{"id":"https://openalex.org/W4389776490","doi":"https://doi.org/10.1109/tpds.2023.3343570","title":"A Memory-Efficient Hybrid Parallel Framework for Deep Neural Network Training","display_name":"A Memory-Efficient Hybrid Parallel Framework for Deep Neural Network Training","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4389776490","doi":"https://doi.org/10.1109/tpds.2023.3343570"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3343570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3343570","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/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9743-2034","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106623069","display_name":"Shengwei Li","orcid":"https://orcid.org/0000-0002-7419-1511"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwei Li","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7419-1511","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055426388","display_name":"Zhiquan Lai","orcid":"https://orcid.org/0000-0002-3458-4732"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiquan Lai","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3458-4732","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003730869","display_name":"Yongquan Fu","orcid":"https://orcid.org/0000-0002-7564-5239"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongquan Fu","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7564-5239","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114546959","display_name":"Xiangyu Ye","orcid":"https://orcid.org/0009-0008-1285-5176"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Ye","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-1285-5176","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Cai","orcid":"https://orcid.org/0009-0007-6965-2268"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Cai","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0007-6965-2268","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043045076","display_name":"Linbo Qiao","orcid":"https://orcid.org/0000-0002-8285-2738"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linbo Qiao","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-8285-2738","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.8509,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7601249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"35","issue":"4","first_page":"577","last_page":"591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8460091352462769},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7457847595214844},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6409789323806763},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5262364745140076},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5221864581108093},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.486467570066452},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4268091320991516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4144250154495239},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4143497943878174},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.41300681233406067},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.25978511571884155},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0838823914527893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8460091352462769},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7457847595214844},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6409789323806763},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5262364745140076},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5221864581108093},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.486467570066452},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4268091320991516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4144250154495239},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4143497943878174},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.41300681233406067},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.25978511571884155},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0838823914527893},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2023.3343570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3343570","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":[],"awards":[{"id":"https://openalex.org/G3606055544","display_name":null,"funder_award_id":"62025208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7291170091","display_name":"\u81ea\u9a71\u52a8\u4e91\u670d\u52a1\u7f51\u72b6\u7f51\u67b6\u6784\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61972409","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1528469369","https://openalex.org/W1598866093","https://openalex.org/W1686810756","https://openalex.org/W1975934607","https://openalex.org/W2083842231","https://openalex.org/W2117539524","https://openalex.org/W2335835108","https://openalex.org/W2338908902","https://openalex