{"id":"https://openalex.org/W4400852077","doi":"https://doi.org/10.1145/3674508","title":"Large-Scale K-Clustering","display_name":"Large-Scale K-Clustering","publication_year":2024,"publication_date":"2024-07-20","ids":{"openalex":"https://openalex.org/W4400852077","doi":"https://doi.org/10.1145/3674508"},"language":"en","primary_location":{"id":"doi:10.1145/3674508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674508","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3674508","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015971004","display_name":"Konstantin Voevodski","orcid":"https://orcid.org/0000-0002-7518-8242"},"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":true,"raw_author_name":"Konstantin Voevodski","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015971004"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09042031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"9","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991999864578247,"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":0.9991999864578247,"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/T10057","display_name":"Face and Expression Recognition","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9922000169754028,"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":0.6416140198707581},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.571679949760437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4869919717311859},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4110153019428253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32493308186531067},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1669418215751648},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10613828897476196}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6416140198707581},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.571679949760437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4869919717311859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4110153019428253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32493308186531067},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1669418215751648},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10613828897476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674508","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3674508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674508","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1558625102","https://openalex.org/W1588576489","https://openalex.org/W1605211498","https://openalex.org/W1981773323","https://openalex.org/W2004931706","https://openalex.org/W2010410498","https://openalex.org/W2050516752","https://openalex.org/W2073459066","https://openalex.org/W2085751730","https://openalex.org/W2091684877","https://openalex.org/W2139841919","https://openalex.org/W2144335278","https://openalex.org/W2156499390","https://openalex.org/W2165420145","https://openalex.org/W2171394996","https://openalex.org/W2174175400","https://openalex.org/W2189949549","https://openalex.org/W2288539294","https://openalex.org/W2412340996","https://openalex.org/W2601251344","https://openalex.org/W2737365479","https://openalex.org/W2768882697","https://openalex.org/W2807006342","https://openalex.org/W2807926398","https://openalex.org/W2950664431","https://openalex.org/W3011209672","https://openalex.org/W3039616371","https://openalex.org/W3087124270","https://openalex.org/W3110446398","https://openalex.org/W3159624436","https://openalex.org/W3214634542","https://openalex.org/W4226459969","https://openalex.org/W4236385439","https://openalex.org/W4284968770","https://openalex.org/W4289674194","https://openalex.org/W4300027775","https://openalex.org/W4301520992","https://openalex.org/W4309299369","https://openalex.org/W6659205101","https://openalex.org/W6662778435","https://openalex.org/W6668990524","https://openalex.org/W6676483098","https://openalex.org/W6683136438","https://openalex.org/W6684992524","https://openalex.org/W6715131512","https://openalex.org/W6846669142"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Large-scale":[0],"learning":[1],"algorithms":[2,42,81],"are":[3,86],"essential":[4],"for":[5,43,58],"modern":[6],"data":[7,14],"collections":[8],"that":[9,48,72,74],"may":[10],"have":[11],"billions":[12],"of":[13,21,98],"points.":[15],"Here,":[16],"we":[17,68],"study":[18],"the":[19,28,55,99],"design":[20,39],"parallel":[22,41],"\\(k\\)":[23,29,31,34,76,79],"-clustering":[24],"algorithms,":[25],"which":[26],"include":[27],"-median,":[30],"-medoids,":[32],"and":[33,46,78],"-means":[35,80],"clustering":[36,60],"problems.":[37],"We":[38],"efficient":[40],"these":[44],"problems":[45],"prove":[47],"they":[49],"still":[50],"compute":[51],"constant-factor":[52],"approximations":[53],"to":[54,64,88],"optimal":[56],"solution":[57],"stable":[59],"instances.":[61],"In":[62],"addition":[63],"our":[65,75],"theoretic":[66],"results,":[67],"present":[69],"computational":[70],"experiments":[71],"show":[73],"-median":[77],"work":[82],"well":[83],"in":[84],"practice\u2014we":[85],"able":[87],"find":[89],"better":[90],"clusterings":[91],"than":[92],"state-of-the-art":[93],"coreset":[94],"constructions":[95],"using":[96],"samples":[97],"same":[100],"size.":[101]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}