{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T00:01:14Z","timestamp":1792886474320,"version":"4.5.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFB1002201"],"award-info":[{"award-number":["2017YFB1002201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Fund for Distinguished Young Scholar","award":["61625204"],"award-info":[{"award-number":["61625204"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836006"],"award-info":[{"award-number":["61836006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,1,1]]},"DOI":"10.1109\/tpds.2021.3090331","type":"journal-article","created":{"date-parts":[[2021,6,17]],"date-time":"2021-06-17T15:25:42Z","timestamp":1623943542000},"page":"192-205","source":"Crossref","is-referenced-by-count":219,"title":["Communication-Efficient Federated Learning With Compensated Overlap-FedAvg"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8074-6416","authenticated-orcid":false,"given":"Yuhao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3956-3348","authenticated-orcid":false,"given":"Qing","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6551-3884","authenticated-orcid":false,"given":"Jiancheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975189"},{"key":"ref38","author":"friedman","year":"2001","journal-title":"The Elements of Statistical Learning"},{"key":"ref33","article-title":"Error feedback fixes SIGNSGD and other gradient compression schemes","author":"karimireddy","year":"2019"},{"key":"ref32","article-title":"Federated learning's blessing: FEDAVG has linear speedup","author":"qu","year":"2020"},{"key":"ref31","article-title":"On the convergence of fedavg on non-IID data","author":"li","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref37","first-page":"4120","article-title":"Asynchronous stochastic gradient descent with delay compensation","author":"zheng","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810091"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1996.0038"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2005.75"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref27","article-title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption","author":"hardy","year":"2017"},{"key":"ref29","article-title":"Federated learning with non-IID data","author":"zhao","year":"2018"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","article-title":"Federated learning with NESTEROV accelerated gradient momentum method","author":"yang","year":"2020"},{"key":"ref22","author":"tieleman","year":"2012","journal-title":"Lecture 6 5—RmsProp Divide the gradient by a running average of its recent magnitude"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3046774"},{"key":"ref23","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref25","first-page":"1","article-title":"PSO-PS: Parameter synchronization with particle swarm optimization for distributed training of deep neural networks","author":"ye","year":"2020","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref50","first-page":"14774","article-title":"Deep leakage from gradients","author":"zhu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","article-title":"IDLG: Improved deep leakage from gradients","author":"zhao","year":"2020"},{"key":"ref52","article-title":"Threats to federated learning: A survey","author":"lyu","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref40","article-title":"Faster on-device training using new federated momentum algorithm","author":"huo","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852172"},{"key":"ref13","article-title":"Federated learning: Strategies for improving communication efficiency","author":"kone?n?","year":"2016"},{"key":"ref14","first-page":"1058","article-title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNS","author":"seide","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc"},{"key":"ref15","article-title":"SIGNSGD: Compressed optimisation for non-convex problems","author":"bernstein","year":"2018"},{"key":"ref16","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref17","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2017"},{"key":"ref18","first-page":"1299","article-title":"Gradient sparsification for communication-efficient distributed optimization","author":"wangni","year":"2018","journal-title":"Proc 32th Int Conf Neural Inf Process Syst"},{"key":"ref19","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence","volume":"269","author":"nesterov","year":"1983","journal-title":"Doklady AN SSSR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref7","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"Advances and Open Problems in Federated Learning","author":"kairouz","year":"2019"},{"key":"ref46","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"ref48","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref47","article-title":"Pointer sentinel mixture models","author":"merity","year":"2016"},{"key":"ref42","article-title":"Gradient descent converges to minimizers","author":"lee","year":"2016"},{"key":"ref41","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref44","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017"},{"key":"ref43","article-title":"MNIST handwritten digit database","author":"lecun","year":"2010"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9465725\/09459540.pdf?arnumber=9459540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T06:55:22Z","timestamp":1643266522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9459540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,1]]},"references-count":52,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3090331","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":[[2022,1,1]]}}}