{"id":"https://openalex.org/W2807006342","doi":"https://doi.org/10.1145/3219819.3219973","title":"Scalable k -Means Clustering via Lightweight Coresets","display_name":"Scalable k -Means Clustering via Lightweight Coresets","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2807006342","doi":"https://doi.org/10.1145/3219819.3219973","mag":"2807006342"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219973","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219973","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219973","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089890773","display_name":"Olivier Bachem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olivier Bachem","raw_affiliation_strings":["Google Brain Ð Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google Brain Ð Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430","https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044677020","display_name":"Mario Lu\u010di\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mario Lucic","raw_affiliation_strings":["Google Brain, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google Brain, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.44,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":90,"citation_normalized_percentile":{"value":0.999898,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9976,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9976,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9967,"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":0.9928,"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/embarrassingly-parallel","display_name":"Embarrassingly parallel","score":0.44989225}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.80830395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71221983},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.6557499},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6431711},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6186799},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5210897},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.44989225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4299545},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35990137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2529446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24314472},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.09515622},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219973","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219973","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1702.08248","pdf_url":"http://arxiv.org/pdf/1702.08248","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219973","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219973","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320307762","funder_display_name":"International Business Machines Corporation","award_id":"Ph.D. Fellowship"},{"funder":"https://openalex.org/F4320309327","funder_display_name":"Google","award_id":"Ph.D. Fellowship"},{"funder":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","award_id":"NRP 75 project 407540_167212"},{"funder":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council","award_id":"StG 307036"}],"datasets":[],"versions":[],"referenced_works_count":27,"referenced_works":["https://openalex.org/W10146634","https://openalex.org/W1556219185","https://openalex.org/W1622263187","https://openalex.org/W1977983731","https://openalex.org/W1981773323","https://openalex.org/W1991417304","https://openalex.org/W2045964207","https://openalex.org/W2061902728","https://openalex.org/W2073459066","https://openalex.org/W2084544490","https://openalex.org/W2094048240","https://openalex.org/W2101012814","https://openalex.org/W2146200992","https://openalex.org/W2164573470","https://openalex.org/W2171125141","https://openalex.org/W2405163282","https://openalex.org/W2601251344","https://openalex.org/W2739607959","https://openalex.org/W2787219950","https://openalex.org/W2962940989","https://openalex.org/W2963096809","https://openalex.org/W2963318518","https://openalex.org/W2964241723","https://openalex.org/W2964339896","https://openalex.org/W3150597598","https://openalex.org/W4247692611","https://openalex.org/W596522316"],"related_works":["https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W4242223894","https://openalex.org/W3148229873","https://openalex.org/W2366403280","https://openalex.org/W2150160875","https://openalex.org/W2091301346","https://openalex.org/W2074275975","https://openalex.org/W1517524280","https://openalex.org/W1495108544"],"abstract_inverted_index":{"\\emphCoresets":[0],"are":[1,14,102],"compact":[2],"representations":[3],"of":[4,56],"data":[5,23,39,147],"sets":[6],"such":[7],"that":[8,59,107,141],"models":[9,18,36],"trained":[10,19],"on":[11,20],"a":[12,53,69],"coreset":[13],"provably":[15],"competitive":[16],"with":[17],"the":[21,99,108,142],"full":[22],"set.":[24],"As":[25],"such,":[26],"they":[27],"have":[28],"been":[29],"successfully":[30],"used":[31,127],"to":[32,37,72,113,121,128],"scale":[33],"up":[34],"clustering":[35,79,117],"massive":[38],"sets.":[40],"While":[41],"existing":[42,94,122,146],"approaches":[43],"generally":[44],"only":[45],"allow":[46],"for":[47,61,76,132],"multiplicative":[48,63],"approximation":[49],"errors,":[50],"we":[51,139],"propose":[52],"novel":[54],"notion":[55],"lightweight":[57,74],"coresets":[58,75,101],"allows":[60],"both":[62],"and":[64,84,98,118],"additive":[65],"errors.":[66],"We":[67,104],"provide":[68],"single":[70],"algorithm":[71,89,144],"construct":[73],"k":[77,115],"-means":[78,116],"as":[80,82],"well":[81],"soft":[83],"hard":[85],"Bregman":[86],"clustering.":[87],"The":[88],"is":[90],"substantially":[91],"faster":[92],"than":[93],"constructions,":[95],"embarrassingly":[96],"parallel,":[97],"resulting":[100],"smaller.":[103],"further":[105],"show":[106],"proposed":[109,143],"approach":[110],"naturally":[111],"generalizes":[112],"statistical":[114],"that,":[119],"compared":[120],"results,":[123],"it":[124],"can":[125],"be":[126],"compute":[129],"smaller":[130],"summaries":[131],"empirical":[133],"risk":[134],"minimization.":[135],"In":[136],"extensive":[137],"experiments,":[138],"demonstrate":[140],"outperforms":[145],"summarization":[148],"strategies":[149],"in":[150],"practice.":[151]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2807006342","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":8}],"updated_date":"2025-01-03T12:58:57.763507","created_date":"2018-06-13"}