{"id":"https://openalex.org/W2139956879","doi":"https://doi.org/10.1145/1014052.1014062","title":"A probabilistic framework for semi-supervised clustering","display_name":"A probabilistic framework for semi-supervised clustering","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2139956879","doi":"https://doi.org/10.1145/1014052.1014062","mag":"2139956879"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014062","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and 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/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":true,"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":"middle","author":{"id":"https://openalex.org/A5043706888","display_name":"Mikhail Bilenko","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":"Mikhail Bilenko","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":3,"corresponding_author_ids":["https://openalex.org/A5112572279"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":50.8341,"has_fulltext":false,"cited_by_count":816,"citation_normalized_percentile":{"value":0.99891271,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9984999895095825,"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":0.9984999895095825,"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":0.998199999332428,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9937999844551086,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.70937180519104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7031610608100891},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7028709650039673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5341467261314392},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34872138500213623},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3310384750366211}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.70937180519104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031610608100891},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7028709650039673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5341467261314392},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34872138500213623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3310384750366211}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1014052.1014062","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.121.5724","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.121.5724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.utdallas.edu/~kriehl/papers/semi-kdd-04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.2964","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.2964","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/semi-kdd-04.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.374.9940","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.374.9940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/kdd04/docs/p59.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.8650","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.8650","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/semi-kdd-04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335055","display_name":"Health and Medical Research Fund","ror":"https://ror.org/03qh32912"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522930108","https://openalex.org/W1554544485","https://openalex.org/W1564583583","https://openalex.org/W1596382552","https://openalex.org/W1660390307","https://openalex.org/W1790954942","https://openalex.org/W1852582905","https://openalex.org/W2020999234","https://openalex.org/W2048239613","https://openalex.org/W2048679005","https://openalex.org/W2049633694","https://openalex.org/W2061130579","https://openalex.org/W2073583237","https://openalex.org/W2096139825","https://openalex.org/W2096765209","https://openalex.org/W2097089247","https://openalex.org/W2099111195","https://openalex.org/W2102524069","https://openalex.org/W2107008379","https://openalex.org/W2114473842","https://openalex.org/W2117154949","https://openalex.org/W2117436816","https://openalex.org/W2123504323","https://openalex.org/W2127097022","https://openalex.org/W2127218421","https://openalex.org/W2127314673","https://openalex.org/W2134089414","https://openalex.org/W2136549265","https://openalex.org/W2136573752","https://openalex.org/W2150926065","https://openalex.org/W2153839362","https://openalex.org/W2159080219","https://openalex.org/W2159583439","https://openalex.org/W2164068772","https://openalex.org/W2164456230","https://openalex.org/W2295665070","https://openalex.org/W2560674852","https://openalex.org/W2567948266","https://openalex.org/W2591957553","https://openalex.org/W2912210943","https://openalex.org/W2963673689","https://openalex.org/W2994982620","https://openalex.org/W2999905431","https://openalex.org/W4246202668","https://openalex.org/W6631307971","https://openalex.org/W6637101025","https://openalex.org/W6675528751","https://openalex.org/W6758700058","https://openalex.org/W6771369255","https://openalex.org/W6827751043"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4290792893","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4205958290"],"abstract_inverted_index":{"Unsupervised":[0],"clustering":[1,38,68,109,135],"can":[2],"be":[3],"significantly":[4],"improved":[5],"using":[6],"supervision":[7,83],"in":[8],"the":[9,47,52,58,102,145,149,160,163],"form":[10],"of":[11,16,31,104,108,136,148,162],"pairwise":[12],"constraints,":[13],"i.e.,":[14],"pairs":[15],"instances":[17],"labeled":[18],"as":[19],"belonging":[20],"to":[21,49,56],"same":[22],"or":[23,55],"different":[24],"clusters.":[25],"In":[26],"recent":[27],"years,":[28],"a":[29,63,78,90,105],"number":[30],"algorithms":[32],"have":[33],"been":[34],"proposed":[35,164],"for":[36,66,81],"enhancing":[37],"quality":[39],"by":[40,138],"employing":[41],"such":[42],"supervision.":[43],"Such":[44],"methods":[45],"use":[46,103],"constraints":[48,95],"either":[50],"modify":[51],"objective":[53,141],"function,":[54],"learn":[57],"distance":[59,98,117],"measure.":[60],"We":[61,127],"propose":[62],"probabilistic":[64],"model":[65,88],"semi-supervised":[67,134],"based":[69],"on":[70,154],"Hidden":[71],"Markov":[72],"Random":[73],"Fields":[74],"(HMRFs)":[75],"that":[76,93,131],"provides":[77],"principled":[79],"framework":[80],"incorporating":[82],"into":[84],"prototype-based":[85],"clustering.":[86],"The":[87],"generalizes":[89],"previous":[91],"approach":[92],"combines":[94],"and":[96,100,118,120],"Euclidean":[97,116],"learning,":[99],"allows":[101],"broad":[106],"range":[107],"distortion":[110],"measures,":[111],"including":[112],"Bregman":[113],"divergences":[114],"(e.g.,":[115,124],"I-divergence)":[119],"directional":[121],"similarity":[122],"measures":[123],"cosine":[125],"similarity).":[126],"present":[128],"an":[129,140],"algorithm":[130],"performs":[132],"partitional":[133],"data":[137,157],"minimizing":[139],"function":[142],"derived":[143],"from":[144],"posterior":[146],"energy":[147],"HMRF":[150],"model.":[151],"Experimental":[152],"results":[153],"several":[155],"text":[156],"sets":[158],"demonstrate":[159],"advantages":[161],"framework.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":37},{"year":2017,"cited_by_count":41},{"year":2016,"cited_by_count":40},{"year":2015,"cited_by_count":60},{"year":2014,"cited_by_count":40},{"year":2013,"cited_by_count":59},{"year":2012,"cited_by_count":65}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}