{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T21:57:21Z","timestamp":1776203841635,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1003305"],"award-info":[{"award-number":["2018YFB1003305"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832020"],"award-info":[{"award-number":["61832020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61821003"],"award-info":[{"award-number":["61821003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772216"],"award-info":[{"award-number":["61772216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Defense Preliminary Research Project","award":["31511010202"],"award-info":[{"award-number":["31511010202"]}]},{"name":"Hubei Province Technical Innovation Special Project","award":["2017AAA129"],"award-info":[{"award-number":["2017AAA129"]}]},{"name":"Wuhan Application Basic Research Project","award":["2017010201010103"],"award-info":[{"award-number":["2017010201010103"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3071579","type":"journal-article","created":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T20:03:03Z","timestamp":1617825783000},"page":"57075-57088","source":"Crossref","is-referenced-by-count":1,"title":["Bridging the Gap Between Memory and Communication Efficiency on Distributed Deep Learning Systems"],"prefix":"10.1109","volume":"9","author":[{"given":"Shaofeng","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8908-0777","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref31","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Proc 31th Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31th Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"ref11","first-page":"1","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"Proc Workshop Mach Learn Syst 28th Annu Conf Neural Inf Process Syst (LearningSys)"},{"key":"ref12","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc 26th Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref13","first-page":"1","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref14","first-page":"25","article-title":"An Effective, low-cost measure of semantic relatedness obtained from Wikipedia links","author":"milne","year":"2008","journal-title":"Proc AAAI Workshop Wikipedia Artif Intell Evolving Synergy (AAAI)"},{"key":"ref15","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol (NAACL)"},{"key":"ref16","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref17","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref18","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3th Int Conf Learn Represent (ICLR)"},{"key":"ref19","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref28","first-page":"205","article-title":"The rise of GPU computing","author":"sanders","year":"2010","journal-title":"CUDA by Example An Introduction to General-Purpose GPU Programming Portable Documents"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3243904"},{"key":"ref27","first-page":"5325","article-title":"Error compensated quantized SGD and its applications to large-scale distributed optimization","volume":"80","author":"wu","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref3","first-page":"41301","article-title":"Key techniques for 5G wireless communications: Network architecture, physical layer, and MAC layer perspectives","volume":"58","author":"zheng","year":"2015","journal-title":"Sci China Inf Sci"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref29","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Conf Oper Syst Design Implement (OSDI)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178528"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"ref1","year":"2020","journal-title":"NVIDIA A100"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","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 16th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref24","first-page":"1509","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc 31st Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref23","first-page":"5151","article-title":"Scalable methods for 8-bit training of neural networks","author":"banner","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64243-3_6"},{"key":"ref25","first-page":"1","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09398682.pdf?arnumber=9398682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:30Z","timestamp":1639770930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9398682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3071579","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}