptotics: A model to compare federated learning algorithms","volume-title":"Proc. AISTATS","volume":"206","author":"Cheng"},{"key":"ref51","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016","journal-title":"arXiv:1609.04836"},{"key":"ref52","first-page":"15176","article-title":"Variance reduced ProxSkip: Algorithm, theory and application to federated learning","volume-title":"Proc. NeurIPS","volume":"35","author":"Malinovsky"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00386"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_41"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3304453"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10819958.pdf?arnumber=10819958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:58:09Z","timestamp":1749059889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10819958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":55,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3517658","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}