{"id":"https://openalex.org/W4411800252","doi":"https://doi.org/10.1109/ccgrid64434.2025.00038","title":"Deep Learning Training Job Scheduling for Proactive Straggler Reduction","display_name":"Deep Learning Training Job Scheduling for Proactive Straggler Reduction","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4411800252","doi":"https://doi.org/10.1109/ccgrid64434.2025.00038"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid64434.2025.00038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","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/A5064217355","display_name":"Haiying Shen","orcid":"https://orcid.org/0000-0002-7681-6255"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiying Shen","raw_affiliation_strings":["University of Virginia,Department of Computer Science,Charlottesville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of Computer Science,Charlottesville,USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040160093","display_name":"Zeyu Zhang","orcid":"https://orcid.org/0009-0005-7853-6854"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Zhang","raw_affiliation_strings":["University of Virginia,Department of Computer Science,Charlottesville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of Computer Science,Charlottesville,USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":1.9246,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8369325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9966999888420105,"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":0.9966999888420105,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.989799976348877,"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":0.7691954374313354},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.47529661655426025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41024142503738403},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.16863250732421875},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10210350155830383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691954374313354},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.47529661655426025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41024142503738403},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.16863250732421875},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10210350155830383}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccgrid64434.2025.00038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2141563029","https://openalex.org/W2141992894","https://openalex.org/W2336650964","https://openalex.org/W2523412218","https://openalex.org/W2523435939","https://openalex.org/W2546571074","https://openalex.org/W2605643718","https://openalex.org/W2744628735","https://openalex.org/W2798515322","https://openalex.org/W2911382970","https://openalex.org/W2919897868","https://openalex.org/W2920397365","https://openalex.org/W2947829929","https://openalex.org/W2955987961","https://openalex.org/W2962684017","https://openalex.org/W2962725887","https://openalex.org/W2968986602","https://openalex.org/W2969388332","https://openalex.org/W2975712713","https://openalex.org/W2982408761","https://openalex.org/W2982664135","https://openalex.org/W3007523155","https://openalex.org/W3011678990","https://openalex.org/W3022298203","https://openalex.org/W3043715968","https://openalex.org/W3097875570","https://openalex.org/W3124352525","https://openalex.org/W3155611867","https://openalex.org/W3202665973","https://openalex.org/W3204998121","https://openalex.org/W4244924642","https://openalex.org/W4286308424","https://openalex.org/W4288079579","https://openalex.org/W4290991121","https://openalex.org/W4295308339","https://openalex.org/W4295312788","https://openalex.org/W4313640087","https://openalex.org/W4318147387","https://openalex.org/W4318541537","https://openalex.org/W4385731844","https://openalex.org/W4386365401","https://openalex.org/W4387321109","https://openalex.org/W4400410992","https://openalex.org/W4400411193","https://openalex.org/W6684859321","https://openalex.org/W6692846177","https://openalex.org/W6703420464","https://openalex.org/W6732337852","https://openalex.org/W6753124209","https://openalex.org/W6753801579","https://openalex.org/W6756009870","https://openalex.org/W6756718674","https://openalex.org/W6758283263","https://openalex.org/W6759814162","https://openalex.org/W6766978945","https://openalex.org/W6769424276","https://openalex.org/W6779740189","https://openalex.org/W6781728138","https://openalex.org/W6782839094","https://openalex.org/W6784425352","https://openalex.org/W6784871562","https://openalex.org/W6810097121","https://openalex.org/W6811928498","https://openalex.org/W6843221661","https://openalex.org/W6849514112","https://openalex.org/W6850040158","https://openalex.org/W6855921298","https://openalex.org/W6922480057","https://openalex.org/W7067822191"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1,66],"work,":[2],"from":[3],"our":[4,93],"trace-driven":[5],"experimental":[6],"measurements,":[7],"we":[8],"observed":[9],"that":[10,95,152,157,207],"despite":[11],"employing":[12],"homogeneous":[13],"GPUs":[14],"for":[15,75,114,146,195,235],"distributed":[16],"deep":[17],"learning":[18],"(DDL)":[19],"training,":[20],"stragglers":[21,37,85],"persistently":[22],"emerge,":[23],"significantly":[24],"prolonging":[25],"time-to-accuracy":[26],"(TTA)":[27],"and":[28,56,104,109,122,135,154,173,186,216],"squandering":[29],"GPU":[30],"resources.":[31],"Previous":[32],"approaches":[33],"typically":[34],"react":[35],"to":[36,102,131,139,151,155,162,176,199,214,222,225],"as":[38],"they":[39,53],"occur":[40],"or":[41],"are":[42,54],"imminent":[43],"during":[44,86],"execution":[45],"after":[46],"scheduling,":[47],"resulting":[48],"in":[49,83],"training":[50,72],"delays":[51],"before":[52],"addressed":[55],"introducing":[57],"additional":[58],"overhead.":[59],"To":[60],"reduce":[61,200],"the":[62,80,110,141,231],"number":[63],"of":[64,143],"stragglers,":[65],"paper":[67],"introduces":[68],"a":[69,105,115,170,177],"novel":[70],"DDL":[71,97,197],"job":[73,116,188,198],"scheduler":[74],"proactive":[76],"straggler":[77],"reduction":[78],"(STRN),":[79],"first":[81],"effort":[82],"mitigating":[84],"scheduling.":[87,189],"STRN":[88,126,167,190,208],"is":[89],"devised":[90],"based":[91],"on":[92,118],"findings":[94],"various":[96],"jobs":[98,147,158],"exhibit":[99],"distinct":[100],"sensitivities":[101],"straggling":[103,163],"particular":[106],"resource's":[107],"overload,":[108],"optimal":[111,187],"synchronization":[112,193],"strategy":[113],"hinges":[117],"its":[119],"specific":[120],"characteristics":[121],"operational":[123],"environment.":[124],"Thus,":[125],"assesses":[127],"each":[128,132,196],"job's":[129],"sensitivity":[130,150,161],"resource":[133,144,153],"type":[134],"straggling.":[136,166],"It":[137],"aims":[138],"minimize":[140],"likelihood":[142],"overload":[145],"with":[148,159],"higher":[149,160],"ensure":[156],"encounter":[164],"less":[165],"initially":[168],"runs":[169],"heuristic":[171],"method":[172,181],"then":[174],"transitions":[175],"Reinforcement":[178],"Learning":[179],"(RL)-based":[180],"once":[182],"trained,":[183],"facilitating":[184],"expedited":[185],"also":[191],"optimizes":[192],"strategies":[194],"overall":[201],"TTA.":[202],"Trace-driven":[203],"real":[204],"experiments":[205],"demonstrate":[206],"reduces":[209],"average":[210,218],"TTA":[211],"by":[212,220],"up":[213,221],"59%":[215],"enhances":[217],"accuracy":[219],"91%":[223],"compared":[224],"state-of-the-art":[226],"methods.":[227],"We":[228],"have":[229],"made":[230],"source":[232],"code":[233],"available":[234],"distribution.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}