{"id":"https://openalex.org/W2605029335","doi":"https://doi.org/10.14778/3067421.3067425","title":"Local search methods for k-means with outliers","display_name":"Local search methods for k-means with outliers","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2605029335","doi":"https://doi.org/10.14778/3067421.3067425","mag":"2605029335"},"language":"en","primary_location":{"id":"doi:10.14778/3067421.3067425","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3067421.3067425","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5000180821","display_name":"Shalmoli Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shalmoli Gupta","raw_affiliation_strings":["University of Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101772779","display_name":"Ravi Kumar","orcid":"https://orcid.org/0000-0002-2203-2586"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Kumar","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064129575","display_name":"Kefu Lu","orcid":"https://orcid.org/0000-0003-0950-2616"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kefu Lu","raw_affiliation_strings":["Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044201440","display_name":"Benjamin Moseley","orcid":"https://orcid.org/0000-0001-8162-017X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Moseley","raw_affiliation_strings":["Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070795618","display_name":"Sergei Vassilvitskii","orcid":"https://orcid.org/0000-0003-0235-1624"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergei Vassilvitskii","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000180821"],"corresponding_institution_ids":["https://openalex.org/I2801919071"],"apc_list":null,"apc_paid":null,"fwci":8.9482,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.98155275,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"10","issue":"7","first_page":"757","last_page":"768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9728000164031982,"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/outlier","display_name":"Outlier","score":0.8504580855369568},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7645679712295532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.634925365447998},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5775779485702515},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5535599589347839},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5369484424591064},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48358529806137085},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47350436449050903},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4676997661590576},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4565460681915283},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4454590976238251},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42571038007736206},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.3594166338443756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29136547446250916}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8504580855369568},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7645679712295532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.634925365447998},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5775779485702515},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5535599589347839},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5369484424591064},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48358529806137085},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47350436449050903},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4676997661590576},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4565460681915283},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4454590976238251},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42571038007736206},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3594166338443756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29136547446250916},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3067421.3067425","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3067421.3067425","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1501500081","https://openalex.org/W1529111168","https://openalex.org/W1530581016","https://openalex.org/W1552339598","https://openalex.org/W1556344493","https://openalex.org/W1592237688","https://openalex.org/W1660133578","https://openalex.org/W1673310716","https://openalex.org/W1978906111","https://openalex.org/W1992419399","https://openalex.org/W1998901634","https://openalex.org/W2003719999","https://openalex.org/W2006685053","https://openalex.org/W2048974928","https://openalex.org/W2061122559","https://openalex.org/W2073459066","https://openalex.org/W2108399535","https://openalex.org/W2110105238","https://openalex.org/W2110784166","https://openalex.org/W2121737596","https://openalex.org/W2123297508","https://openalex.org/W2124536999","https://openalex.org/W2125543909","https://openalex.org/W2127468194","https://openalex.org/W2129281431","https://openalex.org/W2131220986","https://openalex.org/W2131687179","https://openalex.org/W2142827986","https://openalex.org/W2143077131","https://openalex.org/W2144182447","https://openalex.org/W2144405306","https://openalex.org/W2150593711","https://openalex.org/W2171125141","https://openalex.org/W2189949549","https://openalex.org/W2199495299","https://openalex.org/W2206925937","https://openalex.org/W2395916081","https://openalex.org/W2562836854","https://openalex.org/W3120740533","https://openalex.org/W4236385439","https://openalex.org/W4246396312","https://openalex.org/W4254420769","https://openalex.org/W6681368692"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W2171610853","https://openalex.org/W3144143113","https://openalex.org/W3022637481","https://openalex.org/W3120229345","https://openalex.org/W2491448268","https://openalex.org/W4390662392","https://openalex.org/W2394117789","https://openalex.org/W2160785859","https://openalex.org/W2390610678"],"abstract_inverted_index":{"We":[0,96],"study":[1],"the":[2,9,25,28,32,36,62,76,132,140],"problem":[3],"of":[4,11,20,27,38,43,59],"k":[5,79,91],"-means":[6,80,92],"clustering":[7,93],"in":[8,61],"presence":[10],"outliers.":[12,51,95],"The":[13],"goal":[14],"is":[15],"to":[16,23,31,113,115],"cluster":[17],"a":[18,40,57,85],"set":[19,42],"data":[21,44,63,117],"points":[22,29,45],"minimize":[24],"variance":[26],"assigned":[30],"same":[33],"cluster,":[34],"with":[35,53,94,109],"freedom":[37],"ignoring":[39],"small":[41],"that":[46,98,131],"can":[47,106],"be":[48,107],"labeled":[49],"as":[50],"Clustering":[52],"outliers":[54],"has":[55],"received":[56],"lot":[58],"attention":[60],"processing":[64],"community,":[65],"but":[66],"practical,":[67],"efficient,":[68],"and":[69,105,125],"provably":[70],"good":[71],"algorithms":[72],"remain":[73],"unknown":[74],"for":[75,90,139],"most":[77],"popular":[78],"objective.":[81],"Our":[82],"work":[83],"proposes":[84],"simple":[86],"local":[87],"search-based":[88],"algorithm":[89,100,133],"prove":[97],"this":[99],"achieves":[101],"constant-factor":[102],"approximate":[103],"solutions":[104],"combined":[108],"known":[110],"sketching":[111],"techniques":[112],"scale":[114],"large":[116],"sets.":[118],"Using":[119],"empirical":[120],"evaluation":[121],"on":[122],"both":[123],"synthetic":[124],"large-scale":[126],"real-world":[127],"data,":[128],"we":[129],"demonstrate":[130],"dominates":[134],"recently":[135],"proposed":[136],"heuristic":[137],"approaches":[138],"problem.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}