{"id":"https://openalex.org/W3009152766","doi":"https://doi.org/10.1109/globecom38437.2019.9013361","title":"Topology-Aware Job Scheduling for Machine Learning Cluster","display_name":"Topology-Aware Job Scheduling for Machine Learning Cluster","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3009152766","doi":"https://doi.org/10.1109/globecom38437.2019.9013361","mag":"3009152766"},"language":"en","primary_location":{"id":"doi:10.1109/globecom38437.2019.9013361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom38437.2019.9013361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Global Communications Conference (GLOBECOM)","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/A5029175256","display_name":"Jingyuan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Lu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432795","display_name":"Peng Li","orcid":"https://orcid.org/0000-0003-4981-0496"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["The University of Aizu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Aizu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366692","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-9099-2781"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["University of California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101563568","display_name":"Huibin Feng","orcid":"https://orcid.org/0000-0002-7414-1370"},"institutions":[{"id":"https://openalex.org/I354108","display_name":"Minjiang University","ror":"https://ror.org/00s7tkw17","country_code":"CN","type":"education","lineage":["https://openalex.org/I354108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huibin Feng","raw_affiliation_strings":["Minjiang University, Fuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Minjiang University, Fuzhou, China","institution_ids":["https://openalex.org/I354108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035249711","display_name":"Enting Guo","orcid":"https://orcid.org/0000-0002-3462-1505"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enting Guo","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381778","display_name":"Xiaoyan Wang","orcid":"https://orcid.org/0000-0002-4353-3363"},"institutions":[{"id":"https://openalex.org/I6178835","display_name":"Ibaraki University","ror":"https://ror.org/00sjd5653","country_code":"JP","type":"education","lineage":["https://openalex.org/I6178835"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaoyan Wang","raw_affiliation_strings":["Ibaraki University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ibaraki University, Japan","institution_ids":["https://openalex.org/I6178835"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043464306","display_name":"Song Guo","orcid":"https://orcid.org/0000-0001-9831-2202"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Song Guo","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8024388551712036},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.562818169593811},{"id":"https://openalex.org/keywords/fifo","display_name":"FIFO (computing and electronics)","score":0.5228967070579529},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5030383467674255},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5028929114341736},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4741724729537964},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.4499621093273163},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.44157424569129944},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3932557702064514},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36529970169067383},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2332552671432495},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.22079643607139587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12276056408882141},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07038980722427368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8024388551712036},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.562818169593811},{"id":"https://openalex.org/C2777145635","wikidata":"https://www.wikidata.org/wiki/Q515636","display_name":"FIFO (computing and electronics)","level":2,"score":0.5228967070579529},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5030383467674255},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5028929114341736},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4741724729537964},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.4499621093273163},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.44157424569129944},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3932557702064514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36529970169067383},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2332552671432495},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.22079643607139587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12276056408882141},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07038980722427368}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/globecom38437.2019.9013361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom38437.2019.9013361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Global Communications Conference (GLOBECOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-130735","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2019&rft.spage=&rft.aulast=Lu&rft.aufirst=Jingyuan&rft.atitle=Topology-aware+job+scheduling+for+machine+learning+cluster&rft.title=2019+IEEE+Global+Communications+Conference%2C+GLOBECOM+2019+-+Proceedings","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5799999833106995,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1979146060","https://openalex.org/W2060393849","https://openalex.org/W2083842231","https://openalex.org/W2105947650","https://openalex.org/W2141992894","https://openalex.org/W2155893237","https://openalex.org/W2283208771","https://openalex.org/W2402144811","https://openalex.org/W2523435939","https://openalex.org/W2579247884","https://openalex.org/W2727537220","https://openalex.org/W2767239597","https://openalex.org/W2783354355","https://openalex.org/W2789871570","https://openalex.org/W2789896367","https://openalex.org/W2798515322","https://openalex.org/W2800696118","https://openalex.org/W2806037422","https://openalex.org/W2809420642","https://openalex.org/W2883910734","https://openalex.org/W2885338472","https://openalex.org/W2890075093","https://openalex.org/W2899071864","https://openalex.org/W2909611778","https://openalex.org/W2947658163","https://openalex.org/W2953384591","https://openalex.org/W2962684017","https://openalex.org/W2965347872","https://openalex.org/W2982408761","https://openalex.org/W3098222317","https://openalex.org/W4289401659","https://openalex.org/W6680929869","https://openalex.org/W6740062631","https://openalex.org/W6756009870"],"related_works":["https://openalex.org/W2092530219","https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2105580438","https://openalex.org/W2158430778","https://openalex.org/W3172150420","https://openalex.org/W2057435755","https://openalex.org/W2107725657","https://openalex.org/W2533984654"],"abstract_inverted_index":{"Parameter":[0],"Server":[1],"(PS)":[2],"has":[3,42],"been":[4],"widely":[5],"used":[6],"to":[7,27,33,89,133],"train":[8],"a":[9,22,72],"large":[10],"amount":[11],"of":[12,45,49,60,67,80,85,123,135,137,141],"data":[13],"on":[14,77,112],"multiple":[15,30],"machines":[16],"in":[17,102],"parallel.":[18],"In":[19],"parameter":[20,103],"server,":[21],"critical":[23],"problem":[24,101],"is":[25],"how":[26],"effectively":[28,56],"schedule":[29],"training":[31],"jobs":[32],"minimize":[34],"the":[35,47,58,65,78,83,90,108,121],"job":[36,129],"completion":[37],"time.":[38],"Some":[39],"existing":[40],"work":[41],"proposed":[43],"methods":[44],"setting":[46],"number":[48,79],"concurrent":[50],"workers.":[51],"However,":[52],"they":[53],"do":[54],"not":[55],"consider":[57],"topology":[59,84,100],"GPU":[61,86],"placement":[62,109],"which":[63],"affects":[64],"efficiency":[66],"communication.":[68],"This":[69],"paper":[70],"proposes":[71],"novel":[73],"resource-to-time":[74],"model":[75],"based":[76,111],"workers":[81],"and":[82,139],"placement.":[87],"According":[88],"model,":[91],"we":[92],"propose":[93],"an":[94],"algorithm":[95,106],"called":[96],"TOPO-PS":[97,126],"particularly":[98],"for":[99],"servers.":[104],"The":[105],"achieves":[107],"strategy":[110],"graph":[113],"mapping":[114],"algorithm.":[115,125],"Evaluation":[116],"under":[117],"various":[118],"algorithms":[119],"evidences":[120],"superiority":[122],"our":[124],"yields":[127],"shorter":[128],"completion,":[130],"by":[131],"up":[132],"53.48%":[134],"that":[136],"FIFO":[138],"88.77%":[140],"OASIS.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}