{"id":"https://openalex.org/W2062723323","doi":"https://doi.org/10.1145/2556195.2556260","title":"Scalable K-Means by ranked retrieval","display_name":"Scalable K-Means by ranked retrieval","publication_year":2014,"publication_date":"2014-02-18","ids":{"openalex":"https://openalex.org/W2062723323","doi":"https://doi.org/10.1145/2556195.2556260","mag":"2062723323"},"language":"en","primary_location":{"id":"doi:10.1145/2556195.2556260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search and data mining","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/A5108541542","display_name":"Andrei Broder","orcid":null},"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":"Andrei Broder","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014833056","display_name":"Llu\u00eds Garcia-Pueyo","orcid":"https://orcid.org/0000-0002-3278-2997"},"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":"Lluis Garcia-Pueyo","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037908462","display_name":"Vanja Josifovski","orcid":null},"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":"Vanja Josifovski","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111786995","display_name":"Srihari Venkatesan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srihari Venkatesan","raw_affiliation_strings":["xAd, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"xAd, Sunnyvale, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8972,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.96849135,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9976999759674072,"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":0.8042762279510498},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7800779938697815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6980513334274292},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6727777719497681},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6360602378845215},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5781318545341492},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5717332363128662},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32719117403030396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23668524622917175},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13977301120758057}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8042762279510498},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7800779938697815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980513334274292},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6727777719497681},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6360602378845215},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5781318545341492},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5717332363128662},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32719117403030396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23668524622917175},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13977301120758057},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2556195.2556260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.684.1458","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.684.1458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/42853.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":43,"referenced_works":["https://openalex.org/W1496881388","https://openalex.org/W1522930108","https://openalex.org/W1585610988","https://openalex.org/W1660390307","https://openalex.org/W1967187838","https://openalex.org/W1998739300","https://openalex.org/W1999668761","https://openalex.org/W2006533296","https://openalex.org/W2038276547","https://openalex.org/W2065472179","https://openalex.org/W2073459066","https://openalex.org/W2077442640","https://openalex.org/W2091684877","https://openalex.org/W2097776316","https://openalex.org/W2098876286","https://openalex.org/W2100369465","https://openalex.org/W2108399535","https://openalex.org/W2118190603","https://openalex.org/W2125203709","https://openalex.org/W2132958733","https://openalex.org/W2138662031","https://openalex.org/W2142838865","https://openalex.org/W2150593711","https://openalex.org/W2151242668","https://openalex.org/W2154610494","https://openalex.org/W2154714154","https://openalex.org/W2156499390","https://openalex.org/W2161160262","https://openalex.org/W2166999932","https://openalex.org/W2171852577","https://openalex.org/W2199495299","https://openalex.org/W2295820528","https://openalex.org/W2341171179","https://openalex.org/W2604272474","https://openalex.org/W2950437976","https://openalex.org/W4236385439","https://openalex.org/W6631307971","https://openalex.org/W6637101025","https://openalex.org/W6668990524","https://openalex.org/W6677939283","https://openalex.org/W6683136438","https://openalex.org/W6685529966","https://openalex.org/W6704298589"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2011430815","https://openalex.org/W4321606653"],"abstract_inverted_index":{"The":[0,32],"k-means":[1,72,123],"clustering":[2,19,116],"algorithm":[3,73],"has":[4],"a":[5,9,83],"long":[6],"history":[7],"and":[8,108],"proven":[10],"practical":[11],"performance,":[12],"however":[13],"it":[14],"does":[15],"not":[16],"scale":[17],"to":[18,39,66,104,112],"millions":[20],"of":[21,26,56,70,85,121],"data":[22,46,91],"points":[23],"into":[24],"thousands":[25],"clusters":[27,57],"in":[28],"high":[29],"dimensional":[30],"spaces.":[31],"main":[33],"computational":[34],"bottleneck":[35],"is":[36,58,99],"the":[37,41,54,68,71,93,115,122],"need":[38],"recompute":[40],"nearest":[42],"centroid":[43],"for":[44],"every":[45,49],"point":[47],"at":[48],"iteration,":[50],"aprohibitive":[51],"cost":[52,69],"when":[53],"number":[55],"large.":[59],"In":[60],"this":[61],"paper":[62],"we":[63],"show":[64],"how":[65],"reduce":[67],"by":[74,77],"large":[75],"factors":[76],"adapting":[78],"ranked":[79],"retrieval":[80],"techniques.":[81],"Using":[82],"combination":[84],"heuristics,":[86],"on":[87],"two":[88],"real":[89],"life":[90],"sets":[92],"wall":[94],"clock":[95],"time":[96],"per":[97],"iteration":[98],"reduced":[100],"from":[101,109],"445":[102],"minutes":[103,111],"less":[105],"than":[106],"4,":[107],"705":[110],"1.4,":[113],"while":[114],"quality":[117],"remains":[118],"within":[119],"0.5%":[120],"quality.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}