{"id":"https://openalex.org/W2142838865","doi":"https://doi.org/10.1145/1772690.1772862","title":"Web-scale k-means clustering","display_name":"Web-scale k-means clustering","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2142838865","doi":"https://doi.org/10.1145/1772690.1772862","mag":"2142838865"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","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/A5055928795","display_name":"D. Sculley","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":true,"raw_author_name":"D. Sculley","raw_affiliation_strings":["Google, Inc., Pittsburgh, PA, USA","[Google Inc., Pittsburgh, PA, USA]"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Inc., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055928795"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":8.7282,"has_fulltext":false,"cited_by_count":1118,"citation_normalized_percentile":{"value":0.98202013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1177","last_page":"1178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.996399998664856,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.996399998664856,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.7860658764839172},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7845949530601501},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.723561704158783},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5769405364990234},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.546790599822998},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5445712804794312},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4772229492664337},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.46799203753471375},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4666196405887604},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38205140829086304},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36701324582099915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18612554669380188},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17641067504882812},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09345945715904236},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08524718880653381},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0780394971370697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860658764839172},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7845949530601501},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.723561704158783},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5769405364990234},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.546790599822998},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5445712804794312},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4772229492664337},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.46799203753471375},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4666196405887604},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38205140829086304},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36701324582099915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18612554669380188},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17641067504882812},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09345945715904236},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08524718880653381},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0780394971370697},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1772690.1772862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1542270631","https://openalex.org/W1978259121","https://openalex.org/W2048178552","https://openalex.org/W2115665694","https://openalex.org/W2150102617","https://openalex.org/W2171852577","https://openalex.org/W4212774754","https://openalex.org/W6662332321"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W3020853991","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776"],"abstract_inverted_index":{"We":[0],"present":[1],"two":[2],"modifications":[3],"to":[4,10,45],"the":[5,12,28,46,75],"popular":[6],"k-means":[7,34],"clustering":[8],"algorithm":[9,49],"address":[11],"extreme":[13],"requirements":[14],"for":[15,33],"latency,":[16],"scalability,":[17],"and":[18,68],"sparsity":[19,63],"encountered":[20],"in":[21],"user-facing":[22],"web":[23],"applications.":[24],"First,":[25],"we":[26,61],"propose":[27],"use":[29],"of":[30,42],"mini-batch":[31],"optimization":[32],"clustering.":[35],"This":[36],"reduces":[37],"computation":[38],"cost":[39],"by":[40],"orders":[41],"magnitude":[43],"compared":[44],"classic":[47],"batch":[48],"while":[50],"yielding":[51],"significantly":[52],"better":[53],"solutions":[54],"than":[55],"online":[56],"stochastic":[57],"gradient":[58,66],"descent.":[59],"Second,":[60],"achieve":[62],"with":[64],"projected":[65],"descent,":[67],"give":[69],"a":[70],"fast":[71],"\u03b5-accurate":[72],"projection":[73],"onto":[74],"L1-ball.":[76],"Source":[77],"code":[78],"is":[79],"freely":[80],"available:":[81],"http://code.google.com/p/sofia-ml":[82]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":88},{"year":2024,"cited_by_count":103},{"year":2023,"cited_by_count":135},{"year":2022,"cited_by_count":130},{"year":2021,"cited_by_count":130},{"year":2020,"cited_by_count":124},{"year":2019,"cited_by_count":109},{"year":2018,"cited_by_count":71},{"year":2017,"cited_by_count":65},{"year":2016,"cited_by_count":52},{"year":2015,"cited_by_count":38},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}