{"id":"https://openalex.org/W2110553125","doi":"https://doi.org/10.1145/1376916.1376944","title":"Approximation algorithms for clustering uncertain data","display_name":"Approximation algorithms for clustering uncertain data","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W2110553125","doi":"https://doi.org/10.1145/1376916.1376944","mag":"2110553125"},"language":"en","primary_location":{"id":"doi:10.1145/1376916.1376944","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376916.1376944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-seventh ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","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/A5031896681","display_name":"Graham Cormode","orcid":"https://orcid.org/0000-0002-0698-0922"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Graham Cormode","raw_affiliation_strings":["AT&T Labs, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT&T Labs, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101979548","display_name":"Andrew McGregor","orcid":"https://orcid.org/0000-0002-2124-160X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McGregor","raw_affiliation_strings":["UC San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031896681"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":18.6093,"has_fulltext":false,"cited_by_count":159,"citation_normalized_percentile":{"value":0.99511273,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"200"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.856595516204834},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7576003074645996},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.745699942111969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7386547327041626},{"id":"https://openalex.org/keywords/uncertain-data","display_name":"Uncertain data","score":0.5349902510643005},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4492751359939575},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.44799819588661194},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.42695891857147217},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4229500889778137},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4191626012325287},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40378037095069885},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3912619352340698},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.33523374795913696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22605067491531372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17916420102119446}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.856595516204834},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7576003074645996},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.745699942111969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386547327041626},{"id":"https://openalex.org/C2778865114","wikidata":"https://www.wikidata.org/wiki/Q7882489","display_name":"Uncertain data","level":2,"score":0.5349902510643005},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4492751359939575},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.44799819588661194},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.42695891857147217},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4229500889778137},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4191626012325287},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40378037095069885},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3912619352340698},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.33523374795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22605067491531372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17916420102119446},{"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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":2,"locations":[{"id":"doi:10.1145/1376916.1376944","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376916.1376944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-seventh ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8445","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/people/Cormode_Graham/library/publications/CormodeMcGregor08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W596522316","https://openalex.org/W1496151277","https://openalex.org/W1556911662","https://openalex.org/W1673310716","https://openalex.org/W1973264045","https://openalex.org/W1973266211","https://openalex.org/W1979253499","https://openalex.org/W1990368529","https://openalex.org/W2003207175","https://openalex.org/W2003719999","https://openalex.org/W2013089587","https://openalex.org/W2045964207","https://openalex.org/W2049633694","https://openalex.org/W2050290319","https://openalex.org/W2059651397","https://openalex.org/W2073459066","https://openalex.org/W2073583237","https://openalex.org/W2078686663","https://openalex.org/W2091283109","https://openalex.org/W2095897464","https://openalex.org/W2106582507","https://openalex.org/W2110105238","https://openalex.org/W2118224498","https://openalex.org/W2127218421","https://openalex.org/W2131687179","https://openalex.org/W2144342293","https://openalex.org/W2166916904","https://openalex.org/W2171125141","https://openalex.org/W2978337448","https://openalex.org/W4255776112"],"related_works":["https://openalex.org/W2491448268","https://openalex.org/W2559422900","https://openalex.org/W2892323093","https://openalex.org/W3144143113","https://openalex.org/W2394193399","https://openalex.org/W2181939267","https://openalex.org/W2390610678","https://openalex.org/W3071522575","https://openalex.org/W2363054820","https://openalex.org/W2101174895"],"abstract_inverted_index":{"There":[0],"is":[1,27,47,88,109],"an":[2],"increasing":[3],"quantity":[4],"of":[5,22,65,75,115,167,214],"data":[6,42,52,57,128],"with":[7,91,129],"uncertainty":[8,26],"arising":[9],"from":[10],"applications":[11],"such":[12,41,55],"as":[13,20,30,56],"sensor":[14],"network":[15],"measurements,":[16],"record":[17],"linkage,":[18],"and":[19,39,70,117,160,179,195],"output":[21],"mining":[23,63],"algorithms.":[24,170],"This":[25],"typically":[28],"formalized":[29],"probability":[31],"density":[32],"functions":[33],"over":[34],"tuple":[35],"values.":[36],"Beyond":[37],"storing":[38],"processing":[40],"in":[43,135],"a":[44,86,102,165,181,197],"DBMS,":[45],"it":[46,97,108],"necessary":[48],"to":[49,101,122,186],"perform":[50],"other":[51],"analysis":[53],"tasks":[54],"mining.":[58],"We":[59,163],"study":[60],"the":[61,136,144,187,205,212],"core":[62],"problem":[64],"clustering":[66,77,215],"on":[67,84,127],"uncertain":[68,113,153,189,216],"data,":[69],"define":[71],"appropriate":[72],"natural":[73],"generalizations":[74],"standard":[76],"optimization":[78],"criteria.":[79],"Two":[80],"variations":[81],"arise,":[82],"depending":[83],"whether":[85,96],"point":[87],"automatically":[89],"associated":[90],"its":[92],"optimal":[93],"center,":[94],"or":[95],"must":[98],"be":[99],"assigned":[100,145],"fixed":[103],"cluster":[104],"no":[105,130],"matter":[106],"where":[107],"actually":[110],"located.":[111],"For":[112],"versions":[114,126],"k-means":[116],"k-median,":[118],"we":[119],"show":[120,164],"reductions":[121],"their":[123],"corresponding":[124],"weighted":[125],"uncertainties.":[131],"These":[132],"are":[133,151,204],"simple":[134],"unassigned":[137],"case,":[138],"but":[139],"require":[140],"some":[141],"care":[142],"for":[143,152,211],"version.":[146],"Our":[147],"most":[148],"interesting":[149],"results":[150,203],"k-center,":[154],"which":[155],"generalizes":[156],"both":[157],"traditional":[158],"k-center":[159],"k-median":[161],"objectives.":[162],"variety":[166],"bicriteria":[168],"approximation":[169,185,209],"One":[171],"picks":[172,192],"O(k\u025b":[173],"\u22121":[174],"log":[175],"2":[176],"n)":[177],"centers":[178,194],"achieves":[180,196],"(1":[182],"+":[183],"\u025b)":[184],"best":[188],"k-centers.":[190],"Another":[191],"2k":[193],"constant":[198],"factor":[199],"approximation.":[200],"Collectively,":[201],"these":[202],"first":[206],"known":[207],"guaranteed":[208],"algorithms":[210],"problems":[213],"data.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}