{"id":"https://openalex.org/W4401871039","doi":"https://doi.org/10.1109/access.2024.3446770","title":"Optimizing Multi-Level Checkpointing for Distributed Deep Learning Workloads on Cloud Spot VM Clusters","display_name":"Optimizing Multi-Level Checkpointing for Distributed Deep Learning Workloads on Cloud Spot VM Clusters","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401871039","doi":"https://doi.org/10.1109/access.2024.3446770"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3446770","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3446770","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3446770","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025074099","display_name":"Yonghyeon Cho","orcid":"https://orcid.org/0009-0002-1000-0162"},"institutions":[{"id":"https://openalex.org/I4210131320","display_name":"LG (South Korea)","ror":"https://ror.org/03ddh2c27","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210131320"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yonghyeon Cho","raw_affiliation_strings":["webOS SW Development Group, LG Electronics, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"webOS SW Development Group, LG Electronics, Seoul, South Korea","institution_ids":["https://openalex.org/I4210131320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030558417","display_name":"Yoochan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoochan Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353407","display_name":"Kihyun Kim","orcid":"https://orcid.org/0009-0002-8424-002X"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kihyun Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434592","display_name":"Jinwoo Kim","orcid":"https://orcid.org/0000-0002-1437-2206"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinwoo Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111301260","display_name":"Hong-Yeon Kim","orcid":"https://orcid.org/0000-0003-0452-6336"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Yeon Kim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458491","display_name":"Youngjae Kim","orcid":"https://orcid.org/0000-0001-8786-3850"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjae Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025074099"],"corresponding_institution_ids":["https://openalex.org/I4210131320"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.1177,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.92896696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"116891","last_page":"116904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9965999722480774,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9886999726295471,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8435736894607544},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7635964155197144},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4784312844276428},{"id":"https://openalex.org/keywords/hot-spot","display_name":"Hot spot (computer programming)","score":0.45151638984680176},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33891552686691284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435736894607544},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7635964155197144},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4784312844276428},{"id":"https://openalex.org/C199672914","wikidata":"https://www.wikidata.org/wiki/Q4241353","display_name":"Hot spot (computer programming)","level":2,"score":0.45151638984680176},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33891552686691284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3446770","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3446770","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:370e5d65483447189aec74b4ec22de47","is_oa":true,"landing_page_url":"https://doaj.org/article/370e5d65483447189aec74b4ec22de47","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 116891-116904 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3446770","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3446770","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1984564341","https://openalex.org/W2050991960","https://openalex.org/W2128577831","https://openalex.org/W2761777887","https://openalex.org/W2961595369","https://openalex.org/W2991040477","https://openalex.org/W3020605687","https://openalex.org/W3021124033","https://openalex.org/W3036703963","https://openalex.org/W3042975239","https://openalex.org/W3046229946","https://openalex.org/W3086105743","https://openalex.org/W3125012172","https://openalex.org/W3153450967","https://openalex.org/W4214854835","https://openalex.org/W4301239768","https://openalex.org/W4311546745","https://openalex.org/W4385423885","https://openalex.org/W6748645090","https://openalex.org/W6777129363","https://openalex.org/W6787673396","https://openalex.org/W6794474486","https://openalex.org/W6801603025"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4244478748","https://openalex.org/W4304092003","https://openalex.org/W2379142291","https://openalex.org/W2056851929","https://openalex.org/W3150465815","https://openalex.org/W4223488648","https://openalex.org/W2252731128"],"abstract_inverted_index":{"Spot":[0,28],"Virtual":[1],"Machines":[2],"(Spot":[3],"VMs)":[4],"offer":[5],"access":[6],"to":[7,16,94,123,197,208],"underutilized":[8],"computing":[9,102],"resources":[10],"at":[11],"significant":[12],"discounts,":[13],"sometimes":[14],"up":[15],"90%":[17],"off":[18],"regular":[19],"on-demand":[20,101,131],"pricing.":[21],"For":[22],"budget-conscious":[23],"organizations,":[24],"using":[25,75,173],"clusters":[26],"of":[27,45,60,98,130,218],"VMs":[29],"is":[30,93],"an":[31],"effective":[32],"strategy":[33],"for":[34,79,104],"training":[35,112,150],"large-scale":[36],"distributed":[37,175],"deep":[38],"learning":[39],"(DDL)":[40],"models.":[41,223],"However,":[42],"the":[43,58,96,128,149,216],"risk":[44],"preemption":[46],"by":[47],"cloud":[48],"providers":[49],"poses":[50],"a":[51,99,119,209],"challenge,":[52],"as":[53],"it":[54],"can":[55,86],"result":[56],"in":[57,63,127],"loss":[59],"unsaved":[61],"data":[62,109,157,168],"memory":[64,97,129,145],"and":[65,162,170,200],"local":[66],"storage.":[67],"To":[68],"mitigate":[69],"this":[70,115],"risk,":[71],"one":[72],"solution":[73],"involves":[74],"networked":[76],"storage":[77],"systems":[78],"checkpoints,":[80],"though":[81],"their":[82],"low":[83],"write":[84],"throughput":[85],"slow":[87],"down":[88],"training.":[89,135],"An":[90],"alternative":[91],"approach":[92],"use":[95],"remote,":[100],"node":[103],"temporary":[105,125],"checkpoint":[106,156],"storage,":[107],"balancing":[108],"protection":[110],"with":[111],"efficiency.":[113],"In":[114],"paper,":[116],"we":[117],"propose":[118],"novel":[120],"approach,":[121],"ACUTE,":[122],"optimize":[124],"checkpointing":[126,184,206,212],"nodes":[132],"during":[133],"DDL":[134],"ACUTE":[136,178,193],"includes":[137],"three":[138],"key":[139],"optimizations:":[140],"1)":[141],"Check-Mem,":[142],"which":[143,154,165],"reduces":[144,194],"copying":[146],"overhead":[147],"on":[148,186,202],"node;":[151],"2)":[152],"Check-Trans,":[153],"accelerates":[155],"transfer":[158],"through":[159],"parallel":[160],"processing;":[161],"3)":[163],"Check-Pack,":[164],"eliminates":[166],"unnecessary":[167],"unpacking":[169],"repacking.":[171],"Implemented":[172],"PyTorch\u2019s":[174],"data-parallel":[176],"library,":[177],"was":[179],"evaluated":[180],"against":[181],"two":[182],"other":[183],"schemes":[185],"AWS":[187],"VM":[188],"instances.":[189],"Results":[190],"show":[191],"that":[192],"makespan":[195],"delay":[196],"nearly":[198],"zero":[199],"achieves,":[201],"average,":[203],"43.30%":[204],"faster":[205],"compared":[207],"baseline":[210],"multi-level":[211],"scheme,":[213],"without":[214],"compromising":[215],"precision":[217],"Deep":[219],"Neural":[220],"Network":[221],"(DNN)":[222]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}