{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T17:55:43Z","timestamp":1784656543359,"version":"3.55.0"},"reference-count":64,"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":"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\/501100002920","name":"Hong Kong Research Grants Council","doi-asserted-by":"publisher","award":["HKU 17204619"],"award-info":[{"award-number":["HKU 17204619"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Hong Kong Research Grants Council","doi-asserted-by":"publisher","award":["17208920"],"award-info":[{"award-number":["17208920"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Hong Kong Research Grants Council","doi-asserted-by":"publisher","award":["17207621"],"award-info":[{"award-number":["17207621"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tnet.2022.3202529","type":"journal-article","created":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T19:45:46Z","timestamp":1662666346000},"page":"634-647","source":"Crossref","is-referenced-by-count":25,"title":["Deep Learning-Based Job Placement in Distributed Machine Learning Clusters With Heterogeneous Workloads"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6921-2154","authenticated-orcid":false,"given":"Yixin","family":"Bao","sequence":"first","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-4358","authenticated-orcid":false,"given":"Yanghua","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-4398","authenticated-orcid":false,"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"227","article-title":"Interference and locality-aware task scheduling for MapReduce applications in virtual clusters","author":"bu","year":"2013","journal-title":"Proc ACM HPDC"},{"key":"ref57","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref56","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2013.38"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","first-page":"325","article-title":"Network-aware task assignment for MapReduce applications in shared clusters","volume":"16","author":"xu","year":"2015","journal-title":"J Internet Technol"},{"key":"ref58","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref53","first-page":"1","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc ICLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421307"},{"key":"ref11","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref55","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref10","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NeurIPS"},{"key":"ref54","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2499368.2451125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052895"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref51","year":"2018","journal-title":"Alibaba cloud"},{"key":"ref50","year":"2018","journal-title":"Microsoft Azure"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626334"},{"key":"ref45","year":"2017","journal-title":"MXNet Official Examples"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.123"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737391"},{"key":"ref43","first-page":"1","article-title":"A hierarchical model for device placement","author":"mirhoseini","year":"2018","journal-title":"Proc ICLR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref8","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 NSDI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref3","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref6","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018","journal-title":"arXiv 1802 05799"},{"key":"ref5","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","author":"chilimbi","year":"2014","journal-title":"Proc USENIX OSDI"},{"key":"ref40","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","author":"mirhoseini","year":"2017","journal-title":"Proc ICML"},{"key":"ref35","first-page":"481","article-title":"Heterogeneity-aware cluster scheduling policies for deep learning workloads","author":"narayanan","year":"2020","journal-title":"Proc USENIX OSDI"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2015.2481403"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2015.7335272"},{"key":"ref31","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","author":"gu","year":"2019","journal-title":"Proc USENIX NSDI"},{"key":"ref30","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc USENIX OSDI"},{"key":"ref33","first-page":"289","article-title":"THEMIS: Fair and efficient GPU cluster scheduling","author":"mahajan","year":"2020","journal-title":"Proc USENIX NSDI"},{"key":"ref32","first-page":"400","article-title":"Resource elasticity in distributed deep learning","author":"or","year":"2020","journal-title":"Proc MLSys"},{"key":"ref2","first-page":"1","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2016","journal-title":"Proc NeurIPS Workshop Mach Learn Syst (LearningSys)"},{"key":"ref1","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX OSDI"},{"key":"ref39","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541941"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref23","year":"2018","journal-title":"Kubernetes"},{"key":"ref26","year":"2018","journal-title":"Paddlepaddle"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329065"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.82"},{"key":"ref22","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2017.7947053"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref60","year":"2014","journal-title":"Hdfs"},{"key":"ref62","year":"2018","journal-title":"The ImageNet dataset"},{"key":"ref61","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10103748\/09882005.pdf?arnumber=9882005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T19:09:40Z","timestamp":1683572980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9882005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":64,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2022.3202529","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}