{"id":"https://openalex.org/W4385329445","doi":"https://doi.org/10.1109/iwqos57198.2023.10188717","title":"spotDNN: Provisioning Spot Instances for Predictable Distributed DNN Training in the Cloud","display_name":"spotDNN: Provisioning Spot Instances for Predictable Distributed DNN Training in the Cloud","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4385329445","doi":"https://doi.org/10.1109/iwqos57198.2023.10188717"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos57198.2023.10188717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos57198.2023.10188717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS)","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/A5039055026","display_name":"Ruitao Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruitao Shang","raw_affiliation_strings":["East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing","Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029626585","display_name":"Fei Xu","orcid":"https://orcid.org/0000-0003-1590-5323"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Xu","raw_affiliation_strings":["East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing","Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112968726","display_name":"Zhuoyan Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyan Bai","raw_affiliation_strings":["East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing","Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379221","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-2300-6996"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["University of Louisiana at Lafayette"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760218","display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0002-0987-9344"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048398271","display_name":"Fangming Liu","orcid":"https://orcid.org/0000-0002-8570-1345"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangming Liu","raw_affiliation_strings":["Huazhong University of Science and Technology,Peng Cheng Laboratory","Peng Cheng Laboratory, Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I47720641"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8556075096130371},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.8509609699249268},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7007898092269897},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6422712206840515},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4626598656177521},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.43596601486206055},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3254937529563904},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23422804474830627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556075096130371},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.8509609699249268},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7007898092269897},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6422712206840515},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4626598656177521},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.43596601486206055},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3254937529563904},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23422804474830627}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos57198.2023.10188717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos57198.2023.10188717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W778657980","https://openalex.org/W1686810756","https://openalex.org/W2127941149","https://openalex.org/W2168231600","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2308884720","https://openalex.org/W2336650964","https://openalex.org/W2605643718","https://openalex.org/W2612026221","https://openalex.org/W2618530766","https://openalex.org/W2798515322","https://openalex.org/W2895019217","https://openalex.org/W2911714797","https://openalex.org/W2953384591","https://openalex.org/W2963149401","https://openalex.org/W2973058717","https://openalex.org/W2987203808","https://openalex.org/W3037994915","https://openalex.org/W3039712636","https://openalex.org/W3096583839","https://openalex.org/W3103694483","https://openalex.org/W3105739685","https://openalex.org/W3115029474","https://openalex.org/W3118608800","https://openalex.org/W3121702752","https://openalex.org/W3131944805","https://openalex.org/W3181228931","https://openalex.org/W3189640247","https://openalex.org/W3204194028","https://openalex.org/W4205614634","https://openalex.org/W4225004481","https://openalex.org/W4250589301","https://openalex.org/W4293715377","https://openalex.org/W4308426784","https://openalex.org/W4311327447","https://openalex.org/W6622473587","https://openalex.org/W6637373629","https://openalex.org/W6679154944","https://openalex.org/W6684859321","https://openalex.org/W6703420464","https://openalex.org/W6713134421","https://openalex.org/W6780000811","https://openalex.org/W6782839094","https://openalex.org/W6787673396","https://openalex.org/W6787972765","https://openalex.org/W6799160286","https://openalex.org/W6801603025"],"related_works":["https://openalex.org/W2017432143","https://openalex.org/W2116677773","https://openalex.org/W1973694374","https://openalex.org/W4244478748","https://openalex.org/W2983574358","https://openalex.org/W2370475531","https://openalex.org/W4385924768","https://openalex.org/W2785227142","https://openalex.org/W572531444","https://openalex.org/W2945962340"],"abstract_inverted_index":{"Distributed":[0],"Deep":[1],"Neural":[2],"Network":[3],"(DDNN)":[4],"training":[5,41,59,102,123,141,172,201],"on":[6,65,189],"cloud":[7],"spot":[8,43,51,92],"instances":[9,52],"is":[10],"increasingly":[11],"compelling":[12],"as":[13,75,77],"it":[14],"can":[15,53,197],"significantly":[16],"save":[17],"the":[18,31,36,66,78,84,104,109,129,139,161,171,205,214],"user":[19],"budget.":[20],"To":[21,82],"handle":[22],"unexpected":[23],"instance":[24,93,156],"revocations,":[25],"provisioning":[26,47,94,157],"a":[27,48,90,147,154,181],"heterogeneous":[28,125,144],"cluster":[29,49,80],"using":[30],"asynchronous":[32],"parallel":[33],"mechanism":[34],"becomes":[35],"dominant":[37],"method":[38],"for":[39,100,111],"DDNN":[40,58,101,122,140,200],"with":[42,218],"instances.":[44],"However,":[45],"blindly":[46],"of":[50,121,183],"easily":[54],"result":[55],"in":[56,103,124,143],"unpre-dictable":[57],"performance,":[60],"mainly":[61],"because":[62],"bottlenecks":[63],"occur":[64],"parameter":[67],"server":[68],"network":[69],"bandwidth":[70,73],"and":[71,134,164,185],"PCIe":[72],"resources,":[74,113],"well":[76],"inadequate":[79],"heterogeneity.":[81],"address":[83],"challenges":[85],"above,":[86],"we":[87,114,151],"propose":[88],"spotDNN,":[89],"heterogeneity-aware":[91],"framework":[95],"that":[96,195],"provides":[97],"predictable":[98,199],"performance":[99,119,173,202],"cloud.":[105],"By":[106],"explicitly":[107],"considering":[108],"contention":[110],"bottle-neck":[112],"first":[115],"build":[116],"an":[117],"analytical":[118],"model":[120],"clusters.":[126,145],"It":[127],"leverages":[128],"weighted":[130],"average":[131],"batch":[132],"size":[133],"convergence":[135],"coefficient":[136],"to":[137,168,210,213],"quantify":[138],"loss":[142],"Through":[146],"lightweight":[148],"workload":[149],"profiling,":[150],"further":[152],"design":[153],"cost-efficient":[155],"strategy":[158],"which":[159],"incorporates":[160],"bounds":[162],"calculation":[163],"sliding":[165],"window":[166],"techniques":[167],"effectively":[169],"guarantee":[170],"service":[174],"level":[175],"objectives":[176],"(SLOs).":[177],"We":[178],"have":[179],"implemented":[180],"prototype":[182],"spotDNN":[184,196],"conducted":[186],"extensive":[187],"experiments":[188],"Amazon":[190],"EC2.":[191],"Experiment":[192],"results":[193],"show":[194],"deliver":[198],"while":[203],"reducing":[204],"monetary":[206],"cost":[207],"by":[208],"up":[209],"68.1%":[211],"compared":[212],"existing":[215],"solutions,":[216],"yet":[217],"acceptable":[219],"runtime":[220],"overhead.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}