{"id":"https://openalex.org/W3015677374","doi":"https://doi.org/10.1109/tpds.2020.2979702","title":"SaberLDA: Sparsity-Aware Learning of Topic Models on GPUs","display_name":"SaberLDA: Sparsity-Aware Learning of Topic Models on GPUs","publication_year":2020,"publication_date":"2020-04-08","ids":{"openalex":"https://openalex.org/W3015677374","doi":"https://doi.org/10.1109/tpds.2020.2979702","mag":"3015677374"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.2979702","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2979702","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9067774/09061024.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/71/9067774/09061024.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100778151","display_name":"Kaiwei Li","orcid":"https://orcid.org/0000-0002-8015-0812"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaiwei Li","raw_affiliation_strings":["Department of Computer Sciences and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641283","display_name":"Jianfei Chen","orcid":"https://orcid.org/0000-0003-4107-5706"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfei Chen","raw_affiliation_strings":["Department of Computer Sciences and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wenguang Chen","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology (BNRist)","Department of Computer Sciences and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist)","institution_ids":["https://openalex.org/I29955533"]},{"raw_affiliation_string":"Department of Computer Sciences and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606995","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-6254-2388"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Department of Computer Sciences and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100778151"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1359,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53385011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":"9","first_page":"2112","last_page":"2124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9923999905586243,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9923999905586243,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9890999794006348,"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":0.9019407033920288},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7065549492835999},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5308994054794312},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5103165507316589},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5084971189498901},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47746896743774414},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.46675896644592285},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.42325687408447266},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35317152738571167},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.2614215612411499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2031487226486206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9019407033920288},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7065549492835999},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5308994054794312},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5103165507316589},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5084971189498901},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47746896743774414},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.46675896644592285},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.42325687408447266},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35317152738571167},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2614215612411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2031487226486206},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2020.2979702","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2979702","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9067774/09061024.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/tpds.2020.2979702","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2979702","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9067774/09061024.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1336299065","display_name":null,"funder_award_id":"61525202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015677374.pdf","grobid_xml":"https://content.openalex.org/works/W3015677374.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494192115","https://openalex.org/W1546359014","https://openalex.org/W1609010894","https://openalex.org/W1650067024","https://openalex.org/W1863602751","https://openalex.org/W2001082470","https://openalex.org/W2021197309","https://openalex.org/W2045007904","https://openalex.org/W2049600635","https://openalex.org/W2052261215","https://openalex.org/W2060393849","https://openalex.org/W2065221212","https://openalex.org/W2094939105","https://openalex.org/W2094951132","https://openalex.org/W2104924585","https://openalex.org/W2106490775","https://openalex.org/W2116137244","https://openalex.org/W2118034653","https://openalex.org/W2123549998","https://openalex.org/W2129004009","https://openalex.org/W2132827946","https://openalex.org/W2133568543","https://openalex.org/W2138996412","https://openalex.org/W2144100511","https://openalex.org/W2145702984","https://openalex.org/W2150731624","https://openalex.org/W2158307368","https://openalex.org/W2161061943","https://openalex.org/W2379152647","https://openalex.org/W2541688157","https://openalex.org/W2751219672","https://openalex.org/W2794210286","https://openalex.org/W2798798513","https://openalex.org/W2808096987","https://openalex.org/W2897613819","https://openalex.org/W2963491860","https://openalex.org/W3120740533","https://openalex.org/W4231510805","https://openalex.org/W6639268648","https://openalex.org/W6639619044","https://openalex.org/W6675861922","https://openalex.org/W6677121468","https://openalex.org/W6678337573","https://openalex.org/W6679439793","https://openalex.org/W6679563517","https://openalex.org/W6679607006","https://openalex.org/W6681349557","https://openalex.org/W6683923952","https://openalex.org/W6709750409","https://openalex.org/W6755447188"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W90906771"],"abstract_inverted_index":{"Latent":[0],"Dirichlet":[1],"Allocation":[2],"(LDA)":[3],"is":[4,165],"a":[5,25,62,107,113,123,137,141,152,183],"popular":[6],"tool":[7],"for":[8,36],"analyzing":[9],"discrete":[10],"count":[11],"data":[12,89,139],"such":[13],"as":[14,61],"text":[15],"and":[16,24,54,71,91,151,164],"images,":[17],"which":[18,192],"are":[19,52],"required":[20],"to":[21,47,96,116,121],"model":[22],"datasets":[23],"large":[26,124],"number":[27,98,125],"of":[28,32,34,66,83,99,126,175,185,187,199,201],"topics,":[29,84],"e.g.,":[30],"tens":[31,200],"thousands":[33,82,174],"topics":[35,181],"industry":[37],"scale":[38],"applications.":[39],"Although":[40],"distributed":[41],"CPU":[42,202],"systems":[43,58,78,172],"have":[44,59,92],"been":[45],"used":[46],"address":[48,129],"this":[49,102],"problem,":[50],"they":[51,86],"slow":[53],"resource":[55],"inefficient.":[56],"GPU-based":[57,76,108],"emerged":[60],"promising":[63],"alternative":[64],"because":[65,85],"their":[67],"high":[68],"computational":[69],"power":[70],"memory":[72],"bandwidth.":[73],"However,":[74],"existing":[75,170],"LDA":[77,109],"can":[79,178],"only":[80,195],"learn":[81,122,179],"use":[87],"dense":[88],"structures,":[90],"linear":[93,159],"time":[94,119],"complexity":[95,120],"the":[97,130],"topics.":[100,127,176],"In":[101],"article,":[103],"we":[104,135],"propose":[105,136],"SaberLDA,":[106],"system":[110],"that":[111],"implements":[112],"sparsity-aware":[114],"algorithm":[115],"achieve":[117],"sublinear":[118],"To":[128],"challenges":[131],"introduced":[132],"by":[133],"sparsity,":[134],"novel":[138],"layout,":[140],"warp-based":[142],"sampling":[143],"kernel,":[144],"an":[145],"efficient":[146],"sparse":[147],"matrix":[148],"counting":[149],"method,":[150],"fine-grained":[153],"load":[154],"balancing":[155],"strategy.":[156],"SaberLDA":[157],"achieves":[158],"speedup":[160],"on":[161],"4":[162],"GPUs":[163],"6-10":[166],"times":[167],"faster":[168],"than":[169],"GPU":[171],"in":[173,189],"It":[177],"40,000":[180],"from":[182],"dataset":[184],"billions":[186],"tokens":[188],"two":[190],"hours,":[191],"was":[193],"previously":[194],"achievable":[196],"using":[197],"clusters":[198],"servers.":[203]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}