{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T10:53:54Z","timestamp":1781175234232,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2020YFB1807805"],"award-info":[{"award-number":["2020YFB1807805"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071067"],"award-info":[{"award-number":["62071067"]}],"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":["61872310"],"award-info":[{"award-number":["61872310"]}],"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":["61771068"],"award-info":[{"award-number":["61771068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong RGC Research Impact Fund","award":["R5060-19 and R5034-18"],"award-info":[{"award-number":["R5060-19 and R5034-18"]}]},{"name":"General Research Fund","award":["152221\/19E"],"award-info":[{"award-number":["152221\/19E"]}]},{"name":"General Research Fund","award":["15220320\/20E"],"award-info":[{"award-number":["15220320\/20E"]}]},{"name":"Collaborative Research Fund","award":["C5026-18G"],"award-info":[{"award-number":["C5026-18G"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/tcc.2021.3062398","type":"journal-article","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T20:59:07Z","timestamp":1614373147000},"page":"2637-2648","source":"Crossref","is-referenced-by-count":14,"title":["GSSP: Eliminating Stragglers Through Grouping Synchronous for Distributed Deep Learning in Heterogeneous Cluster"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3072-7422","authenticated-orcid":false,"given":"Haifeng","family":"Sun","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyi","family":"Gui","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computing, Hong Kong Polytechnic University, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0829-4624","authenticated-orcid":false,"given":"Qi","family":"Qi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2182-2228","authenticated-orcid":false,"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1486-0573","authenticated-orcid":false,"given":"Jianxin","family":"Liao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1707","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":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3343180.3343192"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00150"},{"key":"ref31","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2018","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00132"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040601"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00028"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2974461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1994.1085"},{"key":"ref40","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref11","article-title":"Revisiting distributed synchronous SGD","author":"chen","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref13","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":"ref14","first-page":"693","article-title":"HOGWILD!: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Proc 24th Int Conf Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref16","first-page":"2331","article-title":"Slow learners are fast","author":"zinkevich","year":"2009","journal-title":"Proc 22nd Int Conf Neural Inf Process Syst"},{"key":"ref17","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref18","first-page":"37","article-title":"Exploiting bounded staleness to speed up big data analytics","author":"cui","year":"2014","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref19","first-page":"165","article-title":"Optimal distributed online prediction using mini-batches","volume":"13","author":"dekel","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref28","article-title":"Automatic differentiation in Pytorch","author":"paszke","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01098"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref6","article-title":"Achieving human parity on automatic chinese to english news translation","author":"hassan","year":"2018"},{"key":"ref29","first-page":"561","article-title":"Ray: A distributed framework for emerging AI applications","author":"moritz","year":"2018","journal-title":"Proc 13th USENIX Symp Operating Syst Des Implementation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014"},{"key":"ref7","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"collobert","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref9","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"Proc 11th USENIX Conf Operating Syst Des Implementation"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"goodfellow","year":"2015","journal-title":"Nature"},{"key":"ref20","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":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-354"},{"key":"ref21","article-title":"Intermittent pulling with local compensation for communication-efficient federated learning","author":"wang","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00220"},{"key":"ref24","first-page":"186","article-title":"The data model concept in statistical mapping","volume":"7","author":"jenks","year":"1967"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852172"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref26","first-page":"2680","article-title":"Natasha 2: Faster non-convex optimization than SGD","author":"allen-zhu","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref25","first-page":"4120","article-title":"Asynchronous stochastic gradient descent with delay compensation","author":"zheng","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245519\/9970353\/09364710.pdf?arnumber=9364710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:13:24Z","timestamp":1672082004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9364710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":42,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2021.3062398","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}