{"id":"https://openalex.org/W4414538491","doi":"https://doi.org/10.1109/icc52391.2025.11161040","title":"Which Cluster Meets My Deadline: a Budget-Aware Scheduler for Distributed Training Jobs in Heterogeneous Environments","display_name":"Which Cluster Meets My Deadline: a Budget-Aware Scheduler for Distributed Training Jobs in Heterogeneous Environments","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414538491","doi":"https://doi.org/10.1109/icc52391.2025.11161040"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11161040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on 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/A5100424320","display_name":"Yuchen Zhang","orcid":"https://orcid.org/0000-0002-7568-4959"},"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,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,P.R. 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,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,P.R. China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022284072","display_name":"Zonghang Li","orcid":"https://orcid.org/0000-0002-2796-039X"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Zonghang Li","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"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,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,P.R. China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","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,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,P.R. China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1506","last_page":"1511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9610999822616577,"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":0.9610999822616577,"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":0.9261000156402588,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9147999882698059,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5841000080108643},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5688999891281128},{"id":"https://openalex.org/keywords/renting","display_name":"Renting","score":0.4691999852657318},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4278999865055084},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.3871000111103058},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.3774000108242035},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.3677000105381012},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3562999963760376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849399983882904},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5777000188827515},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C85502023","wikidata":"https://www.wikidata.org/wiki/Q157171","display_name":"Renting","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11161040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2911714797","https://openalex.org/W2963149401","https://openalex.org/W3209503812","https://openalex.org/W4210877935","https://openalex.org/W4318541537","https://openalex.org/W4387321109","https://openalex.org/W4390263770","https://openalex.org/W4391986993","https://openalex.org/W4395020669","https://openalex.org/W4396817396","https://openalex.org/W4402968235"],"related_works":[],"abstract_inverted_index":{"Training":[0],"deep":[1],"learning":[2],"(DL)":[3],"models":[4],"demands":[5,94],"substantial":[6],"computational":[7,47],"resources,":[8],"often":[9,64],"relying":[10],"on":[11,77,99],"expensive":[12],"GPUs":[13],"in":[14],"a":[15,115,130],"distributed":[16],"manner.":[17],"To":[18],"meet":[19],"this":[20,105],"demand,":[21],"cloud":[22],"providers":[23],"deploy":[24],"GPU":[25,36,43,56,144],"clusters":[26,37],"worldwide":[27],"to":[28,84,109,150,200],"offer":[29],"users":[30,63],"compute":[31],"instance":[32,57],"rental":[33,152],"services.":[34],"These":[35],"are":[38],"typically":[39],"heterogeneous,":[40],"comprising":[41],"multiple":[42],"types":[44,58],"with":[45],"varying":[46],"capabilities,":[48],"and":[49,59,82,92,112,141,146,165,173],"their":[50,70,127],"prices":[51],"vary":[52],"significantly":[53,181],"across":[54],"both":[55],"geographic":[60],"regions.":[61],"Meanwhile,":[62],"have":[65],"specific":[66],"deadlines":[67,128],"for":[68],"training":[69,149],"models.":[71],"Most":[72],"existing":[73,183],"works":[74],"focus":[75],"solely":[76],"performance,":[78],"overlooking":[79],"price":[80],"heterogeneity":[81],"failing":[83],"optimize":[85],"costs":[86],"effectively.":[87],"Given":[88],"the":[89,121,156,186],"high":[90],"cost":[91,113],"time":[93],"of":[95,123],"model":[96],"training,":[97],"focusing":[98],"performance":[100,111],"alone":[101],"is":[102],"insufficient.":[103],"In":[104],"paper,":[106],"we":[107],"aim":[108],"balance":[110],"through":[114],"DL":[116],"broker":[117],"service":[118],"that":[119,179],"maximizes":[120],"number":[122],"jobs":[124],"completed":[125],"within":[126,190],"under":[129],"given":[131],"budget.":[132],"We":[133,154],"propose":[134,166],"CADDS,":[135],"which":[136],"jointly":[137],"optimizes":[138],"cluster":[139],"placement":[140],"dynamically":[142],"adjusts":[143],"type":[145],"quantity":[147],"during":[148],"reduce":[151],"costs.":[153],"formulate":[155],"scheduling":[157],"problem":[158,164],"as":[159],"an":[160,167],"integer":[161],"nonlinear":[162],"programming":[163],"efficient":[168],"online":[169],"approach":[170],"combining":[171],"greedy":[172],"dynamic":[174],"programming.":[175],"Experimental":[176],"results":[177],"demonstrate":[178],"CADDS":[180],"outperforms":[182],"approaches,":[184],"improving":[185],"deadline":[187],"satisfactory":[188],"ratio":[189],"budget":[191],"limits":[192],"by":[193],"<tex":[194,201],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[195,202],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{5":[196],"9.":[197],"4":[198],"\\%}$</tex>":[199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{8":[203],"0.":[204],"2":[205],"\\%}$</tex>.":[206]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
