{"id":"https://openalex.org/W7125971899","doi":"https://doi.org/10.1109/smc58881.2025.11343201","title":"Optimizing Tensor Completion on GPU: Heat Conduction-Based Load Balancing and Shared Memory Acceleration","display_name":"Optimizing Tensor Completion on GPU: Heat Conduction-Based Load Balancing and Shared Memory Acceleration","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125971899","doi":"https://doi.org/10.1109/smc58881.2025.11343201"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5087983681","display_name":"Yie-Ruey Chen","orcid":"https://orcid.org/0000-0001-9700-7361"},"institutions":[{"id":"https://openalex.org/I121296143","display_name":"Hunan University of Science and Technology","ror":"https://ror.org/02m9vrb24","country_code":"CN","type":"education","lineage":["https://openalex.org/I121296143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxiang Chen","raw_affiliation_strings":["Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201"],"affiliations":[{"raw_affiliation_string":"Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201","institution_ids":["https://openalex.org/I121296143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124104199","display_name":"Guotong Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I121296143","display_name":"Hunan University of Science and Technology","ror":"https://ror.org/02m9vrb24","country_code":"CN","type":"education","lineage":["https://openalex.org/I121296143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guotong Yin","raw_affiliation_strings":["Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201"],"affiliations":[{"raw_affiliation_string":"Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201","institution_ids":["https://openalex.org/I121296143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124121042","display_name":"Wei Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I121296143","display_name":"Hunan University of Science and Technology","ror":"https://ror.org/02m9vrb24","country_code":"CN","type":"education","lineage":["https://openalex.org/I121296143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liang","raw_affiliation_strings":["Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201"],"affiliations":[{"raw_affiliation_string":"Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201","institution_ids":["https://openalex.org/I121296143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101095427","display_name":"Xie Kun","orcid":"https://orcid.org/0009-0008-3706-1970"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Xie","raw_affiliation_strings":["Hunan University,School of Information Science and Engineering,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,School of Information Science and Engineering,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102093481","display_name":"Jigang Wen","orcid":"https://orcid.org/0000-0002-7363-881X"},"institutions":[{"id":"https://openalex.org/I121296143","display_name":"Hunan University of Science and Technology","ror":"https://ror.org/02m9vrb24","country_code":"CN","type":"education","lineage":["https://openalex.org/I121296143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jigang Wen","raw_affiliation_strings":["Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201"],"affiliations":[{"raw_affiliation_string":"Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201","institution_ids":["https://openalex.org/I121296143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082396833","display_name":"Jiahong Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I121296143","display_name":"Hunan University of Science and Technology","ror":"https://ror.org/02m9vrb24","country_code":"CN","type":"education","lineage":["https://openalex.org/I121296143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahong Xiao","raw_affiliation_strings":["Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201"],"affiliations":[{"raw_affiliation_string":"Hunan University of Science and Technology,School of Computer Science and Engineering,Xiangtan,China,411201","institution_ids":["https://openalex.org/I121296143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124118954","display_name":"Yuanqiang Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109434","display_name":"Xinyu University","ror":"https://ror.org/021xwcd05","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210109434"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqiang Tang","raw_affiliation_strings":["Xinyu University,School of Information Engineering,Xinyu City"],"affiliations":[{"raw_affiliation_string":"Xinyu University,School of Information Engineering,Xinyu City","institution_ids":["https://openalex.org/I4210109434"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009412288","display_name":"Tianxiong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103530","display_name":"Changsha Central Hospital","ror":"https://ror.org/0132wmv23","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210103530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianxiong Liu","raw_affiliation_strings":["Hunan Aerospace Hospital,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan Aerospace