{"id":"https://openalex.org/W4321485372","doi":"https://doi.org/10.1145/3539597.3573037","title":"ElasticDL: A Kubernetes-native Deep Learning Framework with Fault-tolerance and Elastic Scheduling","display_name":"ElasticDL: A Kubernetes-native Deep Learning Framework with Fault-tolerance and Elastic Scheduling","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321485372","doi":"https://doi.org/10.1145/3539597.3573037"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3573037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3573037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","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/A5045140292","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0001-6033-6102"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Zhejiang University & Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University & Ant Group, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049402797","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0003-1228-5843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101854975","display_name":"Feng Zhu","orcid":"https://orcid.org/0000-0003-4200-0423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Zhu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068305259","display_name":"Qitao Shi","orcid":"https://orcid.org/0000-0001-5893-8761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qitao Shi","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027030871","display_name":"Wenjing Fang","orcid":"https://orcid.org/0000-0001-9795-4158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjing Fang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031027452","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0002-9594-3989"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080633144","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0001-9011-9758"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5045140292"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":3.6851,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93526949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1148","last_page":"1151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9951000213623047,"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/T12127","display_name":"Software System Performance and Reliability","score":0.991599977016449,"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/scalability","display_name":"Scalability","score":0.8098403215408325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7882686853408813},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7599479556083679},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7530160546302795},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.622330904006958},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5261616110801697},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5246524810791016},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5117151737213135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4331413507461548},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.15430331230163574},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14294815063476562},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07499825954437256}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8098403215408325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882686853408813},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7599479556083679},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7530160546302795},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.622330904006958},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5261616110801697},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5246524810791016},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5117151737213135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4331413507461548},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.15430331230163574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14294815063476562},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07499825954437256},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3573037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3573037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","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":9,"referenced_works":["https://openalex.org/W2071965227","https://openalex.org/W2475334473","https://openalex.org/W2745107842","https://openalex.org/W2772043392","https://openalex.org/W2793768763","https://openalex.org/W3037519745","https://openalex.org/W3044261734","https://openalex.org/W3104030692","https://openalex.org/W6779740189"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2064720525","https://openalex.org/W2111125783"],"abstract_inverted_index":{"The":[0],"power":[1,57],"of":[2,18,37,58,90,112],"artificial":[3],"intelligence":[4],"(AI)":[5],"models":[6,24,50],"originates":[7],"with":[8,70],"sophisticated":[9],"model":[10],"architecture":[11],"as":[12,14],"well":[13],"the":[15,19,38,43,56,85],"sheer":[16],"size":[17],"model.":[20],"These":[21],"large-scale":[22,49],"AI":[23],"impose":[25],"new":[26],"and":[27,34,76,88,110,120],"challenging":[28],"system":[29],"requirements":[30],"regarding":[31],"scalability,":[32,72,86],"reliability,":[33],"flexibility.":[35],"One":[36],"most":[39],"promising":[40],"solutions":[41],"in":[42],"industry":[44],"is":[45,63],"to":[46,65,116],"train":[47],"these":[48],"on":[51],"distributed":[52,60],"deep-learning":[53],"frameworks.":[54],"With":[55],"all":[59],"computations,":[61],"it":[62],"desired":[64],"achieve":[66],"a":[67],"training":[68],"process":[69],"excellent":[71],"elastic":[73,122],"scheduling":[74,123],"(flexibility),":[75],"fault":[77,118],"tolerance":[78,119],"(reliability).":[79],"In":[80],"this":[81],"paper,":[82],"we":[83],"demonstrate":[84],"flexibility,":[87],"reliability":[89],"our":[91],"open-source":[92,102],"Elastic":[93],"Deep":[94],"Learning":[95],"(ElasticDL)":[96],"framework.":[97],"Our":[98],"ElasticDL":[99],"utilizes":[100],"an":[101],"system,":[103],"i.e.,":[104],"Kubernetes,":[105],"for":[106,124],"automating":[107],"deployment,":[108],"scaling,":[109],"management":[111],"containerized":[113],"application":[114],"features":[115],"provide":[117],"support":[121],"DL":[125],"tasks.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}