{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:55:02Z","timestamp":1777564502351,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Alibaba Innovative Research"},{"name":"Hong Kong RGC","award":["HKU 17204619"],"award-info":[{"award-number":["HKU 17204619"]}]},{"name":"Hong Kong RGC","award":["17208920"],"award-info":[{"award-number":["17208920"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021,8,1]]},"DOI":"10.1109\/tpds.2021.3052895","type":"journal-article","created":{"date-parts":[[2021,1,20]],"date-time":"2021-01-20T20:30:15Z","timestamp":1611174615000},"page":"1947-1960","source":"Crossref","is-referenced-by-count":82,"title":["DL2: A Deep Learning-Driven Scheduler for Deep Learning Clusters"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-4358","authenticated-orcid":false,"given":"Yanghua","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6921-2154","authenticated-orcid":false,"given":"Yixin","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangrui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-4398","authenticated-orcid":false,"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3064176.3064182"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref33","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref32","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Int Conf Mach Learn"},{"key":"ref31","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017"},{"key":"ref30","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019"},{"key":"ref37","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102422"},{"key":"ref34","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"2000","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref60","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc 16th USENIX Conf Netw Syst Des Implementation"},{"key":"ref62","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume":"1","author":"jayarajan","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref63","article-title":"Fuzzy logic","year":"2020"},{"key":"ref28","article-title":"Deep reinforcement learning for multi-resource multi-cluster job scheduling","author":"chen","year":"2017","journal-title":"Proc IEEE Int Conf Netw Protocols"},{"key":"ref64","article-title":"Genetic algorithm","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref65","article-title":"A dynamic resource scheduling method based on fuzzy control theory in cloud environment","volume":"2015","author":"zhijia","year":"2015","journal-title":"J Control Sci Eng"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2005.27"},{"key":"ref29","article-title":"Accurate, large minibatch SGD: Training imageNet in 1 hour","author":"goyal","year":"2017"},{"key":"ref67","article-title":"Kubernetes","year":"2019"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","author":"hindman","year":"2011","journal-title":"Proc 8th USENIX Conf Netw Syst Des Implementation"},{"key":"ref24","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref23","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987586"},{"key":"ref51","article-title":"CNTK","year":"2019"},{"key":"ref59","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 13th USENIX Conf Operating Syst Des Implementation"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2017.7947053"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref55","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","author":"mirhoseini","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref54","first-page":"2755","article-title":"Efficient and robust automated machine learning","author":"feurer","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8257923"},{"key":"ref52","article-title":"A hierarchical model for device placement","author":"mirhoseini","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","first-page":"323","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","author":"ghodsi","year":"2011","journal-title":"Proc 8th USENIX Conf Netw Syst Des Implementation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref40","first-page":"631","article-title":"Litz: Elastic framework for high-performance distributed machine learning","author":"qiao","year":"2018","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref15","first-page":"270","article-title":"Learning graph-based cluster scheduling algorithms","author":"mao","year":"2018","journal-title":"Proc ACM Special Interest Group Data Commun"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref17","article-title":"Kubernetes","year":"2019"},{"key":"ref18","article-title":"Source code","year":"2021"},{"key":"ref19","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":"ref4","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Conf Operating Syst Des Implementation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref5","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2016","journal-title":"Proc Neural Inf Process Syst Workshop Mach Learn Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref7","article-title":"PaddlePaddle","year":"2019"},{"key":"ref49","article-title":"TFLearn objectives","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref46","article-title":"ImageNet dataset","year":"2019"},{"key":"ref45","article-title":"MXNet official examples","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626334"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661935"},{"key":"ref41","article-title":"Caffe2","year":"2019"},{"key":"ref44","article-title":"Docker","year":"2019"},{"key":"ref43","article-title":"HDFS","year":"2014"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9360409\/09328612.pdf?arnumber=9328612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:25Z","timestamp":1652194225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9328612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,1]]},"references-count":67,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3052895","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,1]]}}}