{"id":"https://openalex.org/W4386133880","doi":"https://doi.org/10.1109/tcc.2023.3308161","title":"On a Meta Learning-Based Scheduler for Deep Learning Clusters","display_name":"On a Meta Learning-Based Scheduler for Deep Learning Clusters","publication_year":2023,"publication_date":"2023-08-24","ids":{"openalex":"https://openalex.org/W4386133880","doi":"https://doi.org/10.1109/tcc.2023.3308161"},"language":"en","primary_location":{"id":"doi:10.1109/tcc.2023.3308161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2023.3308161","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/A5001395664","display_name":"Jin Yang","orcid":"https://orcid.org/0000-0003-3096-7741"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yang","raw_affiliation_strings":["Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-3096-7741","affiliations":[{"raw_affiliation_string":"Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018729096","display_name":"Liang Bao","orcid":"https://orcid.org/0000-0003-1710-4335"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Bao","raw_affiliation_strings":["Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-1710-4335","affiliations":[{"raw_affiliation_string":"Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378290","display_name":"Wenjing Liu","orcid":"https://orcid.org/0000-0001-8207-1862"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Liu","raw_affiliation_strings":["Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-8207-1862","affiliations":[{"raw_affiliation_string":"Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101628238","display_name":"Rong Yang","orcid":"https://orcid.org/0009-0003-3769-7630"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Yang","raw_affiliation_strings":["Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0003-3769-7630","affiliations":[{"raw_affiliation_string":"Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054307870","display_name":"Chase Q. Wu","orcid":"https://orcid.org/0000-0002-8218-1209"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chase Q. Wu","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-8218-1209","affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1103,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94570464,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":"4","first_page":"3631","last_page":"3642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9965000152587891,"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/T12288","display_name":"Optimization and Search Problems","score":0.9919999837875366,"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":0.8598509430885315},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7906656265258789},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7782326936721802},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6699827313423157},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6252177953720093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5119153261184692},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.444486141204834},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.43442004919052124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40787801146507263},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12681812047958374},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.10887092351913452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598509430885315},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7906656265258789},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7782326936721802},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6699827313423157},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6252177953720093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5119153261184692},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.444486141204834},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.43442004919052124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40787801146507263},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12681812047958374},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.10887092351913452},{"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/tcc.2023.3308161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2023.3308161","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"}],"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":[{"id":"https://openalex.org/G8513748798","display_name":null,"funder_award_id":"62172316","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1695021962","https://openalex.org/W2105947650","https://openalex.org/W2480662436","https://openalex.org/W2578206533","https://openalex.org/W2736601468","https://openalex.org/W2798515322","https://openalex.org/W2919897868","https://openalex.org/W2945696849","https://openalex.org/W2949562459","https://openalex.org/W2962684017","https://openalex.org/W2963149401","https://openalex.org/W2963523627","https://openalex.org/W3012125688","https://openalex.org/W3022298203","https://openalex.org/W3047610867","https://openalex.org/W3096956001","https://openalex.org/W3113635268","https://openalex.org/W3131369229","https://openalex.org/W3154142431","https://openalex.org/W3185663263","https://openalex.org/W3197816522","https://openalex.org/W3200459676","https://openalex.org/W3204998121","https://openalex.org/W3205185457","https://openalex.org/W3209503812","https://openalex.org/W4285337568","https://openalex.org/W4286242951","https://openalex.org/W4287827583","https://openalex.org/W4288363736","https://openalex.org/W4298857966","https://openalex.org/W4304820446","https://openalex.org/W4313160155","https://openalex.org/W4315567908","https://openalex.org/W4386608891","https://openalex.org/W6637567504","https://openalex.org/W6637967152","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6756009870","https://openalex.org/W6758283263","https://openalex.org/W6761709163","https://openalex.org/W6766003144","https://openalex.org/W6767869616","https://openalex.org/W6769849633","https://openalex.org/W6770508135","https://openalex.org/W6771843596","https://openalex.org/W6784871562","https://openalex.org/W6788546958","https://openalex.org/W6793903029","https://openalex.org/W6794550059","https://openalex.org/W6799075241","https://openalex.org/W6799579448","https://openalex.org/W6800695281","https://openalex.org/W6841490253"],"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/W2287264064","https://openalex.org/W2130149817","https://openalex.org/W2547038763","https://openalex.org/W44553394","https://openalex.org/W3047653192"],"abstract_inverted_index":{"Deep":[0],"learning":[1,29],"(DL)":[2],"has":[3],"become":[4],"a":[5,69,97],"dominating":[6],"type":[7],"of":[8,16,39,57,108,131,147],"workloads":[9],"on":[10,21,90],"AI":[11],"computing":[12],"platforms.":[13],"The":[14],"performance":[15,121],"such":[17],"platforms":[18],"highly":[19],"depends":[20],"how":[22],"distributed":[23],"DL":[24,92,104],"jobs":[25,44],"are":[26,37],"scheduled.":[27],"Reinforcement":[28],"(RL)-based":[30],"schedulers":[31,51],"have":[32],"been":[33],"extensively":[34],"studied":[35],"and":[36,59],"capable":[38],"modeling":[40],"interferences":[41],"between":[42],"concurrent":[43],"competing":[45],"for":[46,72,86,103],"resources.":[47],"However,":[48],"existing":[49],"RL-based":[50],"must":[52],"learn":[53],"from":[54],"large":[55],"number":[56],"samples":[58],"adapt":[60],"to":[61,115,126,154,164],"workload":[62,160],"changes":[63],"in":[64,145],"real":[65],"systems,":[66],"which":[67],"is":[68],"huge":[70],"cost":[71],"production":[73],"clusters.":[74,93],"This":[75],"paper":[76],"proposes":[77],"an":[78],"intelligent,":[79],"autonomous":[80],"scheduler":[81,114,133],"that":[82,139],"employs":[83],"sample-efficient":[84],"RL":[85],"real-world":[87],"resource":[88],"scheduling":[89],"complex":[91],"Specifically,":[94],"we":[95,111],"design":[96],"closed-loop":[98],"meta-RL-based":[99],"worker":[100],"placement":[101],"algorithm":[102,141],"training":[105],"jobs.":[106],"Instead":[107],"random":[109],"exploration,":[110],"encourage":[112],"the":[113,120,128,132],"explore":[116],"combinatorial":[117],"subspaces,":[118],"where":[119],"model":[122],"might":[123],"be":[124],"inaccurate,":[125],"improve":[127],"sampling":[129],"efficiency":[130],"agent.":[134],"Extensive":[135],"experimental":[136],"results":[137],"demonstrate":[138],"our":[140],"outperforms":[142],"other":[143],"baselines":[144],"terms":[146],"average":[148],"job":[149],"completion":[150],"time":[151],"with":[152,159],"12.29%":[153],"16.24%":[155],"improvements.":[156,166],"Further":[157],"experiments":[158],"variations":[161],"yield":[162],"15.76%":[163],"22.13%":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}