{"id":"https://openalex.org/W3135046730","doi":"https://doi.org/10.1109/tpds.2021.3064942","title":"BALS: Blocked Alternating Least Squares for Parallel Sparse Matrix Factorization on GPUs","display_name":"BALS: Blocked Alternating Least Squares for Parallel Sparse Matrix Factorization on GPUs","publication_year":2021,"publication_date":"2021-03-09","ids":{"openalex":"https://openalex.org/W3135046730","doi":"https://doi.org/10.1109/tpds.2021.3064942","mag":"3135046730"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3064942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3064942","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/A5100394982","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0003-3409-8651"},"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":true,"raw_author_name":"Jing Chen","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083171604","display_name":"Jianbin Fang","orcid":"https://orcid.org/0000-0003-3542-4869"},"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":"Jianbin Fang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444152","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101044975","display_name":"Canqun Yang","orcid":null},"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":"Canqun Yang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100394982"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.6725,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.70081699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"9","first_page":"2291","last_page":"2302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9925000071525574,"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"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9855999946594238,"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/computer-science","display_name":"Computer science","score":0.7375674247741699},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6913691759109497},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6825869679450989},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6429166793823242},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5908606052398682},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.45401516556739807},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4331589341163635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34645622968673706},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1315460503101349},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11917659640312195},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.10627758502960205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7375674247741699},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6913691759109497},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6825869679450989},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6429166793823242},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5908606052398682},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.45401516556739807},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4331589341163635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34645622968673706},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1315460503101349},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11917659640312195},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.10627758502960205},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3064942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3064942","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/G1198003221","display_name":null,"funder_award_id":"2462020XKJS03","funder_id":"https://openalex.org/F4320326291","funder_display_name":"Science Foundation of China University of Petroleum, Beijing"},{"id":"https://openalex.org/G3472349540","display_name":null,"funder_award_id":"61972415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5011199069","display_name":null,"funder_award_id":"TZZT2016002","funder_id":"https://openalex.org/F4320336025","funder_display_name":"Science Challenge Project"},{"id":"https://openalex.org/G503725912","display_name":null,"funder_award_id":"61972408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5214302469","display_name":null,"funder_award_id":"2018YFB0204301","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5660919176","display_name":null,"funder_award_id":"2462019YJRC004","funder_id":"https://openalex.org/F4320326291","funder_display_name":"Science Foundation of China University of Petroleum, Beijing"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326291","display_name":"Science Foundation of China University of Petroleum, Beijing","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336025","display_name":"Science Challenge Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1511814458","https://openalex.org/W1542014621","https://openalex.org/W1747539222","https://openalex.org/W1980147176","https://openalex.org/W2009654791","https://openalex.org/W2020098476","https://openalex.org/W2049469158","https://openalex.org/W2054141820","https://openalex.org/W2076246374","https://openalex.org/W2096544401","https://openalex.org/W2113802117","https://openalex.org/W2117499659","https://openalex.org/W2125996677","https://openalex.org/W2138243089","https://openalex.org/W2143822352","https://openalex.org/W2166706236","https://openalex.org/W2199814763","https://openalex.org/W2213168259","https://openalex.org/W2276719940","https://openalex.org/W2297086932","https://openalex.org/W2410272182","https://openalex.org/W2415035819","https://openalex.org/W2506667019","https://openalex.org/W2532222290","https://openalex.org/W2569020760","https://openalex.org/W2588313843","https://openalex.org/W2605809234","https://openalex.org/W2621863315","https://openalex.org/W2623801597","https://openalex.org/W2696534605","https://openalex.org/W2729544074","https://openalex.org/W2746067462","https://openalex.org/W2962740062","https://openalex.org/W2963288913","https://openalex.org/W3048232878","https://openalex.org/W3098912714","https://openalex.org/W3105227640","https://openalex.org/W3175189837","https://openalex.org/W6614148910","https://openalex.org/W6632701987","https://openalex.org/W6662929504","https://openalex.org/W6677756232","https://openalex.org/W6680402377","https://openalex.org/W6684249991","https://openalex.org/W6695046875","https://openalex.org/W6728182813","https://openalex.org/W6742873993","https://openalex.org/W6797727244"],"related_works":["https://openalex.org/W1973739845","https://openalex.org/W119752240","https://openalex.org/W3202552726","https://openalex.org/W2898722594","https://openalex.org/W2279642117","https://openalex.org/W4321636545","https://openalex.org/W2113856999","https://openalex.org/W4391266752","https://openalex.org/W133838137","https://openalex.org/W2023476765"],"abstract_inverted_index":{"Matrix":[0],"factorization":[1,26,154],"on":[2,57,138,141,146,184,188,194],"sparse":[3,62,75,98],"matrices":[4,99],"has":[5],"been":[6],"proven":[7],"to":[8,28,80,96,101,136,181],"be":[9],"an":[10,42,176],"effective":[11],"approach":[12],"for":[13,24,65],"data":[14,83,87,93],"mining":[15],"and":[16,85,144,162,169,191],"machine":[17],"learning.":[18],"However,":[19],"the":[20,30,46,74],"prior":[21],"parallel":[22,66],"implementations":[23],"matrix":[25,63,67,76,153],"fail":[27],"capture":[29],"internal":[31],"social":[32],"property":[33],"embedded":[34],"in":[35],"real-world":[36],"use":[37],"cases.":[38],"This":[39],"article":[40],"presents":[41],"efficient":[43],"implementation":[44,125],"of":[45,59,134,179],"alternative":[47,152],"least":[48],"squares":[49],"(ALS)":[50],"algorithm":[51],"called":[52],"<italic":[53],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[54],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">BALS</i>":[55],"built":[56],"top":[58],"a":[60,92,111,132],"new":[61],"format":[64,72],"factorization.":[68],"The":[69,103,171],"BALS":[70,108,119,157],"storage":[71],"organizes":[73],"into":[77],"2D":[78],"tiles":[79],"avoid":[81],"repeated":[82],"loads":[84],"improve":[86],"reuses.":[88],"We":[89],"further":[90],"propose":[91],"reordering":[94,172],"technique":[95,173],"sort":[97],"according":[100],"nonzeros.":[102],"experimental":[104],"results":[105],"show":[106],"that":[107],"can":[109,174],"yield":[110],"superior":[112],"performance":[113],"than":[114,123],"state-of-the-art":[115],"implementations,":[116],"i.e.,":[117],"our":[118,156],"generally":[120],"runs":[121],"faster":[122],"Gates\u2019":[124],"over":[126,164],"different":[127],"latent":[128,166],"feature":[129,167],"sizes,":[130],"with":[131,151],"speedup":[133],"up":[135,180],"2.08\u00d7":[137],"K20C,":[139,185],"3.72\u00d7":[140],"TITAN":[142,147,189,195],"X":[143,190],"3.13\u00d7":[145],"RTX.":[148,196],"When":[149],"compared":[150],"algorithms,":[155],"consistently":[158],"outperforms":[159],"CDMF,":[160],"cuMF_CCD,":[161],"cuMF_SGD":[163],"various":[165],"sizes":[168],"datasets.":[170],"provide":[175],"extra":[177],"improvement":[178],"23.68":[182],"percent":[183,187,193],"19.87":[186],"20.38":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}