{"id":"https://openalex.org/W2096100960","doi":"https://doi.org/10.1145/1015330.1015360","title":"Integrating constraints and metric learning in semi-supervised clustering","display_name":"Integrating constraints and metric learning in semi-supervised clustering","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2096100960","doi":"https://doi.org/10.1145/1015330.1015360","mag":"2096100960"},"language":"en","primary_location":{"id":"doi:10.1145/1015330.1015360","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","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/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":true,"raw_author_name":"Mikhail Bilenko","raw_affiliation_strings":["University of Texas at Austin, Austin, TX","Univ. of Texas at Austin, Austin TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Univ. 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","Univ. of Texas at Austin, Austin TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Univ. 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","Univ. of Texas at Austin, Austin TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Univ. 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/A5043706888"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":39.2809,"has_fulltext":false,"cited_by_count":849,"citation_normalized_percentile":{"value":0.99806239,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9973000288009644,"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":0.9973000288009644,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9919000267982483,"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":0.8524019718170166},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.6902433633804321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6874818801879883},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.6388363838195801},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.605873703956604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6023087501525879},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.555576503276825},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5444345474243164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5389827489852905},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5351141095161438},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5222542881965637},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.5094285607337952},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5076788663864136},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4418630301952362},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4343239963054657},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4323423504829407},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.41338372230529785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41306138038635254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2252063751220703},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08925703167915344}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8524019718170166},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.6902433633804321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6874818801879883},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.6388363838195801},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.605873703956604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6023087501525879},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.555576503276825},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5444345474243164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5389827489852905},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5351141095161438},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5222542881965637},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.5094285607337952},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5076788663864136},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4418630301952362},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4343239963054657},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4323423504829407},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.41338372230529785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41306138038635254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2252063751220703},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08925703167915344},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1015330.1015360","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.5745","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.5745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aicml.cs.ualberta.ca/banff04/icml/pages/papers/119.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.3608","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.3608","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-icml-04.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1486632395","https://openalex.org/W1564583583","https://openalex.org/W1572493009","https://openalex.org/W1596382552","https://openalex.org/W1949708275","https://openalex.org/W2084812512","https://openalex.org/W2102524069","https://openalex.org/W2117154949","https://openalex.org/W2118393783","https://openalex.org/W2134089414","https://openalex.org/W2136549265","https://openalex.org/W2139956879","https://openalex.org/W2159583439","https://openalex.org/W2164456230","https://openalex.org/W2295665070","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3146523624","https://openalex.org/W2160785859","https://openalex.org/W2622412490","https://openalex.org/W2241871771","https://openalex.org/W2407786351","https://openalex.org/W2555816786","https://openalex.org/W3011266291","https://openalex.org/W2390610678","https://openalex.org/W3140018618","https://openalex.org/W2607137685"],"abstract_inverted_index":{"Semi-supervised":[0],"clustering":[1,33,56,74,107],"employs":[2],"a":[3,36,71,83],"small":[4],"amount":[5],"of":[6,24,39,79],"labeled":[7],"data":[8,21],"to":[9],"aid":[10],"unsupervised":[11],"learning.":[12],"Previous":[13],"work":[14],"in":[15,22,82],"the":[16,32,40,49,55,64,91],"area":[17],"has":[18],"utilized":[19],"supervised":[20],"one":[23],"two":[25,65],"approaches:":[26],"1)":[27],"constraint-based":[28],"methods":[29,46,62],"that":[30,47,76,90],"guide":[31],"algorithm":[34,75],"towards":[35],"better":[37,95],"grouping":[38],"data,":[41],"and":[42],"2)":[43],"distance-function":[44],"learning":[45],"adapt":[48],"underlying":[50],"similarity":[51],"metric":[52],"used":[53],"by":[54],"algorithm.":[57],"This":[58],"paper":[59],"provides":[60],"new":[61,72],"for":[63],"approaches":[66,100],"as":[67,69,101,103],"well":[68,102],"presents":[70],"semi-supervised":[73,106],"integrates":[77],"both":[78,98],"these":[80],"techniques":[81],"uniform,":[84],"principled":[85],"framework.":[86],"Experimental":[87],"results":[88],"demonstrate":[89],"unified":[92],"approach":[93],"produces":[94],"clusters":[96],"than":[97],"individual":[99],"previously":[104],"proposed":[105],"algorithms.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":45},{"year":2018,"cited_by_count":47},{"year":2017,"cited_by_count":47},{"year":2016,"cited_by_count":47},{"year":2015,"cited_by_count":62},{"year":2014,"cited_by_count":51},{"year":2013,"cited_by_count":62},{"year":2012,"cited_by_count":47}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}