{"id":"https://openalex.org/W4404788297","doi":"https://doi.org/10.1109/tpds.2024.3506588","title":"Joint Dynamic Data and Model Parallelism for Distributed Training of DNNs Over Heterogeneous Infrastructure","display_name":"Joint Dynamic Data and Model Parallelism for Distributed Training of DNNs Over Heterogeneous Infrastructure","publication_year":2024,"publication_date":"2024-11-27","ids":{"openalex":"https://openalex.org/W4404788297","doi":"https://doi.org/10.1109/tpds.2024.3506588"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3506588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3506588","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089450803","display_name":"Zhi Ling","orcid":"https://orcid.org/0009-0006-5022-7256"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhi Ling","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088416755","display_name":"Xiaofeng Jiang","orcid":"https://orcid.org/0000-0001-7595-2397"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Jiang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048357184","display_name":"Xiaobin Tan","orcid":"https://orcid.org/0000-0001-7489-2839"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Tan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047787436","display_name":"Huasen He","orcid":"https://orcid.org/0000-0001-9963-019X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huasen He","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075106826","display_name":"Shiyin Zhu","orcid":"https://orcid.org/0009-0008-5219-0885"},"institutions":[{"id":"https://openalex.org/I4210093776","display_name":"DHC Software (China)","ror":"https://ror.org/00kn8e190","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093776"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Zhu","raw_affiliation_strings":["New H3C Technologies Company, Ltd., Beijing, China","New H3C Technologies Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"New H3C Technologies Company, Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210093776"]},{"raw_affiliation_string":"New H3C Technologies Co., Ltd, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083577000","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-7329-4738"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089450803"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.683,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76877394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"36","issue":"2","first_page":"150","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9036999940872192,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9036999940872192,"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":0.878868818283081},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7220405340194702},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6938464641571045},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5326701402664185},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5166959762573242},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5115860104560852},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.44117286801338196},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.4322354197502136},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41559842228889465},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32933318614959717},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13600704073905945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.878868818283081},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7220405340194702},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6938464641571045},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5326701402664185},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5166959762573242},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5115860104560852},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.44117286801338196},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.4322354197502136},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41559842228889465},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32933318614959717},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13600704073905945},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3506588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3506588","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":null,"license_id":null,"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":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1347616826","display_name":null,"funder_award_id":"62341113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3692048513","display_name":null,"funder_award_id":"62173315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3733970540","display_name":null,"funder_award_id":"2408085MF165","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G4736320777","display_name":null,"funder_award_id":"U23A20275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4835101305","display_name":null,"funder_award_id":"62101525","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7553321691","display_name":null,"funder_award_id":"62201543","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"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2083842231","https://openalex.org/W2137152139","https://openalex.org/W2194775991","https://openalex.org/W2612026221","https://openalex.org/W2786070938","https://openalex.org/W2913400449","https://openalex.org/W2948349252","https://openalex.org/W2960833983","https://openalex.org/W2962684017","https://openalex.org/W2963495533","https://openalex.org/W2967314080","https://openalex.org/W2969388332","https://openalex.org/W2969766737","https://openalex.org/W2982664135","https://openalex.org/W3024862772","https://openalex.org/W3036703963","https://openalex.org/W3090575287","https://openalex.org/W3091864426","https://openalex.org/W3109982791","https://openalex.org/W3132107458","https://openalex.org/W3134069806","https://openalex.org/W3177263144","https://openalex.org/W3188270315","https://openalex.org/W3190730109","https://openalex.org/W4206943884","https://openalex.org/W4206990000","https://openalex.org/W4214940715","https://openalex.org/W4220662349","https://openalex.org/W4224952733","https://openalex.org/W4297902940","https://openalex.org/W4312681979","https://openalex.org/W4312968147","https://openalex.org/W4327694855","https://openalex.org/W4327909439","https://openalex.org/W4364322902","https://openalex.org/W4386076493","https://openalex.org/W4389776490","https://openalex.org/W6679314259","https://openalex.org/W6751238189","https://openalex.org/W6755207826","https://openalex.org/W6756718674","https://openalex.org/W6767997687","https://openalex.org/W6781728138","https://openalex.org/W6810172144","https://openalex.org/W6843133045"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W2468095077","https://openalex.org/W29548032","https://openalex.org/W2593878938","https://openalex.org/W305742777"],"abstract_inverted_index":{"Distributed":[0],"training":[1,45,68,118,180],"of":[2,114,171],"deep":[3],"neural":[4],"networks":[5],"(DNNs)":[6],"suffers":[7],"from":[8],"efficiency":[9,69],"declines":[10],"in":[11,25,32,51,70],"dynamic":[12],"heterogeneous":[13,71],"environments,":[14],"due":[15],"to":[16,65,91,106,151,184],"the":[17,22,37,109,115,169],"resource":[18,39],"wastage":[19],"brought":[20],"by":[21,182],"straggler":[23],"problem":[24,123],"data":[26,75],"parallelism":[27,34],"(DP)":[28],"and":[29,47,77,87,95,98,111,145,158,167],"pipeline":[30],"bubbles":[31],"model":[33,79],"(MP).":[35],"Additionally,":[36],"limited":[38],"availability":[40],"requires":[41],"a":[42,61,100,125,164],"trade-off":[43],"between":[44],"performance":[46,110],"long-term":[48,67,112],"costs,":[49],"particularly":[50],"online":[52,63,116,149],"settings.":[53],"To":[54],"address":[55,152],"these":[56],"challenges,":[57],"this":[58,122],"article":[59],"presents":[60],"novel":[62],"approach":[64],"maximize":[66],"environments":[72],"through":[73],"uneven":[74],"assignment":[76],"communication-aware":[78],"partitioning.":[80],"A":[81],"group-based":[82],"hierarchical":[83],"architecture":[84],"combining":[85],"DP":[86],"MP":[88],"is":[89],"developed":[90],"balance":[92],"discrepant":[93],"computation":[94],"communication":[96],"capabilities,":[97],"offer":[99],"flexible":[101],"parallel":[102],"mechanism.":[103],"In":[104],"order":[105],"jointly":[107],"optimize":[108],"cost":[113],"DL":[117],"process,":[119],"we":[120,138],"formulate":[121],"as":[124],"stochastic":[126,134],"optimization":[127,136],"with":[128],"time-averaged":[129],"constraints.":[130],"By":[131],"utilizing":[132],"Lyapunov\u2019s":[133],"network":[135],"theory,":[137],"decompose":[139],"it":[140],"into":[141],"several":[142],"instantaneous":[143],"sub-optimizations,":[144],"devise":[146],"an":[147],"effective":[148],"solution":[150,173],"them":[153],"based":[154,174],"on":[155,175],"tentative":[156],"searching":[157],"linear":[159],"solving.":[160],"We":[161],"have":[162],"implemented":[163],"prototype":[165],"system":[166],"evaluated":[168],"effectiveness":[170],"our":[172],"realistic":[176],"experiments,":[177],"reducing":[178],"batch":[179],"time":[181],"up":[183],"68.59%":[185],"over":[186],"state-of-the-art":[187],"methods.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
