{"id":"https://openalex.org/W7133361790","doi":"https://doi.org/10.1109/dsaa65442.2025.11416804","title":"Efficient and Automatic 3D Parallelism Strategies Search via Contrastive Reinforcement Learning Pretrained Neural Networks","display_name":"Efficient and Automatic 3D Parallelism Strategies Search via Contrastive Reinforcement Learning Pretrained Neural Networks","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W7133361790","doi":"https://doi.org/10.1109/dsaa65442.2025.11416804"},"language":null,"primary_location":{"id":"doi:10.1109/dsaa65442.2025.11416804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa65442.2025.11416804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)","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/A5102606462","display_name":"Jie Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Ou","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127966528","display_name":"Xiaowang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowang Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033702874","display_name":"Yueming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueming Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128010192","display_name":"Jiahong Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiahong Qian","raw_affiliation_strings":["Huawei Technologies Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127881989","display_name":"Teng Su","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Teng Su","raw_affiliation_strings":["Huawei Technologies Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127917208","display_name":"Wenhong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhong Tian","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.2985000014305115,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.2985000014305115,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07689999788999557,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.050200000405311584,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6406000256538391},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6331999897956848},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5842000246047974},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5756000280380249},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5611000061035156},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4153999984264374},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.3772999942302704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478000283241272},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6406000256538391},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5648000240325928},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa65442.2025.11416804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa65442.2025.11416804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326670","display_name":"Chengdu Science and Technology Bureau","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2339765813","https://openalex.org/W2612076670","https://openalex.org/W2969388332","https://openalex.org/W2991040477","https://openalex.org/W3081168214","https://openalex.org/W3129831491","https://openalex.org/W3132107458","https://openalex.org/W3175937250","https://openalex.org/W3193907509","https://openalex.org/W4229801112","https://openalex.org/W4230563027","https://openalex.org/W4285294723","https://openalex.org/W4307068480","https://openalex.org/W4385245566","https://openalex.org/W4385571616","https://openalex.org/W4416310693","https://openalex.org/W7133212984"],"related_works":[],"abstract_inverted_index":{"As":[0],"deep":[1,47],"learning":[2,48],"models":[3],"grow":[4],"in":[5,94],"complexity":[6],"and":[7,18,50,84,145],"parameter,":[8],"many":[9],"researchers":[10],"have":[11],"attracted":[12],"their":[13],"attention":[14],"to":[15,32,45,101,114,135],"distributed":[16],"training":[17,98],"hybrid":[19],"parallel":[20,178],"strategies.":[21,104],"However,":[22],"current":[23],"methods":[24],"are":[25],"often":[26],"based":[27,78,167],"on":[28,79,168,195],"dynamic":[29],"programming,":[30],"leading":[31],"a":[33,40,80,85,91,106,116,164],"large":[34],"time":[35,55],"cost.":[36],"There":[37],"exist":[38],"only":[39],"limited":[41],"number":[42],"of":[43,159,174,177],"approaches":[44,52],"exploring":[46],"techniques,":[49],"these":[51],"demand":[53],"considerable":[54],"for":[56,120,141],"online":[57],"training.":[58],"In":[59,150,172],"this":[60],"paper,":[61],"we":[62],"develop":[63],"the":[64,97,139,169,175,184],"Automatic":[65],"3D":[66],"Parallelism":[67],"Strategies":[68],"Search":[69],"(APSS),":[70],"which":[71],"is":[72,112],"an":[73,126,157],"efficient":[74],"strategy":[75],"search":[76,151],"algorithm":[77],"pre-trained":[81],"neural":[82],"network":[83],"heuristic":[86,92],"policy.":[87],"APSS":[88,124,153,180],"initially":[89],"employs":[90],"policy":[93],"conjunction":[95],"with":[96],"cluster":[99],"environment":[100],"derive":[102],"candidate":[103,122],"Subsequently,":[105],"Deep":[107],"Pipeline":[108],"Strategy":[109],"Network":[110],"(DPSN)":[111],"proposed":[113],"provide":[115],"detailed":[117],"pipeline":[118],"partition":[119],"each":[121],"strategy.":[123,186],"utilizes":[125],"offline":[127],"pre-training":[128],"method":[129],"called":[130],"Contrastive":[131],"Reinforcement":[132],"Learning":[133],"(CRL)":[134],"pre-train":[136],"DPSN,":[137],"eliminating":[138],"need":[140],"real":[142],"data":[143],"collection":[144],"fine-tuning":[146],"during":[147],"subsequent":[148],"application.":[149],"speed,":[152],"achieves":[154],"enhancements":[155],"by":[156],"order":[158],"magnitude":[160],"faster":[161],"than":[162],"AMP,":[163],"prominent":[165],"framework":[166],"open-source":[170],"DeepSpeed.":[171],"terms":[173],"quality":[176],"strategies,":[179],"can":[181],"still":[182],"identify":[183],"optimal":[185],"The":[187],"source":[188],"code":[189],"will":[190],"be":[191],"made":[192],"publicly":[193],"available":[194],"GitHub<sup":[196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-04T00:00:00"}