{"id":"https://openalex.org/W7084138495","doi":"https://doi.org/10.1109/infocom55648.2025.11044761","title":"Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters","display_name":"Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W7084138495","doi":"https://doi.org/10.1109/infocom55648.2025.11044761"},"language":"en","primary_location":{"id":"doi:10.1109/infocom55648.2025.11044761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer 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":null,"display_name":"Ziyue Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyue Luo","raw_affiliation_strings":["The Ohio State University,Dept. of ECE,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Dept. of ECE,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["The Ohio State University,Dept. of ECE,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Dept. of ECE,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Myungjin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I2801562743","display_name":"Cisco College","ror":"https://ror.org/03gc7jk79","country_code":"US","type":"education","lineage":["https://openalex.org/I2801562743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Myungjin Lee","raw_affiliation_strings":["Cisco Research,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cisco Research,USA","institution_ids":["https://openalex.org/I2801562743"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ness B. Shroff","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ness B. Shroff","raw_affiliation_strings":["The Ohio State University,Dept. of ECE,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Dept. of ECE,USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10367","display_name":"Agricultural Innovations and Practices","score":0.4036000072956085,"subfield":{"id":"https://openalex.org/subfields/1100","display_name":"General Agricultural and Biological Sciences"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10367","display_name":"Agricultural Innovations and Practices","score":0.4036000072956085,"subfield":{"id":"https://openalex.org/subfields/1100","display_name":"General Agricultural and Biological Sciences"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10357","display_name":"Efficiency Analysis Using DEA","score":0.33660000562667847,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13899","display_name":"Agricultural Systems and Practices","score":0.0333000011742115,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6341999769210815},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.628600001335144},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5814999938011169},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.519599974155426},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.5051000118255615},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.49160000681877136},{"id":"https://openalex.org/keywords/rate-monotonic-scheduling","display_name":"Rate-monotonic scheduling","score":0.4648999869823456},{"id":"https://openalex.org/keywords/two-level-scheduling","display_name":"Two-level scheduling","score":0.4609000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248999714851379},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.617900013923645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.519599974155426},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.5051000118255615},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C127456818","wikidata":"https://www.wikidata.org/wiki/Q238879","display_name":"Rate-monotonic scheduling","level":4,"score":0.4648999869823456},{"id":"https://openalex.org/C119948110","wikidata":"https://www.wikidata.org/wiki/Q7858726","display_name":"Two-level scheduling","level":4,"score":0.4609000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4586000144481659},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.42730000615119934},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C112866106","wikidata":"https://www.wikidata.org/wiki/Q267053","display_name":"Lottery scheduling","level":5,"score":0.38510000705718994},{"id":"https://openalex.org/C158336966","wikidata":"https://www.wikidata.org/wiki/Q3074426","display_name":"Flow shop scheduling","level":4,"score":0.37860000133514404},{"id":"https://openalex.org/C175893541","wikidata":"https://www.wikidata.org/wiki/Q1196582","display_name":"Round-robin scheduling","level":4,"score":0.3547999858856201},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C122141398","wikidata":"https://www.wikidata.org/wiki/Q5456330","display_name":"Fixed-priority pre-emptive scheduling","level":5,"score":0.3176000118255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3084999918937683},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2809000015258789}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom55648.2025.11044761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3745309820","display_name":null,"funder_award_id":"N00014-24-1-2729","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4596052697","display_name":null,"funder_award_id":"PGSC-SC-111374-19s","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G5008084248","display_name":null,"funder_award_id":"W911NF-23-2-0225","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G6106237951","display_name":null,"funder_award_id":"W911NF-21-1-0244,W911NF-24-2-0205","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G744435899","display_name":null,"funder_award_id":"CAREER CNS-2110259,IIS-2324052","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"recent":[1],"explosive":[2],"growth":[3],"of":[4],"deep":[5,20],"learning":[6,21],"(DL)":[7],"models":[8,69],"has":[9],"necessitated":[10],"a":[11,39,60,97,114,122,131,143],"compelling":[12],"need":[13],"for":[14,18,133],"efficient":[15],"job":[16,58,135],"scheduling":[17,37,43,111,136,147],"distributed":[19,73],"training":[22,74,104],"with":[23,51],"mixed":[24],"parallelisms":[25],"(DDLwMP)":[26],"in":[27],"GPU":[28,139],"clusters.":[29],"This":[30,126],"paper":[31],"proposes":[32],"an":[33],"adaptive":[34],"shortest-remaining-processing-time-first":[35],"(A-SRPT)":[36],"algorithm,":[38],"novel":[40],"prediction-assisted":[41],"online":[42],"approach":[44],"designed":[45],"to":[46,63,80,102,142,157],"mitigate":[47],"the":[48,81,109,138],"challenges":[49],"associated":[50,72],"DL":[52],"cluster":[53],"scheduling.":[54],"By":[55],"modeling":[56],"each":[57],"as":[59,130],"graph":[61],"corresponding":[62],"heterogeneous":[64],"Deep":[65],"Neural":[66],"Network":[67],"(DNN)":[68],"and":[70,154],"their":[71],"configurations,":[75],"A-SRPT":[76,95,107],"strategically":[77],"assigns":[78],"jobs":[79,93],"available":[82],"GPUs,":[83],"thereby":[84],"minimizing":[85],"inter-server":[86],"communication":[87],"overhead.":[88],"Observing":[89],"that":[90],"most":[91],"DDLwMP":[92],"recur,":[94],"incorporates":[96],"random":[98],"forest":[99],"regression":[100],"model":[101],"predict":[103],"iterations.":[105],"Crucially,":[106],"maps":[108],"complex":[110],"problem":[112],"into":[113],"single-machine":[115],"instance,":[116],"which":[117],"is":[118],"addressed":[119],"optimally":[120],"by":[121],"preemptive":[123],"\u201cshortest-remaining-processing-time-first\u201d":[124],"strategy.":[125],"optimized":[127],"solution":[128],"serves":[129],"guide":[132],"actual":[134],"within":[137],"clusters,":[140],"leading":[141],"theoretically":[144],"provable":[145],"competitive":[146],"efficiency.":[148],"We":[149],"conduct":[150],"extensive":[151],"real-world":[152],"testbed":[153],"simulation":[155],"experiments":[156],"verify":[158],"our":[159],"proposed":[160],"algorithms.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}