{"id":"https://openalex.org/W3106918569","doi":"https://doi.org/10.1109/tcc.2020.3040312","title":"Efficient Online Scheduling for Coflow-Aware Machine Learning Clusters","display_name":"Efficient Online Scheduling for Coflow-Aware Machine Learning Clusters","publication_year":2020,"publication_date":"2020-11-25","ids":{"openalex":"https://openalex.org/W3106918569","doi":"https://doi.org/10.1109/tcc.2020.3040312","mag":"3106918569"},"language":"en","primary_location":{"id":"doi:10.1109/tcc.2020.3040312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2020.3040312","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cloud Computing","raw_type":"journal-article"},"type":"article","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/A5100397205","display_name":"Wenxin Li","orcid":"https://orcid.org/0000-0001-8507-0339"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenxin Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8507-0339","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320971","display_name":"Sheng Chen","orcid":"https://orcid.org/0000-0001-7038-4407"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Chen","raw_affiliation_strings":["Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7038-4407","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111982109","display_name":"Keqiu Li","orcid":"https://orcid.org/0000-0003-1758-3030"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keqiu Li","raw_affiliation_strings":["Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087744818","display_name":"Heng Qi","orcid":"https://orcid.org/0000-0002-8770-3934"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Qi","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-8770-3934","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035883665","display_name":"Renhai Xu","orcid":"https://orcid.org/0000-0002-0645-157X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renhai Xu","raw_affiliation_strings":["Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-0645-157X","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100366509","display_name":"Song Zhang","orcid":"https://orcid.org/0000-0001-5396-0003"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Zhang","raw_affiliation_strings":["Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Advanced Networking (TANK), College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3989,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87772152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"4","first_page":"2564","last_page":"2579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"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":0.9991000294685364,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9966999888420105,"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":0.598824143409729},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5583356618881226},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4951449930667877},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.48546794056892395},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.48434269428253174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42952844500541687},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3339158892631531},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.18981894850730896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16489723324775696},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10767209529876709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.598824143409729},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5583356618881226},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4951449930667877},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.48546794056892395},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.48434269428253174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42952844500541687},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3339158892631531},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.18981894850730896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16489723324775696},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10767209529876709}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcc.2020.3040312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2020.3040312","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cloud Computing","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-109354","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-109354","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":"","raw_type":"Article"},{"id":"pmh:oai:repository.ust.hk:1783.1-109354","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-109354","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":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7733246160","display_name":"\u9762\u5411\u53ef\u89c6\u5a92\u4f53\u5927\u6570\u636e\u5904\u7406\u7684\u8ba1\u7b97\u7f51\u7edc\u534f\u540c\u8c03\u5ea6\u5173\u952e\u6280\u672f\u7684\u7814\u7a76","funder_award_id":"61772112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1442374986","https://openalex.org/W1545728916","https://openalex.org/W1657185548","https://openalex.org/W1990249073","https://openalex.org/W2013932952","https://openalex.org/W2060393849","https://openalex.org/W2062428974","https://openalex.org/W2091520147","https://openalex.org/W2095705004","https://openalex.org/W2096544401","https://openalex.org/W2102549685","https://openalex.org/W2109722477","https://openalex.org/W2110514750","https://openalex.org/W2117884704