Hospital,Changsha,China","institution_ids":["https://openalex.org/I4210103530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5087983681"],"corresponding_institution_ids":["https://openalex.org/I121296143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7281746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5179","last_page":"5184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.5667999982833862,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.5667999982833862,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.31520000100135803,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.012000000104308128,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/load-balancing","display_name":"Load balancing (electrical power)","score":0.6984999775886536},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5551000237464905},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4616999924182892},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.46070000529289246},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.45329999923706055},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.4246000051498413},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.40799999237060547},{"id":"https://openalex.org/keywords/distributed-shared-memory","display_name":"Distributed shared memory","score":0.3982999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867000102996826},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6984999775886536},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6134999990463257},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5551000237464905},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48080000281333923},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.45329999923706055},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.4246000051498413},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.3982999920845032},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.35569998621940613},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.26600000262260437},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C3019591417","wikidata":"https://www.wikidata.org/wiki/Q575614","display_name":"Load distribution","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1512387364","https://openalex.org/W2024165284","https://openalex.org/W2091449379","https://openalex.org/W2103392911","https://openalex.org/W2149854013","https://openalex.org/W2520604322","https://openalex.org/W2888987473","https://openalex.org/W2919008182","https://openalex.org/W3016430712","https://openalex.org/W3021246226","https://openalex.org/W3088979390","https://openalex.org/W3134387702","https://openalex.org/W3159843227","https://openalex.org/W3168654039","https://openalex.org/W4225144709","https://openalex.org/W4280633999","https://openalex.org/W4327861153","https://openalex.org/W4386570618","https://openalex.org/W4388283607","https://openalex.org/W4403756765","https://openalex.org/W4409074932"],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"tensor":[1,216],"completion":[2],"plays":[3],"a":[4,112,118,125,186,211],"crucial":[5],"role":[6],"in":[7,75],"data":[8,42,197],"analysis":[9],"and":[10,28,51,124,163,173,178,204],"anomaly":[11],"detection,":[12],"with":[13,190],"Alternating":[14],"Least":[15],"Squares":[16],"(ALS)-based":[17],"CANDECOMP/PARAFAC(CP)":[18],"decomposition":[19],"being":[20],"widely":[21],"adopted":[22],"due":[23],"to":[24,48,65],"its":[25],"convergence":[26],"properties":[27],"computational":[29,69,104],"stability.":[30],"However,":[31],"when":[32],"accelerating":[33],"ALS":[34,76,114],"computation":[35],"on":[36,139,184,195],"GPUs,":[37],"load":[38,121,131],"imbalance":[39],"caused":[40],"by":[41],"partitioning":[43,137],"significantly":[44],"affects":[45],"efficiency.":[46],"Due":[47],"the":[49,83,140,153,191,202],"sparsity":[50],"heterogeneity":[52],"of":[53,61,68,91,96,142],"data,":[54],"different":[55],"thread":[56],"blocks":[57],"handle":[58],"varying":[59],"amounts":[60],"non-zero":[62,143],"values,":[63,144],"leading":[64],"suboptimal":[66],"utilization":[67,95],"resources.":[70,151],"Moreover,":[71],"updating":[72],"factor":[73,161],"matrices":[74,162],"involves":[77],"frequent":[78],"global":[79,179],"memory":[80,98,127,155,176,180,205],"accesses,":[81],"where":[82],"latency":[84],"is":[85,99],"100":[86],"times":[87],"higher":[88],"than":[89],"that":[90,116],"shared":[92,97,126,154],"memory.":[93],"Efficient":[94],"therefore":[100],"critical":[101],"for":[102,214],"improving":[103],"performance.":[105],"To":[106],"address":[107],"these":[108],"challenges,":[109],"we":[110],"propose":[111],"GPU-optimized":[113],"framework":[115],"incorporates":[117],"heat":[119],"conduction-based":[120],"balancing":[122,132],"strategy":[123,133],"acceleration":[128,156],"mechanism.":[129],"The":[130],"dynamically":[134],"adjusts":[135],"subtensor":[136],"based":[138],"distribution":[141],"ensuring":[145,200],"balanced":[146],"workload":[147],"allocation":[148],"across":[149],"GPU":[150],"Meanwhile,":[152],"mechanism":[157],"caches":[158],"frequently":[159],"accessed":[160],"employs":[164],"element-wise":[165],"implicit":[166],"computation,":[167],"eliminating":[168],"explicit":[169],"intermediate":[170],"matrix":[171],"storage":[172],"thereby":[174],"reducing":[175],"overhead":[177],"access":[181],"latency.":[182],"Based":[183],"this,":[185],"comparison":[187],"was":[188],"made":[189],"other":[192],"three":[193],"methods":[194],"four":[196],"sets.":[198],"While":[199],"accuracy,":[201],"time":[203],"usage":[206],"were":[207],"greatly":[208],"reduced,":[209],"providing":[210],"practical":[212],"solution":[213],"efficient":[215],"completion.":[217]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}