{"id":"https://openalex.org/W2295256067","doi":"https://doi.org/10.1145/1217299.1217303","title":"Clustering aggregation","display_name":"Clustering aggregation","publication_year":2007,"publication_date":"2007-03-01","ids":{"openalex":"https://openalex.org/W2295256067","doi":"https://doi.org/10.1145/1217299.1217303","mag":"2295256067"},"language":"en","primary_location":{"id":"doi:10.1145/1217299.1217303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1217299.1217303","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-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/A5022164041","display_name":"Aristides Gionis","orcid":"https://orcid.org/0000-0002-5211-112X"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Aristides Gionis","raw_affiliation_strings":["Yahoo! Research Labs, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013005096","display_name":"Heikki Mannila","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Heikki Mannila","raw_affiliation_strings":["University of Helsinki and Helsinki University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki and Helsinki University of Technology","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066962453","display_name":"Panayiotis Tsaparas","orcid":"https://orcid.org/0000-0002-3490-1507"},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis Tsaparas","raw_affiliation_strings":["Microsoft Search Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Search Labs","institution_ids":["https://openalex.org/I4210133358"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.0639,"has_fulltext":false,"cited_by_count":816,"citation_normalized_percentile":{"value":0.99655083,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"1","issue":"1","first_page":"4","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9945999979972839,"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"}},{"id":"https://openalex.org/T11502","display_name":"Facility Location and Emergency Management","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8662979602813721},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.7089567184448242},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.605025589466095},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.56447434425354},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.5531394481658936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5449349880218506},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5092190504074097},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.505488395690918},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5000367164611816},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.43180039525032043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3962230682373047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2646583616733551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22829678654670715}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8662979602813721},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.7089567184448242},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.605025589466095},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.56447434425354},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.5531394481658936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5449349880218506},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5092190504074097},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.505488395690918},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5000367164611816},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.43180039525032043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3962230682373047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2646583616733551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22829678654670715}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1217299.1217303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1217299.1217303","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.709.528","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.709.528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uoi.gr/%7Etsap/publications/aggregated.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.2890","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.2890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.helsinki.fi/u/gionis/papers/icde05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.98.369","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.98.369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.helsinki.fi/u/tsaparas/publications/aggregated-journal.pdf","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":29,"referenced_works":["https://openalex.org/W18428236","https://openalex.org/W100104462","https://openalex.org/W1524440898","https://openalex.org/W1560541823","https://openalex.org/W1571413698","https://openalex.org/W1985875030","https://openalex.org/W2017732166","https://openalex.org/W2027752285","https://openalex.org/W2051834357","https://openalex.org/W2057712948","https://openalex.org/W2073583237","https://openalex.org/W2084812512","https://openalex.org/W2085220035","https://openalex.org/W2091858563","https://openalex.org/W2097645701","https://openalex.org/W2128967345","https://openalex.org/W2130851950","https://openalex.org/W2135881767","https://openalex.org/W2140190241","https://openalex.org/W2143654071","https://openalex.org/W2150753219","https://openalex.org/W2158907148","https://openalex.org/W2167372977","https://openalex.org/W2168175751","https://openalex.org/W2169446650","https://openalex.org/W2801455852","https://openalex.org/W2914959486","https://openalex.org/W4255005259","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2390610678","https://openalex.org/W3140018618","https://openalex.org/W3146523624","https://openalex.org/W2188840951","https://openalex.org/W2241871771","https://openalex.org/W2171583777","https://openalex.org/W2555816786","https://openalex.org/W2407786351","https://openalex.org/W2897883632"],"abstract_inverted_index":{"We":[0,197,212],"consider":[1,161],"the":[2,21,43,57,68,86,92,98,108,117,129,145,151,158,174,177,182,188,191,207,219,222,226],"following":[3],"problem:":[4],"given":[5],"a":[6,11,54,81,104,125,136],"set":[7],"of":[8,42,56,88,94,110,128,138,144,153,166,176,190,221,225],"clusterings,":[9],"find":[10],"single":[12],"clustering":[13,26,36,44,55,89,130,148,155,193],"that":[14,72],"agrees":[15],"as":[16,18,53,80],"much":[17],"possible":[19],"with":[20],"input":[22,58],"clusterings.":[23],"This":[24],"problem,":[25,132],"aggregation":[27,45,75,131,149],",":[28],"appears":[29],"naturally":[30,114],"in":[31],"various":[32],"contexts.":[33],"For":[34],"example,":[35],"categorical":[37,48],"data":[38],"is":[39,113],"an":[40,214],"instance":[41],"problem;":[46],"each":[47],"attribute":[49],"can":[50,76,202],"be":[51,78,203],"viewed":[52],"rows":[59,61],"where":[60],"are":[62,162],"grouped":[63],"together":[64],"if":[65],"they":[66],"take":[67],"same":[69],"value":[70],"on":[71,173],"attribute.":[73],"Clustering":[74],"also":[77,198],"used":[79,204],"metaclustering":[82],"method":[83],"to":[84,205],"improve":[85],"robustness":[87],"by":[90,116],"combining":[91],"output":[93],"multiple":[95],"algorithms.":[96,139],"Furthermore,":[97],"problem":[99,152,194,223],"formulation":[100],"does":[101],"not":[102],"require":[103],"priori":[105],"information":[106],"about":[107],"number":[109,137],"clusters;":[111],"it":[112],"determined":[115],"optimization":[118],"function.":[119],"In":[120],"this":[121],"article,":[122],"we":[123,134,160,169,195],"give":[124,213],"formal":[126],"statement":[127],"and":[133,150,224],"propose":[135],"Our":[140,179],"algorithms":[141,208],"make":[142],"use":[143],"connection":[146],"between":[147],"correlation":[154,192],".":[156],"Although":[157],"problems":[159],"NP-hard,":[163],"for":[164,187,209],"several":[165],"our":[167],"methods,":[168],"provide":[170],"theoretical":[171],"guarantees":[172],"quality":[175],"solutions.":[178,227],"work":[180],"provides":[181],"best":[183],"deterministic":[184],"approximation":[185],"algorithm":[186],"variation":[189],"consider.":[196],"show":[199],"how":[200],"sampling":[201],"scale":[206],"large":[210],"datasets.":[211],"extensive":[215],"empirical":[216],"evaluation":[217],"demonstrating":[218],"usefulness":[220]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":51},{"year":2021,"cited_by_count":58},{"year":2020,"cited_by_count":54},{"year":2019,"cited_by_count":81},{"year":2018,"cited_by_count":87},{"year":2017,"cited_by_count":65},{"year":2016,"cited_by_count":72},{"year":2015,"cited_by_count":48},{"year":2014,"cited_by_count":39},{"year":2013,"cited_by_count":24},{"year":2012,"cited_by_count":23}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}