{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:51:15Z","timestamp":1757541075639,"version":"3.33.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025208","62376278"],"award-info":[{"award-number":["62025208","62376278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2022JJ10065"],"award-info":[{"award-number":["2022JJ10065"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}]},{"name":"Continuous Support of PDL","award":["WDZC20235250101"],"award-info":[{"award-number":["WDZC20235250101"]}]},{"name":"Xiangjiang Laboratory Fund","award":["22XJ01012"],"award-info":[{"award-number":["22XJ01012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tbdata.2024.3407510","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:56:48Z","timestamp":1717091808000},"page":"234-246","source":"Crossref","is-referenced-by-count":1,"title":["Communication-Efficient Distributed Learning via Sparse and Adaptive Stochastic Gradient"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0622-1202","authenticated-orcid":false,"given":"Xiaoge","family":"Deng","sequence":"first","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9743-2034","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5024-1900","authenticated-orcid":false,"given":"Tao","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}]},{"given":"Xicheng","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref3","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref7","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref8","first-page":"2595","article-title":"Parallelized stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zinkevich"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1429274"},{"article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref12","first-page":"5977","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"article-title":"Variance reduction with sparse gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Elibol","key":"ref13"},{"key":"ref14","first-page":"4447","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Stich"},{"key":"ref15","first-page":"5050","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref16","first-page":"613","article-title":"CADA: Communication-adaptive distributed adam","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3099977"},{"key":"ref18","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref19","first-page":"14668","article-title":"Qsparse-local-SGD: Distributed SGD with quantization, sparsification and local computations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Basu"},{"key":"ref20","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref21","first-page":"3365","article-title":"Communication-efficient distributed learning via lazily aggregated quantized gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010045"},{"article-title":"A better alternative to error feedback for communication-efficient distributed learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Horv\u00e1th","key":"ref23"},{"article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Stich","key":"ref24"},{"key":"ref25","first-page":"14236","article-title":"PowerSGD: Practical low-rank gradient compression for distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vogels"},{"key":"ref26","first-page":"9872","article-title":"ATOMO: Communication-efficient learning via atomic sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3073112"},{"article-title":"Communication-efficient distributed deep learning: A comprehensive survey","year":"2020","author":"Tang","key":"ref28"},{"key":"ref29","first-page":"559","article-title":"signSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Bernstein"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3209190"},{"key":"ref32","first-page":"3174","article-title":"Adaptive gradient quantization for data-parallel SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Faghri"},{"key":"ref33","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wangni"},{"key":"ref34","first-page":"3252","article-title":"Error feedback fixes signSGD and other gradient compression schemes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref35","first-page":"12593","article-title":"CSER: Communication-efficient SGD with error reset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref36","first-page":"1000","article-title":"Communication-efficient distributed optimization using an approximate newton-type method","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shamir"},{"key":"ref37","first-page":"4203","article-title":"Statistically preconditioned accelerated gradient method for distributed optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hendrikx"},{"article-title":"Don\u2019t use large mini-batches, use local SGD","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083655"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00099"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref43","first-page":"32","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","first-page":"1225","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hardt"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17173"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25894"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/10843063\/10542408.pdf?arnumber=10542408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:03:07Z","timestamp":1737399787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":47,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2024.3407510","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"type":"electronic","value":"2332-7790"},{"type":"electronic","value":"2372-2096"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}