{"id":"https://openalex.org/W4416582772","doi":"https://doi.org/10.1109/tpds.2025.3636547","title":"cuFastTuckerPlusTC: A Stochastic Parallel Sparse FastTucker Decomposition Using GPU Tensor Cores","display_name":"cuFastTuckerPlusTC: A Stochastic Parallel Sparse FastTucker Decomposition Using GPU Tensor Cores","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416582772","doi":"https://doi.org/10.1109/tpds.2025.3636547"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2025.3636547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3636547","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":null,"display_name":"Zixuan Li","orcid":"https://orcid.org/0000-0003-4735-794X"},"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"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":["School of Computer Science & School of Cyberspace Science, Xiangtan University, Xiangtan, Hunan, China","College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0003-4735-794X","affiliations":[{"raw_affiliation_string":"School of Computer Science & School of Cyberspace Science, Xiangtan University, Xiangtan, Hunan, China","institution_ids":["https://openalex.org/I4610292","https://openalex.org/I121296143"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090246160","display_name":"Mingxing Duan","orcid":"https://orcid.org/0000-0002-1049-6244"},"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":"Mingxing Duan","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0002-1049-6244","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082012083","display_name":"Huizhang Luo","orcid":"https://orcid.org/0000-0003-2392-0267"},"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":"Huizhang Luo","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0003-2392-0267","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016247312","display_name":"Wangdong Yang","orcid":"https://orcid.org/0000-0003-2681-7898"},"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":"Wangdong Yang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0003-2681-7898","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"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":"Kenli Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0002-2635-7716","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087894632","display_name":"Keqin Li","orcid":"https://orcid.org/0000-0001-5224-4048"},"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":"Keqin Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0001-5224-4048","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32173913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"2","first_page":"443","last_page":"458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9462000131607056,"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":0.9462000131607056,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.01510000042617321,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.01489999983459711,"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/overhead","display_name":"Overhead (engineering)","score":0.5687999725341797},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5552999973297119},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.527999997138977},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5162000060081482},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4717999994754791},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4359000027179718},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4246000051498413},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"Tensor decomposition","score":0.414900004863739},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.35989999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753000020980835},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.414900004863739},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.35760000348091125},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C2778258933","wikidata":"https://www.wikidata.org/wiki/Q16918986","display_name":"Decomposition method (queueing theory)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C42704193","wikidata":"https://www.wikidata.org/wiki/Q7851097","display_name":"Tucker decomposition","level":4,"score":0.29829999804496765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3636547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3636547","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/G5363641303","display_name":null,"funder_award_id":"62422205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5540616889","display_name":null,"funder_award_id":"62272149","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6120332863","display_name":null,"funder_award_id":"U21A20461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6396121924","display_name":null,"funder_award_id":"62227808","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7200312309","display_name":null,"funder_award_id":"2025JJ60399","funder_id":"https://openalex.org/F4320322866","funder_display_name":"Natural Science Foundation of Hainan Province"},{"id":"https://openalex.org/G8519096021","display_name":null,"funder_award_id":"U24A20255","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8946784670","display_name":null,"funder_award_id":"62321003","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/F4320322866","display_name":"Natural Science Foundation of Hainan Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1512387364","https://openalex.org/W1968154520","https://openalex.org/W2013912476","https://openalex.org/W2018282388","https://openalex.org/W2024165284","https://openalex.org/W2025603201","https://openalex.org/W2061873838","https://openalex.org/W2538515886","https://openalex.org/W2546420264","https://openalex.org/W2761307742","https://openalex.org/W2893359107","https://openalex.org/W2909294622","https://openalex.org/W2918546954","https://openalex.org/W2927180808","https://openalex.org/W2936732054","https://openalex.org/W2950894652","https://openalex.org/W2971196067","https://openalex.org/W2971508019","https://openalex.org/W2980186997","https://openalex.org/W3010217868","https://openalex.org/W3034401198","https://openalex.org/W3034986667","https://openalex.org/W3091170309","https://openalex.org/W3113619479","https://openalex.org/W3115793066","https://openalex.org/W3117765988","https://openalex.org/W3134909912","https://openalex.org/W3152937310","https://openalex.org/W3176915718","https://openalex.org/W3198851774","https://openalex.org/W3204376621","https://openalex.org/W3205226039","https://openalex.org/W4210296929","https://openalex.org/W4210473236","https://openalex.org/W4285160918","https://openalex.org/W4391879330","https://openalex.org/W4396514605"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"tensors":[1,20],"are":[2],"prevalent":[3],"in":[4,179,188],"real-world":[5],"applications,":[6],"often":[7],"characterized":[8],"by":[9],"their":[10],"large-scale,":[11],"high-order,":[12],"and":[13,28,124,158,182],"high":[14],"dimensional":[15],"nature.":[16],"Directly":[17],"handling":[18],"raw":[19],"is":[21,48],"impractical":[22],"due":[23],"to":[24,71,79,98,176,185],"the":[25,40,49,62,110,115,129,147,162,170],"significant":[26],"memory":[27,155],"computational":[29,159],"overhead":[30,157],"involved.":[31],"The":[32],"current":[33],"mainstream":[34],"approach":[35],"involves":[36],"compressing":[37],"or":[38],"decomposing":[39],"original":[41,63,116],"tensor.":[42],"One":[43],"popular":[44],"tensor":[45,84,150],"decomposition":[46,59,85],"algorithm":[47,141,153],"Tucker":[50,58],"decomposition.":[51],"However,":[52],"existing":[53],"state-of-the-art":[54,163,194],"algorithms":[55,77,94],"for":[56,143],"large-scale":[57],"typically":[60],"relax":[61],"optimization":[64,69,89,117,122],"problem":[65,118],"into":[66,119],"multiple":[67],"convex":[68],"problems":[70,123],"ensure":[72],"polynomial":[73],"convergence.":[74],"Unfortunately,":[75],"these":[76],"tend":[78],"converge":[80],"slowly.":[81],"In":[82,105],"contrast,":[83],"exhibits":[86],"a":[87,99,138,174,183],"simple":[88],"landscape,":[90],"making":[91],"local":[92],"search":[93],"capable":[95],"of":[96,149],"converging":[97],"global":[100],"(approximate)":[101],"optimum":[102],"much":[103],"faster.":[104],"this":[106],"paper,":[107],"we":[108,135],"propose":[109],"FastTuckerPlus":[111],"algorithm,":[112],"which":[113],"decomposes":[114],"two":[120],"non-convex":[121],"solves":[125],"them":[126],"alternately":[127],"using":[128],"Stochastic":[130],"Gradient":[131],"Descent":[132],"method.":[133],"Furthermore,":[134],"introduce":[136],"cuFastTuckerPlusTC,":[137],"fine-grained":[139],"parallel":[140],"designed":[142],"GPU":[144],"platforms,":[145],"leveraging":[146],"performance":[148],"cores.":[151],"This":[152],"minimizes":[154],"access":[156],"costs,":[160],"surpassing":[161],"algorithms.":[164,195],"Our":[165],"experimental":[166],"results":[167],"demonstrate":[168],"that":[169],"proposed":[171],"method":[172],"achieves":[173],"2\u00d7":[175],"8\u00d7":[177],"improvement":[178,187],"convergence":[180],"speed":[181,191],"3\u00d7":[184],"5\u00d7":[186],"per-iteration":[189],"execution":[190],"compared":[192],"with":[193]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-25T00:00:00"}