.org/W2512971201","https://openalex.org/W2525778437","https://openalex.org/W2622263826","https://openalex.org/W2891017939","https://openalex.org/W2962801832","https://openalex.org/W2963601856","https://openalex.org/W2965658867","https://openalex.org/W2969388332","https://openalex.org/W2969766737","https://openalex.org/W2991040477","https://openalex.org/W2991615366","https://openalex.org/W3081168214","https://openalex.org/W3089631566","https://openalex.org/W3129831491","https://openalex.org/W3132107458","https://openalex.org/W3189259198","https://openalex.org/W3202134982","https://openalex.org/W3205803342","https://openalex.org/W3206832494","https://openalex.org/W4301239768","https://openalex.org/W4312681979","https://openalex.org/W4321466422","https://openalex.org/W4327694855","https://openalex.org/W4327909439","https://openalex.org/W6614148910","https://openalex.org/W6628377381","https://openalex.org/W6635810480","https://openalex.org/W6637373629","https://openalex.org/W6638533276","https://openalex.org/W6676756733","https://openalex.org/W6679393576","https://openalex.org/W6680402377","https://openalex.org/W6684859321","https://openalex.org/W6703652217","https://openalex.org/W6727690538","https://openalex.org/W6738480291","https://openalex.org/W6739622702","https://openalex.org/W6745458143","https://openalex.org/W6748645090","https://openalex.org/W6753584990","https://openalex.org/W6754187583","https://openalex.org/W6754222578","https://openalex.org/W6766978945","https://openalex.org/W6768723914","https://openalex.org/W6769275798","https://openalex.org/W6778729859","https://openalex.org/W6778883912","https://openalex.org/W6779863968","https://openalex.org/W6784250752","https://openalex.org/W6796414051","https://openalex.org/W6799372109","https://openalex.org/W6811928498"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W2375218795","https://openalex.org/W2078379271","https://openalex.org/W2393010557","https://openalex.org/W2043460294","https://openalex.org/W4210712718","https://openalex.org/W1905398909","https://openalex.org/W2985738161"],"abstract_inverted_index":{"With":[0],"the":[1,15,133,150,160,168,172,179,191],"increasing":[2],"volumes":[3],"of":[4,17,33,126,142,236],"data":[5,48,51,68],"samples":[6],"and":[7,35,58,69,102,124,154,174,193,199,239],"deep":[8],"neural":[9],"network":[10],"(DNN)":[11],"models,":[12,70],"efficiently":[13,84],"scaling":[14,85,217],"training":[16,100,117,181],"DNN":[18,128],"models":[19,87,208],"has":[20],"become":[21],"a":[22,72,114,184,220],"significant":[23],"challenge":[24],"for":[25,75],"server":[26],"clusters":[27],"with":[28,202],"AI":[29],"accelerators":[30],"in":[31,83],"terms":[32],"memory":[34,96,122,155,237],"computing":[36,90],"efficiency.":[37],"Existing":[38],"parallelism":[39,49,54,61],"schemes":[40],"can":[41],"be":[42],"broadly":[43],"classified":[44],"into":[45],"three":[46],"categories:":[47],"(splitting":[50,55,62],"samples),":[52],"model":[53,56,60,63,180],"parameters),":[57],"pipeline":[59,169,197],"layers).":[64],"Hybrid":[65],"approaches":[66],"split":[67],"offering":[71],"comprehensive":[73],"solution":[74],"parallel":[76,116,187],"training.":[77,129],"However,":[78],"these":[79],"methods":[80],"encounter":[81],"limitations":[82],"larger":[86],"across":[88],"more":[89,136],"nodes,":[91],"as":[92],"they":[93],"incur":[94],"substantial":[95],"constraints":[97],"that":[98,189,210],"affect":[99],"efficiency":[101,123,218],"overall":[103],"throughput.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108,138,165,177],"propose":[109,139],"<italic":[110,143,211,224],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[111,144,212,225],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HIPPIE</i>":[112,213,226],",":[113],"hybrid":[115,186],"framework":[118],"designed":[119],"to":[120,131,148,170,231],"enhance":[121],"scalability":[125,194],"large":[127],"First,":[130],"evaluate":[132],"optimization":[134,163],"effect":[135],"reasonably,":[137],"an":[140],"index":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Memory":[145],"Efficiency</i>":[146],"(ME)":[147],"quantify":[149],"tradeoff":[151],"between":[152],"throughput":[153,173,192,228],"overhead.":[156],"Second,":[157],"driven":[158],"by":[159,195,229],"informed":[161,196],"ME":[162],"objective,":[164],"automatically":[166],"partition":[167],"balance":[171],"memory.":[175],"Third,":[176],"optimize":[178],"process":[182],"via":[183],"novel":[185],"scheduler":[188],"improves":[190],"scheduling":[198,201],"communication":[200],"gradient-hidden":[203],"optimization.":[204],"Experiments":[205],"on":[206,219],"various":[207],"show":[209],"achieves":[214],"above":[215],"90%":[216],"16-GPU":[221],"platform.":[222],"Moreover,":[223],"increases":[227],"up":[230],"80%,":[232],"while":[233],"saving":[234],"57%":[235],"overhead":[238],"achieving":[240],"4.18\u00d7":[241],"memory-efficiency":[242],"improvement.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}