{"id":"https://openalex.org/W2975995881","doi":"https://doi.org/10.1109/infcomw.2019.8845276","title":"Poster Abstract: Deep Learning Workloads Scheduling with Reinforcement Learning on GPU Clusters","display_name":"Poster Abstract: Deep Learning Workloads Scheduling with Reinforcement Learning on GPU Clusters","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2975995881","doi":"https://doi.org/10.1109/infcomw.2019.8845276","mag":"2975995881"},"language":"en","primary_location":{"id":"doi:10.1109/infcomw.2019.8845276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2019.8845276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","raw_type":"proceedings-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/A5101981758","display_name":"Zhaoyun Chen","orcid":"https://orcid.org/0000-0003-1552-8396"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoyun Chen","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672909","display_name":"Lei Luo","orcid":"https://orcid.org/0000-0002-9329-1411"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Luo","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082147952","display_name":"Wei Quan","orcid":"https://orcid.org/0000-0002-0934-8324"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Quan","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028935020","display_name":"Mei Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710936","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-0944-2708"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyuan Zhang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101981758"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.4075,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86874799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1023","last_page":"1024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9921000003814697,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8744282126426697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8440206050872803},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7192742824554443},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.709652841091156},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5557041168212891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.553325891494751},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5305740237236023},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5228220224380493},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46327683329582214},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4237639904022217},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.237985759973526},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18020358681678772},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.10122731328010559},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08014810085296631}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8744282126426697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440206050872803},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7192742824554443},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.709652841091156},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5557041168212891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553325891494751},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5305740237236023},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5228220224380493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46327683329582214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4237639904022217},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.237985759973526},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18020358681678772},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.10122731328010559},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08014810085296631},{"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/infcomw.2019.8845276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2019.8845276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2798515322","https://openalex.org/W2899071864","https://openalex.org/W2913196997","https://openalex.org/W2944938400","https://openalex.org/W2962684017","https://openalex.org/W6756009870"],"related_works":["https://openalex.org/W47352601","https://openalex.org/W2981957539","https://openalex.org/W4287378204","https://openalex.org/W2461489085","https://openalex.org/W2545422590","https://openalex.org/W4240705470","https://openalex.org/W2945311252","https://openalex.org/W631546281","https://openalex.org/W4206501676","https://openalex.org/W88292646"],"abstract_inverted_index":{"With":[0],"the":[1,52,73,94],"recent":[2],"widespread":[3],"adoption":[4],"of":[5,27,96,117],"deep":[6],"learning":[7,79],"(DL)":[8],"in":[9],"academia":[10],"and":[11,24,31,60,87,103,122],"industry,":[12],"more":[13],"attention":[14],"are":[15],"attracted":[16],"by":[17],"DL":[18,49],"platform,":[19],"which":[20,71],"can":[21],"support":[22],"research":[23],"development":[25],"(R&D)":[26],"AI":[28],"firms,":[29],"institutes":[30],"universities.":[32],"Towards":[33],"an":[34],"off-the-shelf":[35],"distributed":[36],"GPU":[37],"cluster,":[38],"prior":[39],"work":[40],"propose":[41,67],"prediction-based":[42,53],"schedulers":[43,54],"to":[44],"allocate":[45],"resources":[46],"for":[47],"diverse":[48],"workloads.":[50],"However,":[51],"have":[55],"disadvantages":[56],"on":[57,119],"prediction":[58],"accuracy":[59],"offline-profiling":[61],"costs.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,107],"a":[68,77,115],"learning-based":[69],"scheduler,":[70],"models":[72],"scheduling":[74],"problem":[75],"as":[76,114],"reinforcement":[78],"problem,":[80],"achieving":[81],"minimum":[82],"average":[83],"job":[84],"completion":[85],"time":[86],"maximum":[88],"system":[89],"utilization.":[90],"The":[91],"scheduler":[92,112],"contains":[93],"designs":[95],"state":[97],"space,":[98,100],"action":[99],"reward":[101],"function":[102],"update":[104],"scheme.":[105],"Furthermore,":[106],"will":[108],"evaluate":[109],"our":[110],"proposed":[111],"implemented":[113],"plugin":[116],"Tensorflow":[118],"real":[120],"cluster":[121],"large-scale":[123],"simulation.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}