{"id":"https://openalex.org/W4386902738","doi":"https://doi.org/10.1109/tpds.2023.3317535","title":"UMA-MF: A Unified Multi-CPU/GPU Asynchronous Computing Framework for SGD-Based Matrix Factorization","display_name":"UMA-MF: A Unified Multi-CPU/GPU Asynchronous Computing Framework for SGD-Based Matrix Factorization","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4386902738","doi":"https://doi.org/10.1109/tpds.2023.3317535"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3317535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3317535","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/A5073756975","display_name":"Yizhi Huang","orcid":"https://orcid.org/0000-0001-8808-7718"},"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":true,"raw_author_name":"Yizhi Huang","raw_affiliation_strings":["Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-8808-7718","affiliations":[{"raw_affiliation_string":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008561380","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-1849-6991"},"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":"Yan Liu","raw_affiliation_strings":["Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-1849-6991","affiliations":[{"raw_affiliation_string":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058927956","display_name":"Yang Bai","orcid":"https://orcid.org/0000-0001-6292-3730"},"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":"Yang Bai","raw_affiliation_strings":["Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-6292-3730","affiliations":[{"raw_affiliation_string":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014354705","display_name":"Si Chen","orcid":"https://orcid.org/0000-0001-9030-3969"},"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":"Si Chen","raw_affiliation_strings":["Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9030-3969","affiliations":[{"raw_affiliation_string":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019444969","display_name":"Renfa Li","orcid":"https://orcid.org/0000-0003-4573-7375"},"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":"Renfa Li","raw_affiliation_strings":["Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-4573-7375","affiliations":[{"raw_affiliation_string":"Key Laboratory for Embedded and Network Computing of Hunan Province, College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073756975"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.5903,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68923536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"34","issue":"11","first_page":"2978","last_page":"2993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9653000235557556,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9569000005722046,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8620803356170654},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7968790531158447},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6057252287864685},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.600054919719696},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5723749995231628},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.41942593455314636},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13436540961265564},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09850668907165527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620803356170654},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7968790531158447},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6057252287864685},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.600054919719696},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5723749995231628},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.41942593455314636},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13436540961265564},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09850668907165527}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2023.3317535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3317535","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":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G30724635","display_name":null,"funder_award_id":"62272155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G576546066","display_name":null,"funder_award_id":"61932010","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":43,"referenced_works":["https://openalex.org/W1980147176","https://openalex.org/W1980759071","https://openalex.org/W2002555321","https://openalex.org/W2054141820","https://openalex.org/W2083350792","https://openalex.org/W2087402357","https://openalex.org/W2112284959","https://openalex.org/W2138243089","https