{"id":"https://openalex.org/W2127097022","doi":"https://doi.org/10.1109/icdm.2003.1250966","title":"Information theoretic clustering of sparse cooccurrence data","display_name":"Information theoretic clustering of sparse cooccurrence data","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2127097022","doi":"https://doi.org/10.1109/icdm.2003.1250966","mag":"2127097022"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on 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/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I.S. Dhillon","raw_affiliation_strings":["Department of Computer Sciences, University of Technology, Austin, TX, USA","Dept. of Comput. Sci., Texas Univ., Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Technology, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Texas Univ., Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004682787","display_name":"Yuqiang Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. Guan","raw_affiliation_strings":["Department of Computer Sciences, University of Technology, Austin, TX, USA","Dept. of Comput. Sci., Texas Univ., Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Technology, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Texas Univ., Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5652,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98412189,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"517","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","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"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9944000244140625,"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":0.8429170846939087},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.7771762013435364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5988600850105286},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5063067674636841},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.46604812145233154},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45375844836235046},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.42251256108283997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3882077634334564},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35783812403678894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35208559036254883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31582111120224}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8429170846939087},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.7771762013435364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5988600850105286},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5063067674636841},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.46604812145233154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45375844836235046},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.42251256108283997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3882077634334564},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35783812403678894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35208559036254883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31582111120224},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdm.2003.1250966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.1704","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.1704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/inderjit/public_papers/itc_ieee.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.6479","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.6479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/ftp/pub/techreports/tr03-39.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.6600000262260437,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W2010425028","https://openalex.org/W2060314721","https://openalex.org/W2099111195","https://openalex.org/W2121853761","https://openalex.org/W2127097022","https://openalex.org/W2138570191","https://openalex.org/W2161877964","https://openalex.org/W2799061466","https://openalex.org/W4205687621","https://openalex.org/W6678973112","https://openalex.org/W6680765659"],"related_works":["https://openalex.org/W2036846997","https://openalex.org/W2112223184","https://openalex.org/W2347586617","https://openalex.org/W4385270139","https://openalex.org/W2161963661","https://openalex.org/W2125614474","https://openalex.org/W2295845123","https://openalex.org/W2358054814","https://openalex.org/W2090882960","https://openalex.org/W2889544313"],"abstract_inverted_index":{"A":[0,24],"novel":[1],"approach":[2],"to":[3,62,68,85,94,107],"clustering":[4,26,116,123],"cooccurrence":[5],"data":[6,42],"poses":[7],"it":[8],"as":[9,74],"an":[10],"optimization":[11],"problem":[12],"in":[13,21,49,75,115],"information":[14],"theory":[15],"which":[16,46],"minimizes":[17],"the":[18,50,76,110],"resulting":[19],"loss":[20,32],"mutual":[22],"information.":[23],"divisive":[25],"algorithm":[27,51,98],"that":[28,39,99,109],"monotonically":[29],"reduces":[30],"this":[31,63],"function":[33],"was":[34],"recently":[35],"proposed.":[36],"We":[37,58,103],"show":[38,108],"sparse":[40],"high-dimensional":[41],"presents":[43],"special":[44],"challenges":[45],"can":[47],"result":[48],"getting":[52],"stuck":[53],"at":[54],"poor":[55],"local":[56,83,87],"minima.":[57,88],"propose":[59],"two":[60],"solutions":[61,93],"problem:":[64],"(a)":[65],"a":[66,96],"\"prior\"":[67],"overcome":[69],"infinite":[70],"relative":[71],"entropy":[72],"values":[73],"supervised":[77],"Naive":[78],"Bayes":[79],"algorithm,":[80],"and":[81,119],"(b)":[82],"search":[84],"escape":[86],"Finally,":[89],"we":[90],"combine":[91],"these":[92],"get":[95],"robust":[97],"is":[100,113],"computationally":[101],"efficient.":[102],"present":[104],"experimental":[105],"results":[106],"proposed":[111],"method":[112],"effective":[114],"document":[117],"collections":[118],"outperform":[120],"previous":[121],"information-theoretic":[122],"approaches.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}