{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T06:07:37Z","timestamp":1773814057919,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tc.2026.3654074","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:39:56Z","timestamp":1768423196000},"page":"1433-1445","source":"Crossref","is-referenced-by-count":0,"title":["Communication-Efficient Federated Learning by Exploiting Spatio-Temporal Correlations of Gradients"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0361-0762","authenticated-orcid":false,"given":"Shenlong","family":"Zheng","sequence":"first","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8893-3187","authenticated-orcid":false,"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1522-8943","authenticated-orcid":false,"given":"Yuhui","family":"Deng","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-7314","authenticated-orcid":false,"given":"Geyong","family":"Min","sequence":"additional","affiliation":[{"name":"College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7961-3261","authenticated-orcid":false,"given":"Lin","family":"Cui","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Federated optimization: Distributed optimization beyond the datacenter","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop Optim. Mach. Learn","author":"Kone\u010dn\u00fd","year":"2015"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan","year":"2017"},{"key":"ref3","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Machine Learning Systems","volume":"1","author":"Bonawitz","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s22020450"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref6","first-page":"5","article-title":"Federated learning: Strategies for improving communication efficiency","volume-title":"Proc. 29th Conf. Neural Inf. Process. Syst. (NIPS)","author":"McMahan","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10563-8"},{"key":"ref8","article-title":"Inrank: Incremental Low-Rank Learning","author":"Zhao","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2023.3315088"},{"key":"ref10","article-title":"ATOMO: Communication-efficient learning via atomic sparsification","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"31","author":"Wang","year":"2018"},{"key":"ref11","first-page":"5129","article-title":"Gradiveq: Vector quantization for bandwidth-efficient gradient aggregation in distributed cnn training","volume":"31","author":"Yu","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084806"},{"key":"ref14","article-title":"Evolving and understanding sparse deep neural networks using cosine similarity","author":"Pieterse","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054676"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2586"},{"key":"ref17","first-page":"513","article-title":"Which layer is learning faster? A systematic exploration of layer-wise convergence rate for deep neural networks","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Chen","year":"2023"},{"key":"ref18","first-page":"14280","article-title":"Leveraging spatial and temporal correlations in sparsified mean estimation","volume":"34","author":"Jhunjhunwala","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229032"},{"key":"ref20","first-page":"560","article-title":"SignSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Bernstein","year":"2018"},{"key":"ref21","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","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3073112"},{"key":"ref23","article-title":"Sparsified SGD with memory","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Stich","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tc.2025.3533095"},{"key":"ref27","first-page":"61121","article-title":"Galore: Memory-efficient LLM training by gradient low-rank projection","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Zhao","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3165268"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621176"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645702"},{"key":"ref31","first-page":"234","article-title":"Fedpara: Low-rank Hadamard product for communication-efficient federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hyeon-Woo","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3475578"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/03081087.2016.1267104"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/090771806"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref36","article-title":"Gradient descent happens in a tiny subspace","author":"Gur-Ari","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref39","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3477972"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11435995\/11352945.pdf?arnumber=11352945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:13:02Z","timestamp":1773810782000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11352945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":42,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tc.2026.3654074","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}