://openalex.org/W2143822352","https://openalex.org/W2168231600","https://openalex.org/W2340502990","https://openalex.org/W2515144511","https://openalex.org/W2544624872","https://openalex.org/W2612387305","https://openalex.org/W2626580042","https://openalex.org/W2642043218","https://openalex.org/W2696534605","https://openalex.org/W2788172561","https://openalex.org/W2788615138","https://openalex.org/W2791952321","https://openalex.org/W2797942387","https://openalex.org/W2867345499","https://openalex.org/W2893359107","https://openalex.org/W2913415152","https://openalex.org/W2917532348","https://openalex.org/W2950894652","https://openalex.org/W2953281140","https://openalex.org/W3005621653","https://openalex.org/W3008803005","https://openalex.org/W3016212306","https://openalex.org/W3081267827","https://openalex.org/W3093933627","https://openalex.org/W3167272309","https://openalex.org/W3174469048","https://openalex.org/W3193658714","https://openalex.org/W3204343072","https://openalex.org/W4226304970","https://openalex.org/W6684859321","https://openalex.org/W6703949738","https://openalex.org/W6739554518","https://openalex.org/W6764309476","https://openalex.org/W6765269223","https://openalex.org/W6810941178"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W2042919702","https://openalex.org/W2150611273","https://openalex.org/W4207086172","https://openalex.org/W4225981436","https://openalex.org/W2156185805","https://openalex.org/W2770353918","https://openalex.org/W2389214306"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"shown":[3],"that":[4,56,112],"collaborative":[5],"computing":[6,88,240],"of":[7,28,49,144,157,263,270],"CPUs":[8,103],"and":[9,52,75,104,118,161,175,221],"GPUs":[10,105],"in":[11,35,106,116,195],"the":[12,26,36,69,76,107,134,141,152,167,236,253,259,271],"same":[13],"system":[14,108,209,254],"can":[15,41,132,187,267],"effectively":[16,188],"accelerate":[17,189],"large-scale":[18],"SGD-based":[19,91,190,243],"matrix":[20,92,114],"factorization":[21],"(MF),":[22],"but":[23],"it":[24],"faces":[25,64],"problem":[27],"limited":[29],"scalability":[30],"due":[31],"to":[32,150,165,179,210,228,257],"parameter":[33],"synchronization":[34],"server.":[37],"Theoretically,":[38],"asynchronous":[39,60,77,87,181,197],"methods":[40],"overcome":[42],"this":[43],"shortcoming.":[44],"However,":[45],"through":[46],"a":[47,84,125,172,200],"series":[48],"tests,":[50],"observations,":[51],"analyses,":[53],"we":[54],"realize":[55],"developing":[57],"an":[58,148,196],"effective":[59],"multi-CPU/GPU":[61,86,193,238],"MF":[62,191],"framework":[63,89,241],"several":[65],"major":[66],"design":[67],"challenges:":[68],"underutilized":[70],"CPUs,":[71],"high":[72],"communication":[73,154,168],"overhead,":[74],"data":[78,177,182],"safety":[79],"issue.":[80],"This":[81],"article":[82],"presents":[83],"unified":[85],"for":[90,213,242],"factorization,":[93],"named":[94],"<sc":[95,99,184,223,245,264],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[96,100,185,224,246,265],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">UMA-MF</small>":[97,101,186,225,247,266],".":[98],"treats":[102],"as":[109],"distributed":[110],"workers":[111,160],"train":[113],"datasets":[115,216],"parallel":[117],"update":[119],"feature":[120],"parameters":[121],"asynchronously.":[122],"It":[123,146,170],"provides":[124],"cache-friendly":[126],"CPU":[127],"external":[128],"working":[129],"mode,":[130],"which":[131,234],"improve":[133],"CPU's":[135],"cache":[136],"hit":[137],"rate,":[138],"thereby":[139],"promoting":[140],"efficient":[142],"use":[143],"CPUs.":[145],"offers":[147],"algorithm":[149],"find":[151],"shortest":[153],"ring":[155],"topology":[156],"heterogeneous":[158],"CPU/GPU":[159],"builds":[162],"computing-communication":[163],"pipelines":[164],"minimize":[166],"overhead.":[169],"implements":[171],"wait-free":[173],"structure":[174],"load-balanced":[176],"distribution":[178],"achieve":[180],"safety.":[183],"on":[192],"systems":[194],"way.":[198],"On":[199],"physical":[201],"platform":[202],"with":[203,232],"configurations":[204],"ranging":[205],"from":[206],"single":[207],"processor":[208],"2CPUs--4CPUs":[211],"system,":[212],"five":[214],"common":[215],"Netfix,":[217],"R1,":[218],"R2,":[219],"Goodreads,":[220],"de-dense,":[222],"achieves":[226],"up":[227],"3.56x":[229],"speedup":[230,262],"compared":[231],"HCC-MF,":[233],"is":[235,255],"state-of-the-art":[237],"synchronous":[239],"MF.":[244],"also":[248],"shows":[249],"good":[250],"scalability.":[251],"When":[252],"scaled":[256],"2CPUs-4GPUs,":[258],"training":[260],"time":[261],"reach":[268],"70%--97%":[269],"ideal":[272],"speedup.":[273]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}