","https://openalex.org/W2124718325","https://openalex.org/W2127941149","https://openalex.org/W2132737349","https://openalex.org/W2138243089","https://openalex.org/W2149939304","https://openalex.org/W2155893237","https://openalex.org/W2157614013","https://openalex.org/W2168231600","https://openalex.org/W2168427242","https://openalex.org/W2186615578","https://openalex.org/W2463263320","https://openalex.org/W2487448491","https://openalex.org/W2488801318","https://openalex.org/W2504213755","https://openalex.org/W2579247884","https://openalex.org/W2604783387","https://openalex.org/W2606722458","https://openalex.org/W2612026221","https://openalex.org/W2622263826","https://openalex.org/W2744959101","https://openalex.org/W2769644379","https://openalex.org/W2776474795","https://openalex.org/W2789335636","https://openalex.org/W2793893042","https://openalex.org/W2794339560","https://openalex.org/W2794670651","https://openalex.org/W2794896506","https://openalex.org/W2798515322","https://openalex.org/W2808421218","https://openalex.org/W2809420642","https://openalex.org/W2824027552","https://openalex.org/W2824896242","https://openalex.org/W2884711234","https://openalex.org/W2899071864","https://openalex.org/W2919594608","https://openalex.org/W2953384591","https://openalex.org/W2962758826","https://openalex.org/W2975712713","https://openalex.org/W3047537431","https://openalex.org/W3089626046","https://openalex.org/W3105875719","https://openalex.org/W3124352525","https://openalex.org/W4247842874","https://openalex.org/W4288357791","https://openalex.org/W4289401659","https://openalex.org/W6614148910","https://openalex.org/W6628377381","https://openalex.org/W6636819530","https://openalex.org/W6665801690","https://openalex.org/W6674330103","https://openalex.org/W6676367512","https://openalex.org/W6679154944","https://openalex.org/W6679393576","https://openalex.org/W6680402377","https://openalex.org/W6684859321","https://openalex.org/W6686509673","https://openalex.org/W6713134421","https://openalex.org/W6736413256","https://openalex.org/W6739622702","https://openalex.org/W6739693220","https://openalex.org/W6746200960","https://openalex.org/W6752199355","https://openalex.org/W6753209298","https://openalex.org/W6754818105","https://openalex.org/W6756009870","https://openalex.org/W6759814162","https://openalex.org/W6762211661"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W3204654320"],"abstract_inverted_index":{"Distributed":[0],"machine":[1],"learning":[2],"(DML)":[3],"is":[4,137,163],"an":[5,120,164],"increasingly":[6],"important":[7],"workload.":[8],"In":[9],"a":[10,18,56,94,99,187,202,209,233],"DML":[11,37,86,222],"job,":[12],"each":[13,149],"communication":[14],"phase":[15],"can":[16,250],"comprise":[17],"<italic":[19,126,134,181,228,247],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[20,127,135,182,229,248],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">coflow</i>":[21],",":[22,184],"and":[23,106,151,208],"there":[24,54],"are":[25,55],"dependencies":[26],"among":[27,221],"its":[28,108],"coflows.":[29],"Thus,":[30],"efficient":[31],"coflow":[32],"scheduling":[33,47],"becomes":[34],"critical":[35],"for":[36,103,218],"jobs.":[38,223],"However,":[39],"the":[40,90,140,143,154,178,196,252,262],"majority":[41],"of":[42,62,84,170,180],"existing":[43],"solutions":[44],"focus":[45],"on":[46,159],"single-stage":[48],"coflows":[49,61,83],"with":[50,142],"no":[51],"dependencies.":[52],"While":[53],"few":[57],"studies":[58],"schedule":[59,81],"dependent":[60,82],"multi-stage":[63],"jobs,":[64],"they":[65],"suffer":[66],"from":[67,239],"either":[68],"practical":[69],"or":[70],"theoretical":[71],"issues.":[72],"Motivated":[73],"by":[74,255],"this":[75,104,112],"situation,":[76],"we":[77,118,185],"study":[78],"how":[79,160],"to":[80,88,138,194,257,261],"multiple":[85],"jobs":[87],"minimize":[89],"total":[91,253],"JCT":[92,254],"in":[93,133,177],"shared":[95],"cluster.":[96],"We":[97,199,224],"present":[98,119,186],"formal":[100],"mathematical":[101],"formulation":[102],"problem":[105,113],"prove":[107],"NP-hardness.":[109],"To":[110],"solve":[111],"without":[114],"job":[115,141,166,204],"size":[116],"information,":[117],"online":[121],"coflow-aware":[122],"optimization":[123],"framework":[124],"called":[125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Parrot</i>":[128,136,183,230,249],".":[129],"The":[130,237],"core":[131],"idea":[132],"infer":[139,195],"shortest":[144],"remaining":[145],"processing":[146],"time":[147,150],"(SRPT)":[148],"dynamically":[152],"control":[153],"inferred":[155],"job's":[156],"bandwidth":[157,215,220],"based":[158,213],"confident":[161],"it":[162],"SRPT":[165,197],"while":[167],"being":[168],"mindful":[169],"not":[171],"starving":[172],"any":[173],"other":[174],"job.":[175,198],"Specifically,":[176],"design":[179],"least":[188],"per-coflow":[189],"attained":[190],"service":[191],"(LPCAS)":[192],"policy":[193],"further":[200,243],"propose":[201],"dynamic":[203],"weight":[205],"assignment":[206],"mechanism":[207],"linear":[210],"program":[211],"(LP)":[212],"weighted":[214],"scaling":[216],"strategy":[217],"sharing":[219],"have":[225],"proved":[226],"that":[227,245],"algorithm":[231],"has":[232],"non-trivial":[234],"competitive":[235],"ratio.":[236],"results":[238],"large-scale":[240],"trace-driven":[241],"simulations":[242],"demonstrate":[244],"our":[246],"reduce":[251],"up":[256],"58.4":[258],"percent,":[259],"compared":[260],"state-of-the-art":[263],"Aalo":[264],"solution.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
