{"id":"https://openalex.org/W4401567198","doi":"https://doi.org/10.1109/tpds.2024.3443255","title":"Proteus: Simulating the Performance of Distributed DNN Training","display_name":"Proteus: Simulating the Performance of Distributed DNN Training","publication_year":2024,"publication_date":"2024-08-14","ids":{"openalex":"https://openalex.org/W4401567198","doi":"https://doi.org/10.1109/tpds.2024.3443255"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3443255","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3443255","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpds.2024.3443255","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076729908","display_name":"Jiangfei Duan","orcid":"https://orcid.org/0000-0002-6327-2033"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Jiangfei Duan","raw_affiliation_strings":["Department of IE, The Chinese University of Hong Kong, HKSAR, China"],"affiliations":[{"raw_affiliation_string":"Department of IE, The Chinese University of Hong Kong, HKSAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114246744","display_name":"Xiuhong Li","orcid":"https://orcid.org/0000-0002-4896-121X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuhong Li","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analysis and Applications, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analysis and Applications, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108977645","display_name":"Pingrui Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Xu","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102773472","display_name":"Xingcheng Zhang","orcid":"https://orcid.org/0009-0006-8525-0608"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingcheng Zhang","raw_affiliation_strings":["Shanghai AI Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049910854","display_name":"Shengen Yan","orcid":"https://orcid.org/0009-0005-3858-7972"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengen Yan","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["School of EECS, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5076729908"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.745,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85886051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"35","issue":"10","first_page":"1867","last_page":"1878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.963699996471405,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.963699996471405,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.95660001039505,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9399999976158142,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7875783443450928},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6238820552825928},{"id":"https://openalex.org/keywords/proteus","display_name":"Proteus","score":0.5252040028572083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.341426819562912},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33661383390426636},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32272666692733765},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32173967361450195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875783443450928},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6238820552825928},{"id":"https://openalex.org/C2779464495","wikidata":"https://www.wikidata.org/wiki/Q132229","display_name":"Proteus","level":4,"score":0.5252040028572083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.341426819562912},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33661383390426636},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32272666692733765},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32173967361450195},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C547475151","wikidata":"https://www.wikidata.org/wiki/Q25419","display_name":"Escherichia coli","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3443255","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3443255","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tpds.2024.3443255","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3443255","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1579666790","https://openalex.org/W1598866093","https://openalex.org/W1686810756","https://openalex.org/W2018162709","https://openalex.org/W2045271686","https://openalex.org/W2080166316","https://openalex.org/W2105545110","https://openalex.org/W2130336316","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2338908902","https://openalex.org/W2883830791","https://openalex.org/W2946408574","https://openalex.org/W2947737663","https://openalex.org/W2969388332","https://openalex.org/W2973727699","https://openalex.org/W2991040477","https://openalex.org/W3081168214","https://openalex.org/W3101104221","https://openalex.org/W3129831491","https://openalex.org/W3130395060","https://openalex.org/W3132107458","https://openalex.org/W3163465001","https://openalex.org/W3174394143","https://openalex.org/W3175745020","https://openalex.org/W3197525459","https://openalex.org/W3205805162","https://openalex.org/W4367147621","https://openalex.org/W4378470669","https://openalex.org/W4380881128","https://openalex.org/W4385245566","https://openalex.org/W6635810480","https://openalex.org/W6637373629","https://openalex.org/W6684859321","https://openalex.org/W6703652217","https://openalex.org/W6713134421","https://openalex.org/W6744307745","https://openalex.org/W6751349269","https://openalex.org/W6753584990","https://openalex.org/W6763737044","https://openalex.org/W6767997687","https://openalex.org/W6778883912","https://openalex.org/W6781728138","https://openalex.org/W6785429063","https://openalex.org/W6787953186","https://openalex.org/W6790665546","https://openalex.org/W6792247788","https://openalex.org/W6795581714","https://openalex.org/W6799372109","https://openalex.org/W6811928498","https://openalex.org/W6846232141","https://openalex.org/W6852481455"],"related_works":["https://openalex.org/W2419441924","https://openalex.org/W2369533376","https://openalex.org/W2357348897","https://openalex.org/W2235158164","https://openalex.org/W2327805767","https://openalex.org/W4241042207","https://openalex.org/W230091440","https://openalex.org/W2343585654","https://openalex.org/W4306825251","https://openalex.org/W2323047482"],"abstract_inverted_index":{"DNN":[0,30,53],"models":[1,97],"are":[2],"becoming":[3],"increasingly":[4],"larger":[5],"to":[6,28,34,46,68,84,187,196],"achieve":[7],"unprecedented":[8],"accuracy,":[9],"and":[10,15,24,39,59,121,131,176],"the":[11,19,37,41,48,60,80,86,113,123],"accompanying":[12],"increased":[13],"computation":[14],"memory":[16],"requirements":[17],"necessitate":[18],"employment":[20],"of":[21,51,88,160,182],"massive":[22],"clusters":[23],"elaborate":[25],"parallelization":[26,57,90,99,184],"strategies":[27,58,91,100],"accelerate":[29],"training.":[31,54],"In":[32,74],"order":[33,178],"better":[35],"optimize":[36],"performance":[38,72,87],"analyze":[40],"cost,":[42],"it":[43,66,111],"is":[44],"indispensable":[45],"model":[47,85],"training":[49,180],"throughput":[50,181],"distributed":[52,118],"However,":[55],"complex":[56,62,89,98,124],"resulting":[61],"runtime":[63,125],"behaviors":[64],"make":[65],"challenging":[67],"construct":[69],"an":[70],"accurate":[71],"model.":[73],"this":[75],"article,":[76],"we":[77],"present":[78],"Proteus,":[79],"first":[81,96],"standalone":[82],"simulator":[83],"through":[92],"simulation":[93],"execution.":[94],"Proteus":[95,155,170,190],"with":[101,136],"a":[102,117,137,157],"unified":[103],"representation":[104],"named":[105],"<italic":[106,127,132],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107,128,133,139,142,144,147,150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Strategy":[108],"Tree</i>.":[109],"Then,":[110],"compiles":[112],"strategy":[114],"tree":[115],"into":[116],"execution":[119],"graph":[120],"simulates":[122],"behaviors,":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">comp-comm":[129],"overlap</i>":[130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">bandwidth":[134],"sharing</i>,":[135],"<underline":[138,141,146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">H</u>ierarchical":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</u>opo-<underline":[143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</u>ware":[145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">E</u>xecutor":[148],"(<italic":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HTAE</i>).":[151],"We":[152],"finally":[153],"evaluate":[154],"across":[156],"wide":[158],"variety":[159],"DNNs":[161],"on":[162],"three":[163],"hardware":[164],"configurations.":[165],"Experimental":[166],"results":[167],"show":[168],"that":[169],"achieves":[171],"3.0%":[172],"average":[173],"prediction":[174,192],"error":[175,193],"preserves":[177],"for":[179],"various":[183],"strategies.":[185],"Compared":[186],"state-of-the-art":[188],"approaches,":[189],"reduces":[191],"by":[194],"up":[195],"133.8%.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}