{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:19:45Z","timestamp":1780053585927,"version":"3.54.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}]},{"name":"NSFC\/RGC Collaborative Research Scheme","award":["CRS_HKUST603\/22"],"award-info":[{"award-number":["CRS_HKUST603\/22"]}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2023A03J0011"],"award-info":[{"award-number":["2023A03J0011"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Integrated Communications, Sensing and Computation for Ubiquitous Internet of Things"},{"name":"National Foreign Expert Project","award":["G2022030026"],"award-info":[{"award-number":["G2022030026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tmc.2024.3406554","type":"journal-article","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T18:21:45Z","timestamp":1716920505000},"page":"12131-12145","source":"Crossref","is-referenced-by-count":20,"title":["Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1167-9392","authenticated-orcid":false,"given":"Tailin","family":"Zhou","sequence":"first","affiliation":[{"name":"IPO, Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9503-2464","authenticated-orcid":false,"given":"Zehong","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5222-1898","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0135-7098","authenticated-orcid":false,"given":"Danny H.K.","family":"Tsang","sequence":"additional","affiliation":[{"name":"Internet of Things Thrust, The Hong Kong University of Science and Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref2","doi-asserted-by":"crossref","article-title":"Federated learning with non-IID data","author":"Zhao","DOI":"10.1016\/j.neucom.2021.07.098"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3045266"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3297790"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3263148"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3085979"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3311188"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3283295"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref11","article-title":"A field guide to federated optimization","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295285"},{"key":"ref14","article-title":"Parallel SGD: When does averaging help?","author":"Zhang"},{"key":"ref15","first-page":"5381","article-title":"A unified theory of decentralized SGD with changing topology and local updates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koloskova"},{"key":"ref16","article-title":"On the convergence of fedavg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref18","article-title":"On the unreasonable effectiveness of federated averaging with heterogeneous data","author":"Wang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","first-page":"223:1","article-title":"Parallelizing stochastic gradient descent for least squares regression: Mini-batching, averaging, and model misspecification","volume":"18","author":"Jain","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. Int. Conf. Uncert. Artif. Intell.","author":"Izmailov"},{"key":"ref21","article-title":"Stochastic weight averaging in parallel: Large-batch training that generalizes well","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gupta"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_38"},{"key":"ref23","first-page":"2119","article-title":"Stochastic multiple choice learning for training diverse deep ensembles","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref24","first-page":"10821","article-title":"Diverse weight averaging for out-of-distribution generalization","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Rame"},{"key":"ref25","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Int. Conf. Mach. Learn. Syst.","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3325366"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3376697"},{"key":"ref28","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref29","article-title":"Adaptive federated optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi"},{"key":"ref30","article-title":"Gradient masked averaging for federated learning","author":"Tenison","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref31","first-page":"17","article-title":"Federated learning with GAN-based data synthesis for non-IID clients","volume-title":"Proc. Int. Workshop Trustworthy Federated Learn.","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT50566.2022.9834445"},{"key":"ref33","first-page":"10533","article-title":"DReS-FL: Dropout-resilient secure federated learning for non-IID clients via secret data sharing","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Shao"},{"key":"ref34","first-page":"7587","article-title":"SparseFed: Mitigating model poisoning attacks in federated learning with sparsification","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Panda"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3046971"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2023.3309773"},{"key":"ref37","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3004124"},{"key":"ref39","article-title":"Qualitatively characterizing neural network optimization problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref40","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref41","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Foret"},{"key":"ref42","first-page":"22405","article-title":"Swad: Domain generalization by seeking flat minima","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Cha"},{"key":"ref43","first-page":"8803","article-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Garipov"},{"key":"ref44","first-page":"1309","article-title":"Essentially no barriers in neural network energy landscape","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Draxler"},{"key":"ref45","article-title":"Understanding federated learning through loss landscape visualizations: A pilot study","volume-title":"Proc. Workshop Federated Learning: Recent Adv. New Challenges","author":"Li"},{"key":"ref46","first-page":"19767","article-title":"Revisiting weighted aggregation in federated learning with neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref47","first-page":"1600","article-title":"Mode connectivity and data heterogeneity of federated learning","volume-title":"Proc. Asilomar Conf. Signals Syst. Comput.","author":"Zhou"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.1"},{"key":"ref49","first-page":"275","article-title":"Bias plus variance decomposition for zero-one loss functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kohavi"},{"key":"ref50","first-page":"231","article-title":"A unified bias-variance decomposition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Domingos"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/11494683_30"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref53","article-title":"A survey of what to share in federated learning: Perspectives on model utility, privacy leakage, and communication efficiency","author":"Shao"},{"key":"ref54","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00779"},{"key":"ref56","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref58","article-title":"Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref59","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yurochkin"},{"key":"ref60","article-title":"Fedbn: Federated learning on non-IID features via local batch normalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143917"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref66","first-page":"4387","article-title":"The non-IID data quagmire of decentralized machine learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hsieh"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2023.3338021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2011.941097"},{"key":"ref70","article-title":"Server averaging for federated learning","author":"Pu"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/10746253\/10540229.pdf?arnumber=10540229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:22:51Z","timestamp":1732666971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":70,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2024.3406554","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}