{"id":"https://openalex.org/W2017841038","doi":"https://doi.org/10.1145/2623330.2623725","title":"Representative clustering of uncertain data","display_name":"Representative clustering of uncertain data","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2017841038","doi":"https://doi.org/10.1145/2623330.2623725","mag":"2017841038"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017299501","display_name":"Andreas Z\u00fcfle","orcid":"https://orcid.org/0000-0001-7001-4123"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Z\u00fcfle","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019401090","display_name":"Tobias Emrich","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Emrich","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037818442","display_name":"Klaus Arthur Schmid","orcid":"https://orcid.org/0000-0003-2880-0299"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Arthur Schmid","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045731304","display_name":"Nikos Mamoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nikos Mamoulis","raw_affiliation_strings":["University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047196019","display_name":"Arthur Zimek","orcid":"https://orcid.org/0000-0001-7713-4208"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arthur Zimek","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016653456","display_name":"Matthias Renz","orcid":"https://orcid.org/0000-0002-2024-7700"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Renz","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9987999796867371,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8748337030410767},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7039063572883606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6894088983535767},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5635592937469482},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5581844449043274},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5499057173728943},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5164316296577454},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.4833521544933319},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4764956831932068},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.46709129214286804},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.45547863841056824},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4382263422012329},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.43470126390457153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.292468786239624}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8748337030410767},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7039063572883606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894088983535767},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5635592937469482},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5581844449043274},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5499057173728943},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5164316296577454},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.4833521544933319},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4764956831932068},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.46709129214286804},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.45547863841056824},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4382263422012329},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.43470126390457153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.292468786239624},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2623330.2623725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.433.5403","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.433.5403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dbs.ifi.lmu.de/Publikationen/Papers/KDD14-Uncertain Clustering.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.646.4923","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.4923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://i.cs.hku.hk/~nikos/kdd14.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":63,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1493454437","https://openalex.org/W1496151277","https://openalex.org/W1505129060","https://openalex.org/W1512485814","https://openalex.org/W1574922246","https://openalex.org/W1673310716","https://openalex.org/W1813388215","https://openalex.org/W1963853643","https://openalex.org/W1969642980","https://openalex.org/W1972098431","https://openalex.org/W1978933387","https://openalex.org/W1987111416","https://openalex.org/W1992419399","https://openalex.org/W2007742516","https://openalex.org/W2011430131","https://openalex.org/W2017920586","https://openalex.org/W2018040777","https://openalex.org/W2020018978","https://openalex.org/W2029138824","https://openalex.org/W2030276074","https://openalex.org/W2034891989","https://openalex.org/W2035241283","https://openalex.org/W2044074944","https://openalex.org/W2049075975","https://openalex.org/W2052793325","https://openalex.org/W2070333970","https://openalex.org/W2078686663","https://openalex.org/W2085843229","https://openalex.org/W2086128349","https://openalex.org/W2088422262","https://openalex.org/W2098331493","https://openalex.org/W2100922564","https://openalex.org/W2103012681","https://openalex.org/W2106578604","https://openalex.org/W2106582507","https://openalex.org/W2108009586","https://openalex.org/W2116838486","https://openalex.org/W2120342618","https://openalex.org/W2121207090","https://openalex.org/W2125402103","https://openalex.org/W2127218421","https://openalex.org/W2129035130","https://openalex.org/W2130308858","https://openalex.org/W2133839490","https://openalex.org/W2137591261","https://openalex.org/W2138271690","https://openalex.org/W2140757415","https://openalex.org/W2155094138","https://openalex.org/W2156617549","https://openalex.org/W2169278414","https://openalex.org/W2341627671","https://openalex.org/W2402612973","https://openalex.org/W2432267564","https://openalex.org/W2999729612","https://openalex.org/W3120740533","https://openalex.org/W4233413206","https://openalex.org/W4235169531","https://openalex.org/W4300514788","https://openalex.org/W6638266167","https://openalex.org/W6646945327","https://openalex.org/W6672615329","https://openalex.org/W6674367641"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W3146523624","https://openalex.org/W3140018618","https://openalex.org/W2390610678","https://openalex.org/W2188840951","https://openalex.org/W2407786351","https://openalex.org/W2897883632","https://openalex.org/W2241871771","https://openalex.org/W2555816786","https://openalex.org/W3124860551"],"abstract_inverted_index":{"This":[0],"paper":[1],"targets":[2],"the":[3,77,82,85,103,128,137],"problem":[4],"of":[5,26,60,64,84,139],"computing":[6],"meaningful":[7],"clusterings":[8,121],"from":[9,127],"uncertain":[10,17,54],"data":[11,18],"sets.":[12],"Existing":[13],"methods":[14],"for":[15],"clustering":[16,22,83,98,131],"compute":[19],"a":[20,44,58,67,123],"single":[21],"without":[23],"any":[24,96],"indication":[25],"its":[27,110],"quality":[28,107],"and":[29,100],"reliability;":[30],"thus,":[31],"decisions":[32],"based":[33,46],"on":[34,47,52],"their":[35],"results":[36],"are":[37],"questionable.":[38],"In":[39,112],"this":[40],"paper,":[41],"we":[42],"describe":[43],"framework,":[45],"possible-worlds":[48],"semantics;":[49],"when":[50],"applied":[51],"an":[53],"dataset,":[55],"it":[56,101],"computes":[57],"set":[59],"representative":[61,120],"clusterings,":[62],"each":[63],"which":[65],"has":[66],"probabilistic":[68],"guarantee":[69],"not":[70],"to":[71,76,105],"exceed":[72],"some":[73],"maximum":[74],"distance":[75],"ground":[78,129],"truth":[79,130],"clustering,":[80],"i.e.,":[81],"actual":[86],"(but":[87],"unknown)":[88],"data.":[89],"Our":[90],"framework":[91],"can":[92],"be":[93],"combined":[94],"with":[95],"existing":[97,133],"algorithm":[99],"is":[102],"first":[104],"provide":[106],"guarantees":[108],"about":[109],"result.":[111],"addition,":[113],"our":[114,119],"experimental":[115],"evaluation":[116],"shows":[117],"that":[118],"have":[122],"much":[124],"smaller":[125],"deviation":[126],"than":[132],"approaches,":[134],"thus":[135],"reducing":[136],"effect":[138],"uncertainty.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}