{"id":"https://openalex.org/W2146341620","doi":"https://doi.org/10.1145/1401890.1401960","title":"Fast collapsed gibbs sampling for latent dirichlet allocation","display_name":"Fast collapsed gibbs sampling for latent dirichlet allocation","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2146341620","doi":"https://doi.org/10.1145/1401890.1401960","mag":"2146341620"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5088860761","display_name":"Ian R. Porteous","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ian Porteous","raw_affiliation_strings":["University of California Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088727983","display_name":"David Newman","orcid":"https://orcid.org/0000-0002-4959-2428"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Newman","raw_affiliation_strings":["University of California Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048047705","display_name":"Alexander Ihler","orcid":"https://orcid.org/0000-0002-4331-1015"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Ihler","raw_affiliation_strings":["University of California Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011959718","display_name":"Arthur Asuncion","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arthur Asuncion","raw_affiliation_strings":["University of California Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077460655","display_name":"Padhraic Smyth","orcid":"https://orcid.org/0000-0001-9971-8378"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Padhraic Smyth","raw_affiliation_strings":["University of California Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087368991","display_name":"Max Welling","orcid":"https://orcid.org/0000-0003-1484-2121"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max Welling","raw_affiliation_strings":["University of California Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088860761"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":25.1716,"has_fulltext":false,"cited_by_count":567,"citation_normalized_percentile":{"value":0.99549853,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"569","last_page":"577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T11269","display_name":"Algorithms and Data Compression","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/gibbs-sampling","display_name":"Gibbs sampling","score":0.8926689624786377},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8896138668060303},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7243359088897705},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7088783979415894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6817106008529663},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6385846138000488},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.5462455749511719},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4908023774623871},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4829532504081726},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46634241938591003},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4640898108482361},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.32493746280670166},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.28612464666366577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.260036826133728},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22213062644004822},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.058011531829833984}],"concepts":[{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.8926689624786377},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8896138668060303},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7243359088897705},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7088783979415894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6817106008529663},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6385846138000488},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.5462455749511719},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4908023774623871},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4829532504081726},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46634241938591003},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4640898108482361},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.32493746280670166},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.28612464666366577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.260036826133728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22213062644004822},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.058011531829833984},{"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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1401890.1401960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.1349","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.1349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~ihler/papers/kdd08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.7284","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.7284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~welling/publications/papers/rtp378-porteous.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1561994953","https://openalex.org/W1585610988","https://openalex.org/W1880262756","https://openalex.org/W1999668761","https://openalex.org/W2001082470","https://openalex.org/W2023405098","https://openalex.org/W2042980227","https://openalex.org/W2106490775","https://openalex.org/W2114693731","https://openalex.org/W2124998943","https://openalex.org/W2131297510","https://openalex.org/W2137268161","https://openalex.org/W2141441158","https://openalex.org/W2152255870","https://openalex.org/W2153029569","https://openalex.org/W2158266063","https://openalex.org/W2165558283","https://openalex.org/W2168319451","https://openalex.org/W2912651257","https://openalex.org/W6633521410","https://openalex.org/W6683603713"],"related_works":["https://openalex.org/W2939843948","https://openalex.org/W2497860580","https://openalex.org/W2097627380","https://openalex.org/W2914864478","https://openalex.org/W2891616219","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W3204672119","https://openalex.org/W2352674739"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,95],"introduce":[4],"a":[5,124,140],"novel":[6],"collapsed":[7,85],"Gibbs":[8,33,86],"sampling":[9,34,100,112],"method":[10,22,55],"for":[11,36,88,123,148],"the":[12,46,51,83,104,108,131],"widely":[13],"used":[14],"latent":[15],"Dirichlet":[16],"allocation":[17],"(LDA)":[18],"model.":[19,52],"Our":[20,53],"new":[21],"results":[23,106],"in":[24,50],"significant":[25],"speedups":[26,122],"on":[27,61,115],"real":[28,117],"world":[29,118],"text":[30],"corpora.":[31],"Conventional":[32],"schemes":[35],"LDA":[37],"require":[38],"O(K)":[39],"operations":[40,67],"per":[41,68],"sample":[42],"where":[43],"K":[44,66],"is":[45],"number":[47],"of":[48,127,134,144,152,159],"topics":[49],"proposed":[54],"draws":[56],"equivalent":[57],"samples":[58],"but":[59],"requires":[60],"average":[62],"significantly":[63],"less":[64],"then":[65],"sample.":[69],"On":[70],"real-word":[71],"corpora":[72],"FastLDA":[73],"can":[74,154],"be":[75],"as":[76,78,107],"much":[77],"8":[79,136],"times":[80],"faster":[81],"than":[82],"standard":[84,109],"sampler":[87],"LDA.":[89],"No":[90],"approximations":[91],"are":[92],"necessary,":[93],"and":[94],"show":[96],"that":[97],"our":[98,150],"fast":[99],"scheme":[101],"produces":[102],"exactly":[103],"same":[105],"(but":[110],"slower)":[111],"scheme.":[113],"Experiments":[114],"four":[116],"data":[119],"sets":[120],"demonstrate":[121],"wide":[125],"range":[126],"collection":[128,133],"sizes.":[129],"For":[130],"PubMed":[132],"over":[135],"million":[137],"documents":[138],"with":[139],"required":[141],"computation":[142],"time":[143],"6":[145],"CPU":[146,157],"months":[147,158],"LDA,":[149],"speedup":[151],"5.7":[153],"save":[155],"5":[156],"computation.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":39},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":46},{"year":2017,"cited_by_count":57},{"year":2016,"cited_by_count":49},{"year":2015,"cited_by_count":64},{"year":2014,"cited_by_count":51},{"year":2013,"cited_by_count":39},{"year":2012,"cited_by_count":35}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}