{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T17:35:41Z","timestamp":1784828141302,"version":"3.55.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"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":["62072344"],"award-info":[{"award-number":["62072344"]}],"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":["U20A20177"],"award-info":[{"award-number":["U20A20177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hubei Science Foundation","award":["2020CFB195"],"award-info":[{"award-number":["2020CFB195"]}]},{"name":"Compact Exponential Algorithm Project of Huawei","award":["YBN2020035131"],"award-info":[{"award-number":["YBN2020035131"]}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2047719"],"award-info":[{"award-number":["CNS-2047719"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong RGC","award":["17204619"],"award-info":[{"award-number":["17204619"]}]},{"name":"Hong Kong RGC","award":["17208920"],"award-info":[{"award-number":["17208920"]}]},{"name":"Hong Kong RGC","award":["17207621"],"award-info":[{"award-number":["17207621"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2023,4,1]]},"DOI":"10.1109\/tcc.2022.3143153","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T20:36:21Z","timestamp":1642192581000},"page":"1514-1529","source":"Crossref","is-referenced-by-count":22,"title":["Online Scheduling Algorithm for Heterogeneous Distributed Machine Learning Jobs"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9681-6482","authenticated-orcid":false,"given":"Ruiting","family":"Zhou","sequence":"first","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6425-9669","authenticated-orcid":false,"given":"Jinlong","family":"Pang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Hubei, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-4398","authenticated-orcid":false,"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3964-3172","authenticated-orcid":false,"given":"Lei","family":"Jiao","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0626-7510","authenticated-orcid":false,"given":"Yi","family":"Zhong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongpeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Hubei, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2017.34"},{"key":"ref35","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX 12th Conf Oper Syst Des Implementation"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2905560"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.22.3.513"},{"key":"ref36","year":"0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS49365.2020.9212862"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2609844"},{"key":"ref11","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486340"},{"key":"ref10","first-page":"1676","article-title":"Spotlight: Optimizing device placement for training deep neural networks","author":"gao","year":"2018","journal-title":"Proc ACM 35th Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2018.11.015"},{"key":"ref2","first-page":"571","article-title":"Project Adam: Building an efficient and scalable deep learning training system","author":"chilimbi","year":"2014","journal-title":"Proc USENIX Conf Oper Syst Des Implementation"},{"key":"ref1","article-title":"MXNet: A Flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2016","journal-title":"Proc NIPS Workshop Mach Learn Syst"},{"key":"ref17","first-page":"533","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","author":"xiao","year":"2020","journal-title":"Proc USENIX Conf Oper Syst Des Implementation"},{"key":"ref39","article-title":"NCCL 2.0","author":"jeaugey","year":"2017"},{"key":"ref16","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","author":"narayanan","year":"2020","journal-title":"Proc USENIX Conf Oper Syst Des Implementation"},{"key":"ref38","year":"0"},{"key":"ref19","first-page":"289","article-title":"THEMIS: Fair and efficient GPU cluster scheduling","author":"mahajan","year":"2020","journal-title":"Proc USENIX 17th Conf Netw Syst Des Implementation"},{"key":"ref18","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"jeon","year":"2019","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2591971.2591980"},{"key":"ref23","article-title":"DL2: A deep learning-driven scheduler for deep learning clusters","author":"peng","year":"2019"},{"key":"ref45","article-title":"Spark: Cluster computing with working sets","author":"zaharia","year":"2010","journal-title":"Proc 2nd USENIX Conf Hot Top cloud Comput"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2745844.2745855"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3078505.3078529"},{"key":"ref20","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc Usenix Conf Netw Syst Des Implementation"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref41","article-title":"Google Cloud TPU","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783270"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2742343"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682911"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1008861.1008867"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2018.8624119"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2707142"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2764468.2764535"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref7","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","author":"hindman","year":"2011","journal-title":"Proc Usenix Conf Netw Syst Des Implementation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref6","first-page":"323","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","author":"ghodsi","year":"2011","journal-title":"Proc Usenix Conf Netw Syst Des Implementation"},{"key":"ref5","year":"0","journal-title":"Baidu allreduce"},{"key":"ref40","year":"0"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6245519\/10144930\/9682563-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245519\/10144930\/09682563.pdf?arnumber=9682563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:50:02Z","timestamp":1687805402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9682563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":45,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2022.3143153","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,1]]}}}