{"id":"https://openalex.org/W2962684017","doi":"https://doi.org/10.1109/infocom.2018.8486422","title":"Online Job Scheduling in Distributed Machine Learning Clusters","display_name":"Online Job Scheduling in Distributed Machine Learning Clusters","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962684017","doi":"https://doi.org/10.1109/infocom.2018.8486422","mag":"2962684017"},"language":"en","primary_location":{"id":"doi:10.1109/infocom.2018.8486422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom.2018.8486422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2018 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054679083","display_name":"Yixin Bao","orcid":"https://orcid.org/0000-0002-6921-2154"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yixin Bao","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013856812","display_name":"Yanghua Peng","orcid":"https://orcid.org/0000-0003-3989-4358"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yanghua Peng","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012597518","display_name":"Chuan Wu","orcid":"https://orcid.org/0000-0002-3144-4398"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chuan Wu","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066247159","display_name":"Zongpeng Li","orcid":"https://orcid.org/0000-0001-5351-2075"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zongpeng Li","raw_affiliation_strings":["Department of Computer Science, University of Calgary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Calgary","institution_ids":["https://openalex.org/I168635309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.6661,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.99424533,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"495","last_page":"503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8450559377670288},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6077002286911011},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5780271887779236},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5529268383979797},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5351335406303406},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.504449725151062},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.4674326777458191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4645886719226837},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.45218342542648315},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4477781653404236},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.4322908818721771},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.41575154662132263},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4156338572502136},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17191195487976074},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14846360683441162},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.13896813988685608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450559377670288},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6077002286911011},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5780271887779236},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5529268383979797},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5351335406303406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.504449725151062},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.4674326777458191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4645886719226837},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.45218342542648315},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4477781653404236},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.4322908818721771},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.41575154662132263},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4156338572502136},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17191195487976074},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14846360683441162},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13896813988685608},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom.2018.8486422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom.2018.8486422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2018 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1525444182","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1888294891","https://openalex.org/W1890643295","https://openalex.org/W2018162709","https://openalex.org/W2025222277","https://openalex.org/W2025616337","https://openalex.org/W2060393849","https://openalex.org/W2074694452","https://openalex.org/W2083842231","https://openalex.org/W2105947650","https://openalex.org/W2108598243","https://openalex.org/W2129542763","https://openalex.org/W2139901185","https://openalex.org/W2141992894","https://openalex.org/W2142339200","https://openalex.org/W2163605009","https://openalex.org/W2163961697","https://openalex.org/W2183243439","https://openalex.org/W2186615578","https://openalex.org/W2189465200","https://openalex.org/W2194775991","https://openalex.org/W2335814492","https://openalex.org/W2402144811","https://openalex.org/W2527855297","https://openalex.org/W2609354095","https://openalex.org/W2764122222","https://openalex.org/W2949117887","https://openalex.org/W2953384591","https://openalex.org/W2962684017","https://openalex.org/W2962835968","https://openalex.org/W2962911728","https://openalex.org/W3102385572","https://openalex.org/W3105569215","https://openalex.org/W4206478994","https://openalex.org/W4245846982","https://openalex.org/W6628377381","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6639249596","https://openalex.org/W6639518697","https://openalex.org/W6665801690","https://openalex.org/W6680929869","https://openalex.org/W6684084819","https://openalex.org/W6684191040","https://openalex.org/W6686509673","https://openalex.org/W6687322159","https://openalex.org/W6713134421","https://openalex.org/W6744847032","https://openalex.org/W6786389395"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2092966558","https://openalex.org/W1956651153","https://openalex.org/W1984267569","https://openalex.org/W2347561926","https://openalex.org/W2315766899","https://openalex.org/W2327547880","https://openalex.org/W3130253067","https://openalex.org/W3153517983","https://openalex.org/W210339300"],"abstract_inverted_index":{"Nowadays":[0],"large-scale":[1],"distributed":[2,98],"machine":[3,99],"learning":[4,100],"systems":[5],"have":[6],"been":[7],"deployed":[8],"to":[9,40,65,76,135,189],"support":[10],"various":[11],"analytics":[12],"and":[13,24,47,69,88,118,126,180],"intelligence":[14],"services":[15],"in":[16,38,94,194],"IT":[17],"firms.":[18],"To":[19],"train":[20,41],"a":[21,30,53,60,97,152],"large":[22],"dataset":[23],"derive":[25],"the":[26,44,71,103,115,120,172],"prediction/inference":[27],"model,":[28],"e.g.,":[29],"deep":[31],"neural":[32],"network,":[33],"multiple":[34,57],"workers":[35,75,125],"are":[36,85],"run":[37,77],"parallel":[39],"partitions":[42],"of":[43,73,123,139,171],"input":[45],"dataset,":[46],"update":[48],"shared":[49,54],"model":[50,89],"parameters.":[51],"In":[52],"cluster":[55],"handling":[56],"training":[58,90],"jobs,":[59,141],"fundamental":[61],"issue":[62],"is":[63,175],"how":[64],"efficiently":[66],"schedule":[67],"jobs":[68,117],"set":[70],"number":[72],"concurrent":[74,124],"for":[78,113,129],"each":[79,130],"job,":[80],"such":[81],"that":[82],"server":[83,105],"resources":[84],"maximally":[86],"utilized":[87],"can":[91],"be":[92],"completed":[93],"time.":[95],"Targeting":[96],"system":[101],"using":[102,177],"parameter":[104,127],"framework,":[106],"w":[107],"e":[108],"design":[109,150],"an":[110],"online":[111,148,173],"algorithm":[112,149,174],"scheduling":[114,192],"arriving":[116],"deciding":[119],"adjusted":[121],"numbers":[122],"servers":[128],"job":[131],"over":[132],"its":[133,185],"course,":[134],"maximize":[136],"overall":[137],"utility":[138],"all":[140],"contingent":[142],"on":[143],"their":[144],"completion":[145],"times.":[146],"Our":[147],"utilizes":[151],"primal-dual":[153],"framework":[154],"coupled":[155],"with":[156,165],"efficient":[157],"dual":[158],"subroutines,":[159],"achieving":[160],"good":[161],"long-term":[162],"performance":[163],"guarantees":[164],"polynomial":[166],"time":[167],"complexity.":[168],"Practical":[169],"effectiveness":[170],"evaluated":[176],"trace-driven":[178],"simulation":[179],"testbed":[181],"experiments,":[182],"which":[183],"demonstrate":[184],"outperformance":[186],"as":[187],"compared":[188],"commonly":[190],"adopted":[191],"algorithms":[193],"today's":[195],"cloud":[196],"systems.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}