{"id":"https://openalex.org/W2054283387","doi":"https://doi.org/10.1587/transinf.2014edp7108","title":"Efficient K-Nearest Neighbor Graph Construction Using MapReduce for Large-Scale Data Sets","display_name":"Efficient K-Nearest Neighbor Graph Construction Using MapReduce for Large-Scale Data Sets","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2054283387","doi":"https://doi.org/10.1587/transinf.2014edp7108","mag":"2054283387"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2014edp7108","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7108","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/12/E97.D_2014EDP7108/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/12/E97.D_2014EDP7108/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079927684","display_name":"Tomohiro WARASHINA","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomohiro WARASHINA","raw_affiliation_strings":["Nara Institute of Science and Technology",", Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":", Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047879","display_name":"Kazuo Aoyama","orcid":"https://orcid.org/0000-0001-5578-842X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuo AOYAMA","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation","NTT Communication Science Laboratories, NTT Corporation,"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation,","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007032557","display_name":"Hiroshi Sawada","orcid":"https://orcid.org/0000-0002-4831-9286"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi SAWADA","raw_affiliation_strings":["NTT Service Evolution Laboratories, NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Service Evolution Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110795249","display_name":"Takashi Hattori","orcid":"https://orcid.org/0000-0003-1939-7530"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi HATTORI","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation","NTT Communication Science Laboratories, NTT Corporation,"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation,","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079927684"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.2944,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.56640246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"E97.D","issue":"12","first_page":"3142","last_page":"3154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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":0.9987999796867371,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9944999814033508,"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":0.8860846757888794},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7261478304862976},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5359834432601929},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44073933362960815},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4363759756088257},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40338370203971863},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39828646183013916},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35052257776260376},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18544965982437134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8860846757888794},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7261478304862976},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5359834432601929},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44073933362960815},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4363759756088257},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40338370203971863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39828646183013916},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35052257776260376},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18544965982437134},{"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":[{"id":"doi:10.1587/transinf.2014edp7108","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7108","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/12/E97.D_2014EDP7108/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005786403","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/7952","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"master thesis"}],"best_oa_location":{"id":"doi:10.1587/transinf.2014edp7108","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7108","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/12/E97.D_2014EDP7108/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2054283387.pdf","grobid_xml":"https://content.openalex.org/works/W2054283387.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1547566968","https://openalex.org/W1550211845","https://openalex.org/W1978112828","https://openalex.org/W1986693891","https://openalex.org/W1987819498","https://openalex.org/W1997020216","https://openalex.org/W2001141328","https://openalex.org/W2011430131","https://openalex.org/W2018378172","https://openalex.org/W2024930473","https://openalex.org/W2044936152","https://openalex.org/W2049003051","https://openalex.org/W2082042699","https://openalex.org/W2101999582","https://openalex.org/W2110026675","https://openalex.org/W2112090702","https://openalex.org/W2116762767","https://openalex.org/W2121456571","https://openalex.org/W2128678576","https://openalex.org/W2130502756","https://openalex.org/W2145607950","https://openalex.org/W2148606196","https://openalex.org/W2151930506","https://openalex.org/W2154879298","https://openalex.org/W2154956324","https://openalex.org/W2161854574","https://openalex.org/W2168649524","https://openalex.org/W2171960770","https://openalex.org/W2173213060","https://openalex.org/W4231146329","https://openalex.org/W4245252159"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2095886385","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2898214470"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,54,72,156,162],"efficient":[4,55,163],"method":[5,68,145,175],"using":[6],"Hadoop":[7,90,116],"MapReduce":[8,91,117,141,152],"for":[9,29,88,95,114],"constructing":[10],"a":[11,17,26,44,65,79,96,111,185],"K-nearest":[12],"neighbor":[13],"graph":[14,195],"(K-NNG)":[15],"from":[16],"large-scale":[18,45,168],"data":[19,27,30,46,98,137,169,186],"set.":[20],"K-NNG":[21,56],"has":[22],"been":[23],"utilized":[24],"as":[25],"structure":[28],"analysis":[31],"techniques":[32,42],"in":[33,182],"various":[34],"applications.":[35],"If":[36],"we":[37,52],"are":[38],"to":[39,43,107],"apply":[40],"the":[41,89,102,115,130,135,147,151,173,188,194],"set,":[47],"it":[48,122],"is":[49,64,76,93,105,119,180],"desirable":[50],"that":[51,69,101,172],"develop":[53],"construction":[57],"method.":[58],"We":[59],"focus":[60],"on":[61,78,167],"NN-Descent,":[62],"which":[63,154],"recently":[66],"proposed":[67,144,174],"efficiently":[70,178],"constructs":[71],"approximate":[73],"K-NNG.":[74],"NN-Descent":[75],"implemented":[77],"shared-memory":[80,103],"system":[81,104,126],"with":[82],"OpenMP-based":[83],"parallelization,":[84],"and":[85,134,161,179,193],"its":[86],"extension":[87,113],"framework":[92,118],"implied":[94],"larger":[97],"set":[99],"such":[100],"difficult":[106],"deal":[108],"with.":[109],"However,":[110],"simple":[112],"impractical":[120],"since":[121],"requires":[123],"extremely":[124],"high":[125,131],"performance":[127],"because":[128],"of":[129,140,184,190],"memory":[132],"consumption":[133],"low":[136],"transmission":[138],"efficiency":[139],"jobs.":[142],"The":[143],"relaxes":[146],"requirement":[148],"by":[149],"improving":[150],"jobs,":[153],"employs":[155],"appropriate":[157],"key-value":[158],"pair":[159],"format":[160],"sampling":[164],"strategy.":[165],"Experiments":[166],"sets":[170],"demonstrate":[171],"both":[176],"works":[177],"scalable":[181],"terms":[183],"size,":[187],"number":[189],"machine":[191],"nodes,":[192],"structural":[196],"parameter":[197],"K.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}