{"id":"https://openalex.org/W1609010894","doi":"https://doi.org/10.1145/2736277.2741115","title":"LightLDA","display_name":"LightLDA","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W1609010894","doi":"https://doi.org/10.1145/2736277.2741115","mag":"1609010894"},"language":"en","primary_location":{"id":"doi:10.1145/2736277.2741115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-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/A5036378701","display_name":"Jinhui Yuan","orcid":"https://orcid.org/0000-0003-1410-7792"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jinhui Yuan","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103244341","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0002-4679-856X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012361506","display_name":"Qirong Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qirong Ho","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752232","display_name":"Wei Dai","orcid":"https://orcid.org/0000-0002-0408-1835"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Dai","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112647533","display_name":"Jinliang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinliang Wei","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023132445","display_name":"Xun Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xun Zheng","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Po Xing","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research, Beijing, China","Microsoft Research, , Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, , Beijing, China","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":38.2849,"has_fulltext":false,"cited_by_count":163,"citation_normalized_percentile":{"value":0.99776589,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1351","last_page":"1361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9980999827384949,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.843002438545227},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5309832692146301},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47580915689468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47162342071533203},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4302791953086853},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4253199100494385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4193095862865448},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.41850173473358154},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.412993848323822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843002438545227},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5309832692146301},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47580915689468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47162342071533203},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4302791953086853},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4253199100494385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4193095862865448},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41850173473358154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.412993848323822},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2736277.2741115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W109881820","https://openalex.org/W1822248432","https://openalex.org/W1866637071","https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2041517243","https://openalex.org/W2049875313","https://openalex.org/W2052261215","https://openalex.org/W2056760934","https://openalex.org/W2058209916","https://openalex.org/W2065221212","https://openalex.org/W2083842231","https://openalex.org/W2087937280","https://openalex.org/W2101101940","https://openalex.org/W2107107106","https://openalex.org/W2113547287","https://openalex.org/W2116137244","https://openalex.org/W2132737349","https://openalex.org/W2135194391","https://openalex.org/W2136796925","https://openalex.org/W2138309709","https://openalex.org/W2138996412","https://openalex.org/W2142092798","https://openalex.org/W2150731624","https://openalex.org/W2962885409","https://openalex.org/W3003241580","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W3205684019","https://openalex.org/W3038776261"],"abstract_inverted_index":{"When":[0],"building":[1],"large-scale":[2],"machine":[3,169],"learning":[4],"(ML)":[5],"programs,":[6],"such":[7,29],"as":[8,75,77,175],"massive":[9,30,243],"topic":[10,62,84],"models":[11,210,246],"or":[12],"deep":[13],"neural":[14],"networks":[15],"with":[16,36,39,70,86,105,116,260],"up":[17],"to":[18,160,206,211],"trillions":[19],"of":[20,41,46,61,74,97,118,138,147,173,182,226],"parameters":[21],"and":[22,51,67,90,141,186,203,233,245],"training":[23],"examples,":[24],"one":[25],"usually":[26],"assumes":[27],"that":[28,69],"tasks":[31],"can":[32,81],"only":[33],"be":[34],"attempted":[35],"industrial-sized":[37],"clusters":[38],"thousands":[40,117],"nodes,":[42],"which":[43,196],"are":[44,222],"out":[45],"reach":[47,248],"for":[48,193,201],"most":[49],"practitioners":[50],"academic":[52],"researchers.":[53],"We":[54],"consider":[55],"this":[56,240],"challenge":[57],"in":[58,178,213],"the":[59,162,171,227],"context":[60],"modeling":[63],"on":[64,101,224,249],"web-scale":[65],"corpora,":[66],"show":[68],"a":[71,83,91,95,102,110,125,157,179,190,250],"modest":[72],"cluster":[73,262],"few":[76],"8":[78],"machines,":[79],"we":[80,234],"train":[82],"model":[85,139,164,194],"1":[87,98],"million":[88],"topics":[89],"1-million-word":[92],"vocabulary":[93],"(for":[94],"total":[96],"trillion":[99],"parameters),":[100],"document":[103],"collection":[104],"200":[106],"billion":[107],"tokens":[108],"---":[109],"scale":[111],"not":[112],"yet":[113],"reported":[114],"even":[115],"machines.":[119],"Our":[120],"major":[121],"contributions":[122,221],"include:":[123],"1)":[124],"new,":[126],"highly-efficient":[127],"O(1)":[128],"Metropolis-Hastings":[129],"sampling":[130],"algorithm,":[131],"whose":[132],"running":[133],"cost":[134,258],"is":[135],"(surprisingly)":[136],"agnostic":[137],"size,":[140],"empirically":[142],"converges":[143],"nearly":[144],"an":[145],"order":[146],"magnitude":[148],"more":[149],"quickly":[150],"than":[151],"current":[152],"state-of-the-art":[153],"Gibbs":[154],"samplers;":[155],"2)":[156],"model-scheduling":[158],"scheme":[159],"handle":[161],"big":[163],"challenge,":[165],"where":[166],"each":[167],"worker":[168],"schedules":[170],"fetch/use":[172],"sub-models":[174],"needed,":[176],"resulting":[177],"frugal":[180],"use":[181],"limited":[183],"memory":[184],"capacity":[185],"network":[187],"bandwidth;":[188],"3)":[189],"differential":[191],"data-structure":[192],"storage,":[195],"uses":[197],"separate":[198],"data":[199,244],"structures":[200],"high-":[202],"low-frequency":[204],"words":[205],"allow":[207],"extremely":[208],"large":[209],"fit":[212],"memory,":[214],"while":[215,253],"maintaining":[216],"high":[217],"inference":[218],"speed.":[219],"These":[220],"built":[223],"top":[225],"Petuum":[228],"open-source":[229],"distributed":[230],"ML":[231],"framework,":[232],"provide":[235],"experimental":[236],"evidence":[237],"showing":[238],"how":[239],"development":[241],"puts":[242],"within":[247],"small":[251],"cluster,":[252],"still":[254],"enjoying":[255],"proportional":[256],"time":[257],"reductions":[259],"increasing":[261],"size.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}