{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:52:34Z","timestamp":1791910354335,"version":"4.3.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Australian Research Council Discovery Project","award":["DP200103718"],"award-info":[{"award-number":["DP200103718"]}]},{"name":"Australian Research Council Discovery Project","award":["DP200103494"],"award-info":[{"award-number":["DP200103494"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpds.2023.3294688","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T13:25:25Z","timestamp":1689168325000},"page":"2629-2641","source":"Crossref","is-referenced-by-count":23,"title":["Hierarchical Federated Learning With Momentum Acceleration in Multi-Tier Networks"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7530-3562","authenticated-orcid":false,"given":"Zhengjie","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4340-3945","authenticated-orcid":false,"given":"Sen","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1874-1766","authenticated-orcid":false,"given":"Wei","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1130-0888","authenticated-orcid":false,"given":"Dong","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3090-1059","authenticated-orcid":false,"given":"Albert Y.","family":"Zomaya","sequence":"additional","affiliation":[{"name":"School of Information Technologies, University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975189"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00006","article-title":"Why momentum really works","author":"goh","year":"2017","journal-title":"Distillation"},{"key":"ref12","first-page":"410","article-title":"On the convergence of Nesterov's accelerated gradient method in stochastic settings","author":"assran","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref15","first-page":"1","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","author":"yang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref14","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","author":"yu","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence o(1\/k2)","volume":"269","author":"nesterov","year":"1983"},{"key":"ref31","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref11","first-page":"1195","article-title":"Fast and faster convergence of SGD for over-parameterized models and an accelerated perceptron","author":"vaswani","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref33","first-page":"437","article-title":"A public domain dataset for human activity recognition using smartphones","author":"anguita","year":"2013","journal-title":"Proc 21st Int Eur Symp Artif Neural Netw Comput Intell Mach Learn"},{"key":"ref10","first-page":"1","article-title":"Accelerating SGD with momentum for over-parameterized learning","author":"liu","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2005.858622"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600746456"},{"key":"ref17","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016"},{"key":"ref39","first-page":"1","article-title":"Multi-level local SGD: Distributed SGD for heterogeneous hierarchical networks","author":"castiglia","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16920"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20832"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488756"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3187678"},{"key":"ref23","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"karimireddy","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9517850"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20853"},{"key":"ref20","article-title":"Faster on-device training using new federated momentum algorithm","author":"huo","year":"2020"},{"key":"ref42","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3206480"},{"key":"ref44","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","author":"reisizadeh","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref21","first-page":"1","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","author":"wang","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404457"},{"key":"ref28","author":"gross","year":"2021","journal-title":"Pytorch-VGG"},{"key":"ref27","author":"jay","year":"2023","journal-title":"FL on MNIST Using a CNN"},{"key":"ref29","author":"moon","year":"2020","journal-title":"Pytorch-Tiny-ImageNet"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3190512"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207469"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/410"},{"key":"ref4","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref3","volume":"1","author":"yu","year":"2016","journal-title":"Automatic Speech Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054634"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10201356\/10180030.pdf?arnumber=10180030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T14:06:25Z","timestamp":1692626785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10180030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":45,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3294688","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}