{"id":"https://openalex.org/W2767385901","doi":"https://doi.org/10.1145/3132847.3133091","title":"Fast K-means for Large Scale Clustering","display_name":"Fast K-means for Large Scale Clustering","publication_year":2017,"publication_date":"2017-11-06","ids":{"openalex":"https://openalex.org/W2767385901","doi":"https://doi.org/10.1145/3132847.3133091","mag":"2767385901"},"language":"en","primary_location":{"id":"doi:10.1145/3132847.3133091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102016069","display_name":"Qinghao Hu","orcid":"https://orcid.org/0009-0007-5300-5787"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghao Hu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011348984","display_name":"Jiaxiang Wu","orcid":"https://orcid.org/0000-0001-9132-5625"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxiang Wu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101517110","display_name":"Lu Bai","orcid":"https://orcid.org/0000-0002-1033-8908"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Bai","raw_affiliation_strings":["Central University of Finance and Economics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central University of Finance and Economics, Beijing, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376972","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0003-4533-3880"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112149353","display_name":"Jian Cheng","orcid":"https://orcid.org/0000-0003-1289-2758"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cheng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2388,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.62137674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2099","last_page":"2102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/T10057","display_name":"Face and Expression Recognition","score":0.9944999814033508,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976259589195251},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7683641910552979},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5226143002510071},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5067499279975891},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"k-means clustering","score":0.4941921532154083},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46669700741767883},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.44405901432037354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4408465325832367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30521076917648315},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.2702770233154297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976259589195251},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7683641910552979},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5226143002510071},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5067499279975891},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.4941921532154083},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46669700741767883},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.44405901432037354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4408465325832367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30521076917648315},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.2702770233154297},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3132847.3133091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7168708639","display_name":null,"funder_award_id":"61332016,61602535,61503422,61572500","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W118481696","https://openalex.org/W1624140875","https://openalex.org/W1893754589","https://openalex.org/W1907458443","https://openalex.org/W2010642153","https://openalex.org/W2012833704","https://openalex.org/W2124509324","https://openalex.org/W2141362318","https://openalex.org/W2142838865","https://openalex.org/W2171852577","https://openalex.org/W2211964529","https://openalex.org/W2618530766"],"related_works":["https://openalex.org/W3088133960","https://openalex.org/W3144143113","https://openalex.org/W2393707058","https://openalex.org/W3022637481","https://openalex.org/W3174322327","https://openalex.org/W2170078080","https://openalex.org/W2371010743","https://openalex.org/W2607902515","https://openalex.org/W3120229345","https://openalex.org/W1584028106"],"abstract_inverted_index":{"K-means":[0],"algorithm":[1,23,51,70,108,118],"has":[2],"been":[3],"widely":[4],"used":[5],"in":[6,96],"machine":[7],"learning":[8],"and":[9,16],"data":[10,32],"mining":[11],"due":[12],"to":[13,85,112],"its":[14],"simplicity":[15],"good":[17],"performance.":[18],"However,":[19],"the":[20,68,80,87,92,106,116],"standard":[21],"k-means":[22,50,54,69,117],"would":[24],"be":[25],"quite":[26],"slow":[27],"for":[28],"clustering":[29],"millions":[30],"of":[31,35,39,41],"into":[33],"thousands":[34,40],"or":[36],"even":[37],"tens":[38],"clusters.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"a":[48,58,72],"fast":[49],"named":[52],"multi-stage":[53,59,63],"(MKM)":[55],"which":[56,90],"uses":[57],"filtering":[60,64],"approach.":[61],"The":[62],"approach":[65],"greatly":[66],"accelerates":[67],"via":[71],"coarse-to-fine":[73],"search":[74],"strategy.":[75],"To":[76],"further":[77],"speed":[78],"up":[79,111],"algorithm,":[81],"hashing":[82],"is":[83,91],"introduced":[84],"accelerate":[86],"assignment":[88],"step":[89],"most":[93],"time-consuming":[94],"part":[95],"k-means.":[97],"Extensive":[98],"experiments":[99],"on":[100],"several":[101],"massive":[102],"datasets":[103],"show":[104],"that":[105],"proposed":[107],"can":[109],"obtain":[110],"600X":[113],"speed-up":[114],"over":[115],"with":[119],"comparable":[120],"accuracy.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}