{"id":"https://openalex.org/W2885998509","doi":"https://doi.org/10.1145/3225058.3225096","title":"Matrix Factorization on GPUs with Memory Optimization and Approximate Computing","display_name":"Matrix Factorization on GPUs with Memory Optimization and Approximate Computing","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2885998509","doi":"https://doi.org/10.1145/3225058.3225096","mag":"2885998509"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","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/A5079169201","display_name":"Wei Tan","orcid":"https://orcid.org/0000-0002-2617-7598"},"institutions":[{"id":"https://openalex.org/I91036609","display_name":"Citadel","ror":"https://ror.org/01vwr6t80","country_code":"US","type":"education","lineage":["https://openalex.org/I91036609"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Tan","raw_affiliation_strings":["Citadel, Chicago, Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Citadel, Chicago, Illinois","institution_ids":["https://openalex.org/I91036609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112248869","display_name":"Shiyu Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Chang","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083938597","display_name":"Liana Fong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liana Fong","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697250","display_name":"Cheng Li","orcid":"https://orcid.org/0000-0003-4451-2852"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Li","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729843","display_name":"Zijun Wang","orcid":"https://orcid.org/0009-0002-1261-2760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Wang","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103187717","display_name":"Liangliang Cao","orcid":"https://orcid.org/0000-0003-0900-1512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"LiangLiang Cao","raw_affiliation_strings":["HelloVera.AI, New York, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HelloVera.AI, New York, New York","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9904999732971191,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9904999732971191,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9739000201225281,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9664000272750854,"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":0.8353878259658813},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7852990627288818},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.7087276577949524},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6065694689750671},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5806502103805542},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.544187605381012},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4798440635204315},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4788070321083069},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.47758200764656067},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.46302974224090576},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42734000086784363},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.41910362243652344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3621160387992859},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3421257734298706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27158135175704956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18614476919174194},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.16179627180099487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353878259658813},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7852990627288818},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.7087276577949524},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6065694689750671},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5806502103805542},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.544187605381012},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4798440635204315},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4788070321083069},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.47758200764656067},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.46302974224090576},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42734000086784363},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41910362243652344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3621160387992859},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3421257734298706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27158135175704956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18614476919174194},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.16179627180099487},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1511814458","https://openalex.org/W1542014621","https://openalex.org/W1555915743","https://openalex.org/W1630668835","https://openalex.org/W1762731526","https://openalex.org/W1833917188","https://openalex.org/W1980147176","https://openalex.org/W2002555321","https://openalex.org/W2020098476","https://openalex.org/W2028683648","https://openalex.org/W2054141820","https://openalex.org/W2063468305","https://openalex.org/W2096544401","https://openalex.org/W2101409192","https://openalex.org/W2112284959","https://openalex.org/W2121966774","https://openalex.org/W2134797427","https://openalex.org/W2137028279","https://openalex.org/W2143822352","https://openalex.org/W2146682077","https://openalex.org/W2149941839","https://openalex.org/W2162390675","https://openalex.org/W2187230075","https://openalex.org/W2199814763","https://openalex.org/W2202715214","https://openalex.org/W2250539671","https://openalex.org/W2265166184","https://openalex.org/W2293706247","https://openalex.org/W2297086932","https://openalex.org/W2316564661","https://openalex.org/W2532222290","https://openalex.org/W2588313843","https://openalex.org/W2696534605","https://openalex.org/W2950263839","https://openalex.org/W2951781666","https://openalex.org/W2963288913","https://openalex.org/W6614148910"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W3109911900","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031"],"abstract_inverted_index":{"Matrix":[0],"factorization":[1],"(MF)":[2],"discovers":[3],"latent":[4],"features":[5],"from":[6,96],"observations,":[7],"which":[8],"has":[9],"shown":[10],"great":[11],"promises":[12],"in":[13],"the":[14,97],"fields":[15],"of":[16,70],"collaborative":[17],"filtering,":[18],"data":[19,91],"compression,":[20],"feature":[21],"extraction,":[22],"word":[23],"embedding,":[24],"etc.":[25],"While":[26],"many":[27],"problem-specific":[28],"optimization":[29],"techniques":[30],"have":[31],"been":[32],"proposed,":[33],"alternating":[34],"least":[35],"square":[36],"(ALS)":[37],"remains":[38],"popular":[39],"due":[40],"to":[41,47],"its":[42],"general":[43],"applicability":[44],"(e.g.":[45],"easy":[46],"handle":[48],"positive-unlabeled":[49],"inputs),":[50],"fast":[51],"convergence":[52],"and":[53],"parallelization":[54],"capability.":[55],"Current":[56],"MF":[57],"implementations":[58],"are":[59,77],"either":[60],"optimized":[61],"for":[62,89],"a":[63,68,71,82],"single":[64,83],"machine":[65,84],"or":[66],"with":[67],"need":[69],"large":[72],"computer":[73],"cluster":[74],"but":[75],"still":[76],"insufficent.":[78],"This":[79],"is":[80],"because":[81],"provides":[85],"limited":[86],"compute":[87],"power":[88],"large-scale":[90],"while":[92],"multiple":[93],"machines":[94],"suffer":[95],"network":[98],"communication":[99],"bottleneck.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}