{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:00:08Z","timestamp":1784995208207,"version":"3.55.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Hong Kong Research Grants Council","doi-asserted-by":"publisher","award":["ECS 21212419"],"award-info":[{"award-number":["ECS 21212419"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Technological Breakthrough Project of Science, Technology and Innovation Commission of Shenzhen Municipality","doi-asserted-by":"publisher","award":["JSGG20201102162000001"],"award-info":[{"award-number":["JSGG20201102162000001"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK Initiative, the Government of the Hong Kong Special Administrative Region (HKSAR), and the Laboratory for AI-Powered Financial Technologies"},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong Strategic Research Grant","doi-asserted-by":"publisher","award":["7005660"],"award-info":[{"award-number":["7005660"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong Strategic Research Grant","doi-asserted-by":"publisher","award":["7005561"],"award-info":[{"award-number":["7005561"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent AI Laboratory Rhino-Bird Gift Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["KQTD20170810150821146"],"award-info":[{"award-number":["KQTD20170810150821146"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA0715202"],"award-info":[{"award-number":["2021YFA0715202"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High-End Foreign Expert Talent Introduction Plan","award":["G2021032013L"],"award-info":[{"award-number":["G2021032013L"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/jsac.2022.3192050","type":"journal-article","created":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T19:31:35Z","timestamp":1658345495000},"page":"2678-2693","source":"Crossref","is-referenced-by-count":37,"title":["AC-SGD: Adaptively Compressed SGD for Communication-Efficient Distributed Learning"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0936-9467","authenticated-orcid":false,"given":"Guangfeng","family":"Yan","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6129-4792","authenticated-orcid":false,"given":"Tan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2827-4022","authenticated-orcid":false,"given":"Shao-Lun","family":"Huang","sequence":"additional","affiliation":[{"name":"Data Science and Information Technology Research Center, Tsinghua-Berkeley Shenzhen Institute, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3010-8090","authenticated-orcid":false,"given":"Tian","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The George Washington University, Washington, DC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2756-4984","authenticated-orcid":false,"given":"Linqi","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"FastText.Zip: Compressing text classification models","author":"joulin","year":"2016","journal-title":"arXiv 1612 03651"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","article-title":"On biased compression for distributed learning","author":"beznosikov","year":"2020","journal-title":"arXiv 2002 12410"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref31","first-page":"6155","article-title":"DoubleSqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","author":"tang","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref37","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref35","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update SGD","author":"wang","year":"2018","journal-title":"arXiv 1810 08313"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/110830629"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054164"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3234944.3234978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178365"},{"key":"ref13","first-page":"55","article-title":"Adaptive gradient communication via critical learning regime identification","volume":"3","author":"agarwal","year":"2021","journal-title":"Proc 4th Conf Mach Learn Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488815"},{"key":"ref15","first-page":"3","article-title":"Incremental gradient, subgradient, and proximal methods for convex optimization: A survey","volume":"2010","author":"bertsekas","year":"2011","journal-title":"Optimization for Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref17","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"1299","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume":"31","author":"wangni","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"3329","article-title":"Distributed mean estimation with limited communication","author":"suresh","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","first-page":"12593","article-title":"CSER: Communication-efficient SGD with error reset","volume":"33","author":"xie","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref27","first-page":"13551","article-title":"ScaleCom: Scalable sparsified gradient compression for communication-efficient distributed training","volume":"33","author":"chen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139042918"},{"key":"ref6","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc Mach Learn Res (PMLR)"},{"key":"ref29","article-title":"Federated optimization: Distributed optimization beyond the datacenter","author":"kone?n\u00fd","year":"2015","journal-title":"arXiv 1511 03575"},{"key":"ref5","first-page":"4447","article-title":"Sparsified SGD with memory","author":"stich","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2985917"},{"key":"ref7","first-page":"1","article-title":"Local SGD converges fast and communicates little","author":"stich","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","first-page":"1","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MASS52906.2021.00025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9518221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"ref21","first-page":"1","article-title":"PowerSGD: Practical low-rank gradient compression for distributed optimization","volume":"32","author":"vogels","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"3174","article-title":"Adaptive gradient quantization for data-parallel SGD","volume":"33","author":"faghri","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3154387"},{"key":"ref26","article-title":"Error compensated quantized SGD and its applications to large-scale distributed optimization","author":"wu","year":"2018","journal-title":"arXiv 1806 08054"},{"key":"ref25","first-page":"1","article-title":"IntSGD: Adaptive floatless compression of stochastic gradients","author":"mishchenko","year":"2021","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9863724\/09834260.pdf?arnumber=9834260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:03:45Z","timestamp":1662408225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9834260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":39,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2022.3192050","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}