{"id":"https://openalex.org/W2905438871","doi":"https://doi.org/10.1609/aaai.v33i01.33014197","title":"X-DMM: Fast and Scalable Model Based Text Clustering","display_name":"X-DMM: Fast and Scalable Model Based Text Clustering","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2905438871","doi":"https://doi.org/10.1609/aaai.v33i01.33014197","mag":"2905438871"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014197","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014197","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4325/4203","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4325/4203","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100721239","display_name":"Linwei Li","orcid":"https://orcid.org/0000-0002-8406-8322"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linwei Li","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018479585","display_name":"Liangchen Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangchen Guo","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059000467","display_name":"Zhenying He","orcid":"https://orcid.org/0000-0002-2926-4814"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenying He","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087411191","display_name":"Yinan Jing","orcid":"https://orcid.org/0000-0002-1169-8032"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinan Jing","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072790845","display_name":"X. Sean Wang","orcid":"https://orcid.org/0000-0002-9059-3713"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"X. Sean Wang","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100721239"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.5321,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71754179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"33","issue":"01","first_page":"4197","last_page":"4204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9914000034332275,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9914000034332275,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9894000291824341,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9685999751091003,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7755016088485718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6944125890731812},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5891975164413452},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.5737485885620117},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5730727910995483},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.4232724905014038},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4220579266548157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38822948932647705},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38358381390571594},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3528260886669159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3368161916732788},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.3253011703491211},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.2770342230796814},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17135918140411377}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7755016088485718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6944125890731812},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5891975164413452},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.5737485885620117},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5730727910995483},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.4232724905014038},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4220579266548157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38822948932647705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38358381390571594},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3528260886669159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3368161916732788},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.3253011703491211},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2770342230796814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17135918140411377},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014197","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014197","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4325/4203","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014197","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014197","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4325/4203","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3294234326","display_name":null,"funder_award_id":"2018YFB1004","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4557816978","display_name":null,"funder_award_id":"61872207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4811743277","display_name":null,"funder_award_id":"2018YFC","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5484828425","display_name":null,"funder_award_id":"2018YFC0830900","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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"},{"id":"https://openalex.org/G7851391746","display_name":null,"funder_award_id":"61732004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8048650684","display_name":null,"funder_award_id":"2018YFC0830900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8188466228","display_name":null,"funder_award_id":"2018YFB100440","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8691506008","display_name":null,"funder_award_id":"2018YFB10044","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2905438871.pdf","grobid_xml":"https://content.openalex.org/works/W2905438871.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W4952878","https://openalex.org/W1612003148","https://openalex.org/W1826790618","https://openalex.org/W1866637071","https://openalex.org/W1977556410","https://openalex.org/W1983989471","https://openalex.org/W1989753615","https://openalex.org/W2001082470","https://openalex.org/W2005564522","https://openalex.org/W2011430131","https://openalex.org/W2025653016","https://openalex.org/W2052261215","https://openalex.org/W2061922307","https://openalex.org/W2066680326","https://openalex.org/W2073414385","https://openalex.org/W2083620785","https://openalex.org/W2087743880","https://openalex.org/W2087962968","https://openalex.org/W2097417931","https://openalex.org/W2116137244","https://openalex.org/W2150286230","https://openalex.org/W2380042537","https://openalex.org/W2404930856","https://openalex.org/W2471517265","https://openalex.org/W4231510805","https://openalex.org/W4255975151","https://openalex.org/W6632088959","https://openalex.org/W6636021564","https://openalex.org/W6636440780","https://openalex.org/W6638727336","https://openalex.org/W6639619044","https://openalex.org/W6644682428","https://openalex.org/W6650793866","https://openalex.org/W6651763111","https://openalex.org/W6663247956","https://openalex.org/W6671018158","https://openalex.org/W6676033047","https://openalex.org/W6677121468","https://openalex.org/W6713360210"],"related_works":["https://openalex.org/W2048766621","https://openalex.org/W2813472416","https://openalex.org/W2380850649","https://openalex.org/W2939843948","https://openalex.org/W2352674739","https://openalex.org/W2060556149","https://openalex.org/W1966862482","https://openalex.org/W1480783174","https://openalex.org/W2072169887","https://openalex.org/W197558907"],"abstract_inverted_index":{"Text":[0],"clustering":[1,19,38,237],"is":[2,51,76,120],"a":[3,93,144,174,189],"widely":[4],"studied":[5],"problem":[6],"in":[7,36,78,139,159],"the":[8,44,54,59,105,109,121,126,133,151,160,168,197,211,221],"text":[9,31,71,207],"mining":[10],"domain.":[11],"The":[12],"Dirichlet":[13,98],"Multinomial":[14],"Mixture":[15],"(DMM)":[16],"model":[17,49,170,199],"based":[18],"algorithms":[20,235],"have":[21],"shown":[22],"good":[23],"performance":[24,212],"to":[25,53,69,103,116,157,172,200],"cope":[26],"with":[27,232],"high":[28],"dimensional":[29],"sparse":[30],"data,":[32],"obtaining":[33],"reasonable":[34],"results":[35,223],"both":[37],"accuracy":[39,238],"and":[40,58,72,86,100,131,205,220],"computational":[41],"efficiency.":[42],"However,":[43],"time":[45,106,153],"complexity":[46,107,154],"of":[47,61,108,123,129,136,213],"DMM":[48,113,169,198],"training":[50,111,162,171],"proportional":[52],"average":[55,127,134],"document":[56],"length":[57,128],"number":[60,122,135],"clusters,":[62,124],"making":[63],"it":[64],"inefficient":[65],"for":[66,97,112,203],"scaling":[67],"up":[68,202,230],"long":[70,204],"large":[73],"corpora,":[74],"which":[75,148,195],"common":[77],"realworld":[79],"applications":[80],"such":[81],"as":[82],"documents":[83],"organization,":[84],"retrieval":[85],"recommendation.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91,165],"leverage":[92],"symmetric":[94],"prior":[95],"setting":[96],"distribution,":[99],"build":[101],"indices":[102],"decrease":[104],"sampling-based":[110],"from":[114,155],"O(K\u2217L)":[115],"O(K\u2217U),":[117],"where":[118],"K":[119],"L":[125],"document,":[130],"U":[132],"unique":[137],"words":[138],"each":[140],"document.":[141],"We":[142,183,209],"introduce":[143],"Metropolis-Hastings":[145],"sampling":[146,152],"algorithm,":[147],"further":[149,175],"reduces":[150],"O(K\u2217U)":[156],"O(U)":[158],"nearly-to-convergence":[161],"stages.":[163],"Moreover,":[164],"also":[166],"parallelize":[167],"obtain":[173],"acceleration":[176],"by":[177],"using":[178],"an":[179],"uncollapsed":[180],"Gibbs":[181],"sampler.":[182],"combine":[184],"all":[185],"these":[186],"optimizations":[187],"into":[188],"highly":[190],"efficient":[191],"implementation,":[192],"called":[193],"X-DMM,":[194],"enables":[196],"scale":[201],"large-scale":[206],"clustering.":[208],"evaluate":[210],"X-DMM":[214],"on":[215],"several":[216],"real":[217],"world":[218],"datasets,":[219],"experimental":[222],"show":[224],"that":[225],"XDMM":[226],"achieves":[227],"substantial":[228],"speed":[229],"compared":[231],"existing":[233],"state-of-the-art":[234],"without":[236],"degradation.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}