{"id":"https://openalex.org/W2001411438","doi":"https://doi.org/10.1145/1277741.1277760","title":"Regularized clustering for documents","display_name":"Regularized clustering for documents","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2001411438","doi":"https://doi.org/10.1145/1277741.1277760","mag":"2001411438"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual 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/A5100455958","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-3462-8472"},"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":"Fei Wang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065063835","display_name":"Changshui Zhang","orcid":"https://orcid.org/0000-0002-8088-367X"},"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":"Changshui Zhang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455386","display_name":"Tao Li","orcid":"https://orcid.org/0000-0003-3113-6835"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Florida International University","FLORIDA INTERNATIONAL UNIVERSITY"],"affiliations":[{"raw_affiliation_string":"Florida International University","institution_ids":["https://openalex.org/I19700959"]},{"raw_affiliation_string":"FLORIDA INTERNATIONAL UNIVERSITY","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100455958"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.9043,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.97086076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9958999752998352,"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":0.8465673923492432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6982460618019104},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6224544048309326},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6111922860145569},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.5734514594078064},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.485617071390152},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4707382619380951},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41798681020736694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3897118866443634}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8465673923492432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6982460618019104},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6224544048309326},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6111922860145569},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.5734514594078064},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.485617071390152},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4707382619380951},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41798681020736694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3897118866443634}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1277741.1277760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.123.3627","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.123.3627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.fiu.edu/~taoli/pub/p95-wzL-sigir.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.1767","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.1767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.au.tsinghua.edu.cn/szll/bodao/zhangchangshui/bigeye/paper/wf_SIGIR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W1492327544","https://openalex.org/W1524688041","https://openalex.org/W1790954942","https://openalex.org/W1866611211","https://openalex.org/W1989368986","https://openalex.org/W1996764654","https://openalex.org/W2013029404","https://openalex.org/W2043545458","https://openalex.org/W2056763477","https://openalex.org/W2064580901","https://openalex.org/W2064742743","https://openalex.org/W2097308346","https://openalex.org/W2097645701","https://openalex.org/W2103829273","https://openalex.org/W2104290444","https://openalex.org/W2107887685","https://openalex.org/W2111953658","https://openalex.org/W2121947440","https://openalex.org/W2124890708","https://openalex.org/W2134737843","https://openalex.org/W2135674549","https://openalex.org/W2139850885","https://openalex.org/W2140942285","https://openalex.org/W2149148023","https://openalex.org/W2152322845","https://openalex.org/W2154455818","https://openalex.org/W2155754954","https://openalex.org/W2156909104","https://openalex.org/W2165874743","https://openalex.org/W2571268788","https://openalex.org/W2799061466","https://openalex.org/W2990138404","https://openalex.org/W2999905431","https://openalex.org/W3119651796","https://openalex.org/W4241122026","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1482912984","https://openalex.org/W2899601636","https://openalex.org/W3015674157","https://openalex.org/W4385270139","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2375068342","https://openalex.org/W3080491161","https://openalex.org/W2111119584","https://openalex.org/W2019737068"],"abstract_inverted_index":{"In":[0,30],"recent":[1],"years,":[2],"document":[3,20,61,133],"clustering":[4,39,47,134],"has":[5],"been":[6],"receiving":[7],"more":[8,10],"and":[9,15,24,63,83],"attentions":[11],"as":[12],"an":[13],"important":[14],"fundamental":[16],"technique":[17],"for":[18,38,59],"unsupervised":[19],"organization,":[21],"automatictopic":[22],"extraction,":[23],"fast":[25],"information":[26],"retrieval":[27],"or":[28],"filtering.":[29],"this":[31],"paper,":[32],"we":[33,76],"propose":[34],"a":[35,53,71,104],"novel":[36],"method":[37,50],"documents":[40,96],"using":[41],"regularization.":[42],"Unlike":[43],"traditional":[44,132],"globally":[45],"regularized":[46,55],"methods,":[48],"our":[49,78,117],"first":[51],"construct":[52],"local":[54,68],"linear":[56],"label":[57],"predictor":[58],"each":[60],"vector,":[62],"then":[64],"combine":[65],"all":[66],"those":[67],"regularizers":[69],"with":[70,81],"global":[72],"smoothness":[73],"regularizer.":[74],"So":[75],"call":[77],"algorithm":[79],"Clustering":[80],"Local":[82],"Global":[84],"Regularization":[85],"(CLGR).":[86],"We":[87],"will":[88],"show":[89,126],"that":[90],"the":[91,95,127],"cluster":[92],"memberships":[93],"of":[94,103,129],"can":[97,109],"be":[98,110],"achieved":[99],"by":[100,113],"eigenvalue":[101],"decomposition":[102],"sparse":[105],"symmetric":[106],"matrix,":[107],"which":[108],"efficiently":[111],"solved":[112],"iterative":[114],"methods.":[115,135],"Finally":[116],"experimental":[118],"evaluations":[119],"on":[120],"several":[121],"datasets":[122],"are":[123],"presented":[124],"to":[125],"superiorities":[128],"CLGR":[130],"over":[131]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}