{"id":"https://openalex.org/W4402048480","doi":"https://doi.org/10.1145/3625549.3658658","title":"ETS: Deep Learning Training Iteration Time Prediction based on Execution Trace Sliding Window","display_name":"ETS: Deep Learning Training Iteration Time Prediction based on Execution Trace Sliding Window","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4402048480","doi":"https://doi.org/10.1145/3625549.3658658"},"language":"en","primary_location":{"id":"doi:10.1145/3625549.3658658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658658","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1145/3625549.3658658","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101461003","display_name":"Zichao Yang","orcid":"https://orcid.org/0000-0003-0699-394X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zichao Yang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101074209","display_name":"Hao Guo","orcid":"https://orcid.org/0009-0006-9665-5520"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Guo","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709659","display_name":"Heng Wu","orcid":"https://orcid.org/0000-0001-7903-5879"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4391767820","display_name":"State Key Laboratory of Computer Science","ror":"https://ror.org/01hsx4r68","country_code":null,"type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818","https://openalex.org/I4391767820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Wu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China","Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences., Beijing, China","Nanjing Institute of Software Technology, Nanjing, China","University of Chinese Academy of Sciences, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences., Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366","https://openalex.org/I4391767820"]},{"raw_affiliation_string":"Nanjing Institute of Software Technology, Nanjing, China","institution_ids":["https://openalex.org/I2799736854","https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Nanjing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017383055","display_name":"Yuewen Wu","orcid":"https://orcid.org/0000-0002-1323-2455"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Wu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052661644","display_name":"Zhong Hua","orcid":"https://orcid.org/0000-0003-3650-1475"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Zhong","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398448","display_name":"Wenbo Zhang","orcid":"https://orcid.org/0000-0002-0237-5100"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Zhang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China","Nanjing Institute of Software Technology, Nanjing, China","University of Chinese Academy of Sciences, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Nanjing Institute of Software Technology, Nanjing, China","institution_ids":["https://openalex.org/I2799736854","https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Nanjing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045995181","display_name":"Chuan Zhou","orcid":"https://orcid.org/0000-0002-9193-281X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Zhou","raw_affiliation_strings":["Minzu University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101202830","display_name":"Yan Liu","orcid":"https://orcid.org/0009-0005-9806-1243"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["Inspur Software Co., Ltd., Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Software Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101461003"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60258134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9825000166893005,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9825000166893005,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9674999713897705,"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/T11122","display_name":"Online Learning and Analytics","score":0.9592000246047974,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.7689018249511719},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.7575567960739136},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.6638666391372681},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5950461030006409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5566761493682861},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5344011187553406},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5283644199371338},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4030149281024933},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.374938428401947},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09561732411384583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7689018249511719},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.7575567960739136},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6638666391372681},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5950461030006409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5566761493682861},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5344011187553406},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5283644199371338},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4030149281024933},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.374938428401947},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09561732411384583},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625549.3658658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658658","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3625549.3658658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658658","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G7440757308","display_name":null,"funder_award_id":"No.62302489","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2042154985","https://openalex.org/W2097117768","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2240989855","https://openalex.org/W2249475272","https://openalex.org/W2734941459","https://openalex.org/W2766736793","https://openalex.org/W2946408574","https://openalex.org/W2954141573","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963918968","https://openalex.org/W2966284335","https://openalex.org/W2981758446","https://openalex.org/W3022548332","https://openalex.org/W3034429256","https://openalex.org/W3135013702","https://openalex.org/W3138516171","https://openalex.org/W3157306683","https://openalex.org/W3183603480","https://openalex.org/W3197816522","https://openalex.org/W3209503812","https://openalex.org/W4247618872","https://openalex.org/W4281637935","https://openalex.org/W4286300788","https://openalex.org/W4287715829","https://openalex.org/W4308426104","https://openalex.org/W4312443924","https://openalex.org/W4319068657","https://openalex.org/W6786080308"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2109115373","https://openalex.org/W2390901981","https://openalex.org/W2353818951","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W1605879311","https://openalex.org/W3014558862"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"has":[3],"become":[4],"essential":[5],"across":[6],"various":[7],"computer":[8],"science":[9],"domains.":[10],"Accurately":[11],"predicting":[12,167],"iteration":[13,78,169],"time":[14,79,170,183,196],"for":[15,26],"DL":[16,48,58,91,125,134,160,172],"models":[17,92],"in":[18,38,61,133,166],"diverse":[19,55],"cloud":[20],"data":[21],"center":[22],"environments":[23],"is":[24],"critical":[25],"making":[27],"high-quality":[28],"scheduling":[29,190],"decisions.":[30],"Existing":[31],"approaches":[32],"neglect":[33],"the":[34,39,69,117,130,168,185],"sequential":[35,96,114],"features":[36,115,122],"inherent":[37],"runtime":[40,97,118],"execution,":[41],"leading":[42],"to":[43,53,108,142],"issues":[44],"such":[45],"as":[46],"overlooking":[47],"framework":[49,126],"overhead":[50,127],"and":[51,128,151,188],"struggling":[52],"handle":[54],"sizes":[56],"of":[57,68,113,171],"models,":[59,173],"resulting":[60],"either":[62],"low":[63],"accuracy":[64,150],"or":[65],"slow":[66],"convergence":[67,153],"prediction":[70,80,145,178],"model.":[71],"This":[72],"paper":[73],"introduces":[74],"ETS,":[75],"a":[76,94,110,139,144,175,181],"novel":[77,111],"method":[81,141],"utilizing":[82],"execution":[83,98,119],"trace":[84],"sliding":[85,106],"windows.":[86],"Our":[87],"observation":[88],"reveals":[89],"that":[90],"exhibit":[93],"highly":[95],"nature.":[99],"Building":[100],"upon":[101],"this":[102],"insight,":[103],"we":[104,147],"leverage":[105],"windows":[107],"extract":[109],"type":[112],"from":[116],"trace.":[120],"These":[121],"comprehensively":[123],"capture":[124],"address":[129],"diversity":[131],"challenge":[132],"model":[135,161],"sizes.":[136],"By":[137],"combining":[138],"best-practice":[140],"train":[143],"model,":[146],"achieve":[148],"high":[149],"rapid":[152],"simultaneously.":[154],"Experimental":[155],"validation":[156],"on":[157],"over":[158],"14,000":[159],"configurations":[162],"demonstrates":[163],"ETS's":[164],"effectiveness":[165],"achieving":[174],"mere":[176],"5.9%":[177],"error":[179],"with":[180],"training":[182],"at":[184],"10-minute":[186],"level,":[187],"improving":[189],"outcomes":[191],"by":[192,197],"reducing":[193],"job":[194],"completion":[195],"17%.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}