{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:28:50Z","timestamp":1781022530581,"version":"3.54.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP200103718"],"award-info":[{"award-number":["DP200103718"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP200103494"],"award-info":[{"award-number":["DP200103494"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpds.2022.3206480","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T19:30:47Z","timestamp":1663183847000},"page":"4863-4873","source":"Crossref","is-referenced-by-count":41,"title":["Federated Learning With Nesterov Accelerated Gradient"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7530-3562","authenticated-orcid":false,"given":"Zhengjie","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, The 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, The 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\/0000-0001-7323-9213","authenticated-orcid":false,"given":"Nguyen H.","family":"Tran","sequence":"additional","affiliation":[{"name":"School of Computer Science, The 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 Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600746456"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2005.858622"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_8551"},{"key":"ref4","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref6","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00006","article-title":"Why momentum really works","author":"Goh","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref9","first-page":"1195","article-title":"Fast and faster convergence of SGD for over-parameterized models and an accelerated perceptron","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Vaswani"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/410"},{"key":"ref11","first-page":"410","article-title":"On the convergence of nesterovs accelerated gradient method in stochastic settings","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Assran"},{"key":"ref12","article-title":"Faster on-device training using new federated momentum algorithm","author":"Huo","year":"2020"},{"key":"ref13","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref14","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"Karimireddy","year":"2020"},{"key":"ref15","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","journal-title":"Doklady ANSSSR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref17","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li"},{"key":"ref18","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref19","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.","author":"Reisizadeh"},{"key":"ref20","first-page":"5895","article-title":"Acceleration for compressed gradient descent in distributed and federated optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2987958"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3088056"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LCN48667.2020.9314811"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000430"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2988579"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1201\/9781003107026-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3035770"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975189"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"ref35","article-title":"CS231n convolutional neural networks for visual recognition","author":"Li","year":"2020"},{"key":"ref36","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref37","article-title":"The MNIST database of handwritten digits","author":"LeCun","year":"1998"},{"key":"ref38","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref39","article-title":"A generic framework for privacy preserving deep learning","author":"Ryffel","year":"2018"},{"key":"ref40","article-title":"Federated learning on MNIST using a CNN model","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2020.110208"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3486609.3487210"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9790018\/09891808.pdf?arnumber=9891808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T17:33:41Z","timestamp":1717004021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891808\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3206480","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":[[2022,12,1]]}}}