{"id":"https://openalex.org/W2144767994","doi":"https://doi.org/10.1145/1081870.1081932","title":"Model-based overlapping clustering","display_name":"Model-based overlapping clustering","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2144767994","doi":"https://doi.org/10.1145/1081870.1081932","mag":"2144767994"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081932","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in 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/A5014459472","display_name":"Arindam Banerjee","orcid":"https://orcid.org/0000-0002-7856-5699"},"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":true,"raw_author_name":"Arindam Banerjee","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837732","display_name":"Chase Krumpelman","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":"Chase Krumpelman","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103071668","display_name":"Joydeep Ghosh","orcid":"https://orcid.org/0000-0002-7366-3548"},"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":"Joydeep Ghosh","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112572279","display_name":"Sugato Basu","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":"Sugato Basu","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008715111","display_name":"Raymond J. Mooney","orcid":"https://orcid.org/0000-0002-4504-0490"},"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":"Raymond J. Mooney","raw_affiliation_strings":["University of Texas at Austin, Austin, TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014459472"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":15.0839,"has_fulltext":false,"cited_by_count":208,"citation_normalized_percentile":{"value":0.98957943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"532","last_page":"537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998000264167786,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998000264167786,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9965999722480774,"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/T11106","display_name":"Data Management and Algorithms","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8090238571166992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6443620920181274},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6060510873794556},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5912551879882812},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.55887371301651},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5027210712432861},{"id":"https://openalex.org/keywords/bregman-divergence","display_name":"Bregman divergence","score":0.49526920914649963},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.45982885360717773},{"id":"https://openalex.org/keywords/exponential-family","display_name":"Exponential family","score":0.44336646795272827},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4320526123046875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41961216926574707},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41505396366119385},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.40069395303726196},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3872010111808777},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3486708998680115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2952321171760559},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2428051233291626},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0802411437034607}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8090238571166992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6443620920181274},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6060510873794556},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5912551879882812},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.55887371301651},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5027210712432861},{"id":"https://openalex.org/C149073432","wikidata":"https://www.wikidata.org/wiki/Q4960382","display_name":"Bregman divergence","level":2,"score":0.49526920914649963},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.45982885360717773},{"id":"https://openalex.org/C55974624","wikidata":"https://www.wikidata.org/wiki/Q1188504","display_name":"Exponential family","level":2,"score":0.44336646795272827},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4320526123046875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41961216926574707},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41505396366119385},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.40069395303726196},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3872010111808777},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3486708998680115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2952321171760559},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2428051233291626},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0802411437034607},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1081870.1081932","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.3495","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.3495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lans.ece.utexas.edu/papers/banerjee05overlapping.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.8450","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.8450","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/ml/papers/moc-submitted-05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W16591383","https://openalex.org/W62192591","https://openalex.org/W292990780","https://openalex.org/W1493217831","https://openalex.org/W1493526108","https://openalex.org/W1494851074","https://openalex.org/W1501299699","https://openalex.org/W1520890006","https://openalex.org/W1528905581","https://openalex.org/W1540198634","https://openalex.org/W1546961578","https://openalex.org/W1561414385","https://openalex.org/W1593486402","https://openalex.org/W1774711529","https://openalex.org/W1790954942","https://openalex.org/W1920003194","https://openalex.org/W1970290925","https://openalex.org/W1975503278","https://openalex.org/W2004022680","https://openalex.org/W2010315317","https://openalex.org/W2018740085","https://openalex.org/W2049633694","https://openalex.org/W2096765209","https://openalex.org/W2110111529","https://openalex.org/W2119430004","https://openalex.org/W2126185296","https://openalex.org/W2127097022","https://openalex.org/W2135001774","https://openalex.org/W2138072998","https://openalex.org/W2139956879","https://openalex.org/W2144544802","https://openalex.org/W2252194958","https://openalex.org/W2322524800","https://openalex.org/W2976223356","https://openalex.org/W3015463134","https://openalex.org/W3143596294","https://openalex.org/W4254223024","https://openalex.org/W4285719527","https://openalex.org/W4301861531","https://openalex.org/W4302564868","https://openalex.org/W4388279027","https://openalex.org/W6611379484","https://openalex.org/W6629329278","https://openalex.org/W6635743399","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W2188840951","https://openalex.org/W4241767317","https://openalex.org/W2101637161","https://openalex.org/W2171610853","https://openalex.org/W2160785859","https://openalex.org/W1999117613","https://openalex.org/W2559422900","https://openalex.org/W3092684173","https://openalex.org/W2103650652","https://openalex.org/W1887359504"],"abstract_inverted_index":{"While":[0],"the":[1,73,79],"vast":[2],"majority":[3],"of":[4,29,50,66,96],"clustering":[5,39,61],"algorithms":[6],"are":[7],"partitional,":[8],"many":[9],"real":[10],"world":[11],"datasets":[12],"have":[13,23],"inherently":[14],"overlapping":[15,21,38,60],"clusters.":[16],"Several":[17],"approaches":[18],"to":[19,58],"finding":[20],"clusters":[22],"come":[24],"from":[25],"work":[26],"on":[27,64,89],"analysis":[28],"biological":[30],"datasets.":[31,100],"In":[32],"this":[33,84],"paper,":[34],"we":[35,55],"interpret":[36],"an":[37,59],"model":[40,62],"proposed":[41],"by":[42],"Segal":[43],"et":[44],"al.":[45],"[23]":[46],"as":[47,92,94],"a":[48],"generalization":[49],"Gaussian":[51],"mixture":[52],"models,":[53],"and":[54,72,86,98],"extend":[56],"it":[57],"based":[63],"mixtures":[65],"any":[67],"regular":[68],"exponential":[69],"family":[70],"distribution":[71],"corresponding":[74],"Bregman":[75],"divergence.":[76],"We":[77],"provide":[78],"necessary":[80],"algorithm":[81],"modifications":[82],"for":[83],"extension,":[85],"present":[87],"results":[88],"synthetic":[90],"data":[91],"well":[93],"subsets":[95],"20-Newsgroups":[97],"EachMovie":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":15}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}