{"id":"https://openalex.org/W2153068592","doi":"https://doi.org/10.1145/2348283.2348335","title":"Group matrix factorization for scalable topic modeling","display_name":"Group matrix factorization for scalable topic modeling","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2153068592","doi":"https://doi.org/10.1145/2348283.2348335","mag":"2153068592"},"language":"en","primary_location":{"id":"doi:10.1145/2348283.2348335","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2348283.2348335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval","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/A5100418265","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0002-7056-0519"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Wang","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of Statistics&Information Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of Statistics&Information Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005638757","display_name":"Zheng Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Cao","raw_affiliation_strings":["Dept. of Computer Science & Engineering, Shanghai JiaoTong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Shanghai JiaoTong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455138","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-5317-7227"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100418265"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":6.1898,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.9635582,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"375","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.998199999332428,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9954000115394592,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143829107284546},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.693832278251648},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.648784339427948},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6162042021751404},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5959519147872925},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5387049913406372},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.522022545337677},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5083641409873962},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5046044588088989},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4937792718410492},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35731804370880127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34315750002861023},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09946995973587036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143829107284546},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.693832278251648},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.648784339427948},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6162042021751404},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5959519147872925},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5387049913406372},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.522022545337677},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5083641409873962},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5046044588088989},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4937792718410492},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35731804370880127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34315750002861023},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09946995973587036},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2348283.2348335","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2348283.2348335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.259.7825","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.259.7825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/people/junxu/gmf-sigir2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W86136852","https://openalex.org/W1482214997","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W1974490937","https://openalex.org/W1986931325","https://openalex.org/W2042980227","https://openalex.org/W2056636001","https://openalex.org/W2062102668","https://openalex.org/W2063978378","https://openalex.org/W2082855665","https://openalex.org/W2098062695","https://openalex.org/W2102760656","https://openalex.org/W2105464873","https://openalex.org/W2107743791","https://openalex.org/W2112247328","https://openalex.org/W2113606819","https://openalex.org/W2122683976","https://openalex.org/W2128638419","https://openalex.org/W2135029798","https://openalex.org/W2141441158","https://openalex.org/W2147152072","https://openalex.org/W2156693754","https://openalex.org/W2157639439","https://openalex.org/W2165612380","https://openalex.org/W2171806843","https://openalex.org/W2174706414","https://openalex.org/W2530593441","https://openalex.org/W2953139536","https://openalex.org/W3098745759","https://openalex.org/W3143596294","https://openalex.org/W4233135949","https://openalex.org/W6603551166","https://openalex.org/W6674735981","https://openalex.org/W6676903177","https://openalex.org/W6678757208","https://openalex.org/W6680012447","https://openalex.org/W6683265229"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2146544734","https://openalex.org/W2075222291"],"abstract_inverted_index":{"Topic":[0,121],"modeling":[1,31,58,70,122],"can":[2,154,165,206,253],"reveal":[3],"the":[4,26,55,81,86,92,111,140,149,161,244],"latent":[5],"structure":[6],"of":[7,25,41,85,110,129,151,214,246],"text":[8,93],"data":[9],"and":[10,21,38,63,83,103,143,159,163,174,180,190,204,210,216,223,227,251],"is":[11,32,123],"useful":[12],"for":[13,52,108],"knowledge":[14],"discovery,":[15],"search":[16,235,256],"relevance":[17,236],"ranking,":[18],"document":[19],"classification,":[20],"so":[22],"on.":[23],"One":[24],"major":[27],"challenges":[28],"in":[29,43,157,212],"topic":[30,57,69],"to":[33,73,79,172],"deal":[34],"with":[35,135],"large":[36,39],"datasets":[37],"numbers":[40],"topics":[42,107,117,142,153,219,247],"real-world":[44,192],"applications.":[45],"In":[46,146],"this":[47,147],"paper,":[48],"we":[49],"investigate":[50],"techniques":[51],"scaling":[53],"up":[54],"non-probabilistic":[56,87],"approaches":[59],"such":[60],"as":[61,74,113,115,126],"RLSI":[62,173,178,209],"NMF.":[64],"We":[65,169],"propose":[66],"a":[67,127,131,187,191,234],"general":[68,132],"method,":[71],"referred":[72],"Group":[75,177,181],"Matrix":[76],"Factorization":[77],"(GMF),":[78],"enhance":[80],"scalability":[82,162,215],"efficiency":[84,164],"approaches.":[88],"GMF":[89,171],"assumes":[90],"that":[91,202,243],"documents":[94],"have":[95,228],"already":[96],"been":[97],"categorized":[98],"into":[99],"multiple":[100],"semantic":[101],"classes,":[102],"there":[104],"exist":[105],"class-specific":[106,141,152],"each":[109,195],"classes":[112],"well":[114],"shared":[116,144],"across":[118],"all":[119],"classes.":[120],"then":[124],"formalized":[125],"problem":[128],"minimizing":[130],"objective":[133],"function":[134],"regularizations":[136],"and/or":[137],"constraints":[138],"on":[139,186,233],"topics.":[145],"way,":[148],"learning":[150],"be":[155,166],"conducted":[156],"parallel,":[158],"thus":[160],"greatly":[167,207],"improved.":[168],"apply":[170],"NMF,":[175],"obtaining":[176],"(GRLSI)":[179],"NMF":[182,211],"(GNMF)":[183],"respectively.":[184],"Experiments":[185],"Wikipedia":[188],"dataset":[189],"web":[193],"dataset,":[194,237],"containing":[196,238],"about":[197],"3":[198],"million":[199],"documents,":[200],"show":[201,242],"GRLSI":[203,222,250],"GNMF":[205,224,252],"improve":[208,255],"terms":[213],"efficiency.":[217],"The":[218],"discovered":[220],"by":[221,249],"are":[225],"coherent":[226],"good":[229],"readability.":[230],"Further":[231],"experiments":[232],"30,000":[239],"labeled":[240],"queries,":[241],"use":[245],"learned":[248],"significantly":[254],"relevance.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}