{"id":"https://openalex.org/W4408182811","doi":"https://doi.org/10.1109/tcc.2025.3548604","title":"Deadline-Aware Online Job Scheduling for Distributed Training in Heterogeneous Clusters","display_name":"Deadline-Aware Online Job Scheduling for Distributed Training in Heterogeneous Clusters","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4408182811","doi":"https://doi.org/10.1109/tcc.2025.3548604"},"language":"en","primary_location":{"id":"doi:10.1109/tcc.2025.3548604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2025.3548604","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/A5100424312","display_name":"Yuchen Zhang","orcid":"https://orcid.org/0000-0002-3153-4000"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015538526","display_name":"Long Luo","orcid":"https://orcid.org/0000-0003-1028-8178"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Luo","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1028-8178","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053945147","display_name":"Gang Sun","orcid":"https://orcid.org/0000-0002-2448-8915"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Sun","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2448-8915","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101507232","display_name":"Hongfang Yu","orcid":"https://orcid.org/0000-0002-5219-1780"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfang Yu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5219-1780","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100374506","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-2083-9105"},"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":"Bo Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong","Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-2083-9105","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6049,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95821171,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"13","issue":"2","first_page":"590","last_page":"604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.95660001039505,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.95660001039505,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9563999772071838,"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":0.9247999787330627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778565287590027},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5150761008262634},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5143355131149292},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5030624270439148},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.42949503660202026},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19128459692001343},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.07887041568756104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778565287590027},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5150761008262634},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5143355131149292},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5030624270439148},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.42949503660202026},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19128459692001343},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.07887041568756104},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcc.2025.3548604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2025.3548604","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:1783.1-151572","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-151572","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G1369682866","display_name":null,"funder_award_id":"ZYGX2022J003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5223361291","display_name":null,"funder_award_id":"62394324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G709155833","display_name":null,"funder_award_id":"62102066","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2083842231","https://openalex.org/W2618530766","https://openalex.org/W2798515322","https://openalex.org/W2962684017","https://openalex.org/W2964667342","https://openalex.org/W2991040477","https://openalex.org/W3022298203","https://openalex.org/W3121689374","https://openalex.org/W3130934537","https://openalex.org/W3134991928","https://openalex.org/W3209503812","https://openalex.org/W4205500752","https://openalex.org/W4205916020","https://openalex.org/W4221149636","https://openalex.org/W4234534407","https://openalex.org/W4250739957","https://openalex.org/W4288083766","https://openalex.org/W4306955484","https://openalex.org/W4318541537","https://openalex.org/W4321485372","https://openalex.org/W4360884927","https://openalex.org/W4372262787","https://openalex.org/W4386133880","https://openalex.org/W4387321109","https://openalex.org/W4388966802","https://openalex.org/W4392309097","https://openalex.org/W4395020669","https://openalex.org/W4400410044","https://openalex.org/W6684859321","https://openalex.org/W6753584990","https://openalex.org/W6753801579","https://openalex.org/W6756009870","https://openalex.org/W6759814162","https://openalex.org/W6769424276","https://openalex.org/W6781728138","https://openalex.org/W6782839094","https://openalex.org/W6784871562","https://openalex.org/W6793903029","https://openalex.org/W6845705509","https://openalex.org/W6855921298"],"related_works":["https://openalex.org/W1582214068","https://openalex.org/W44553394","https://openalex.org/W2172100609","https://openalex.org/W3174084021","https://openalex.org/W1970208768","https://openalex.org/W1559381305","https://openalex.org/W3047653192","https://openalex.org/W4283696703","https://openalex.org/W381368390","https://openalex.org/W1984090128"],"abstract_inverted_index":{"The":[0],"explosive":[1],"growth":[2],"in":[3,18,27,51,62,119,155],"training":[4,25,104],"data":[5],"and":[6,130,169],"model":[7],"sizes":[8],"has":[9],"spurred":[10],"the":[11,91,94,112,132,138,191],"adoption":[12],"of":[13,96,114,140],"distributed":[14,24],"deep":[15],"learning":[16],"(DL)":[17],"heterogeneous":[19,29,63,120],"computing":[20],"clusters.":[21,64,122],"Efficiently":[22],"scheduling":[23,133],"jobs":[26,115,142],"such":[28],"environments":[30],"while":[31],"ensuring":[32],"they":[33,54],"meet":[34],"user-specified":[35],"deadlines":[36,61,118],"remains":[37],"a":[38,83,163],"critical":[39],"challenge.":[40],"While":[41],"most":[42],"existing":[43],"works":[44],"focus":[45],"on":[46,177],"reducing":[47],"job":[48,60,101,125],"completion":[49],"time":[50],"homogeneous":[52],"clusters,":[53],"pay":[55],"little":[56],"attention":[57],"to":[58,99,110,196],"meeting":[59,116],"To":[65,150],"address":[66],"this":[67,152],"issue,":[68],"we":[69,157],"propose":[70,158],"<sc":[71,106,183],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72,107,184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Dancer</small>":[73,108,185],"(Deadline-Aware":[74],"dyNamiC":[75],"GPU":[76,121],"allocation":[77,129],"approach":[78],"for":[79,136],"Efficient":[80],"Resource":[81],"utilization),":[82],"novel":[84],"framework":[85],"that":[86,182],"dynamically":[87],"adjusts":[88],"not":[89],"only":[90],"number":[92,113,139],"but":[93],"type":[95],"GPUs":[97],"assigned":[98],"each":[100],"throughout":[102],"its":[103],"lifecycle.":[105],"aims":[109],"maximize":[111],"their":[117],"It":[123],"decouples":[124],"placement":[126],"from":[127],"resource":[128],"formulates":[131],"optimization":[134],"problem":[135,154],"maximizing":[137],"deadline-meeting":[141],"as":[143],"an":[144,159],"Integer":[145],"Linear":[146],"Programming":[147],"(ILP)":[148],"problem.":[149],"solve":[151],"ILP":[153],"real-time,":[156],"online":[160],"algorithm":[161],"with":[162],"competitive":[164],"ratio":[165,194],"guarantee,":[166],"leveraging":[167],"primal-dual":[168],"dynamic":[170],"programming":[171],"techniques.":[172],"Extensive":[173],"trace-driven":[174],"simulations":[175],"based":[176],"real-world":[178],"DL":[179],"workloads":[180],"demonstrate":[181],"significantly":[186],"outperforms":[187],"state-of-the-art":[188],"approaches,":[189],"improving":[190],"deadline":[192],"satisfactory":[193],"up":[195],"58.9%\u201374.2%.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
