{"id":"https://openalex.org/W2154879298","doi":"https://doi.org/10.1145/2247596.2247602","title":"Efficient parallel kNN joins for large data in MapReduce","display_name":"Efficient parallel kNN joins for large data in MapReduce","publication_year":2012,"publication_date":"2012-03-27","ids":{"openalex":"https://openalex.org/W2154879298","doi":"https://doi.org/10.1145/2247596.2247602","mag":"2154879298"},"language":"en","primary_location":{"id":"doi:10.1145/2247596.2247602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","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/A5088345153","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0003-1304-8209"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Florida State University"],"affiliations":[{"raw_affiliation_string":"Florida State University","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feifei Li","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064482744","display_name":"Jeffrey Jestes","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Jestes","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088345153"],"corresponding_institution_ids":["https://openalex.org/I103163165"],"apc_list":null,"apc_paid":null,"fwci":21.8,"has_fulltext":false,"cited_by_count":251,"citation_normalized_percentile":{"value":0.99690442,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"38","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9958999752998352,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.9269014000892639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8797904253005981},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7689058780670166},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5333768129348755},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47350695729255676},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4673754572868347},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4662885367870331},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40277862548828125},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3414733409881592}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9269014000892639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8797904253005981},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7689058780670166},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5333768129348755},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47350695729255676},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4673754572868347},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4662885367870331},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40277862548828125},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3414733409881592},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2247596.2247602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.178","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utah.edu/%7Elifeifei/papers/mrknnj.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1207900119","display_name":null,"funder_award_id":"IIS-1212310IIS-1200792","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W596485744","https://openalex.org/W1585614323","https://openalex.org/W1868886949","https://openalex.org/W1974871453","https://openalex.org/W1985635698","https://openalex.org/W1987403831","https://openalex.org/W2016854254","https://openalex.org/W2020572986","https://openalex.org/W2058458206","https://openalex.org/W2061601738","https://openalex.org/W2078528123","https://openalex.org/W2100325481","https://openalex.org/W2100344784","https://openalex.org/W2115079562","https://openalex.org/W2118021173","https://openalex.org/W2120787923","https://openalex.org/W2122465391","https://openalex.org/W2151663987","https://openalex.org/W2151930506","https://openalex.org/W2156504591","https://openalex.org/W2157057296","https://openalex.org/W2157234796","https://openalex.org/W2162709812","https://openalex.org/W2164331678","https://openalex.org/W2165329839","https://openalex.org/W2169628462","https://openalex.org/W4238594802","https://openalex.org/W6682198890"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W650102067","https://openalex.org/W3086237447","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W2622139626","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794"],"abstract_inverted_index":{"In":[0],"data":[1,70,80,104],"mining":[2],"applications":[3,55],"and":[4,6,42,126,151,165,167,177],"spatial":[5],"multimedia":[7],"databases,":[8],"a":[9,26,33,51,59,87,109],"useful":[10],"tool":[11],"is":[12,17,50,82,112],"the":[13,20,40,43,67,83,174],"kNN":[14,47,99,135],"join,":[15],"which":[16],"to":[18,57,71,97,131,169],"produce":[19],"k":[21],"nearest":[22],"neighbors":[23],"(NN),":[24],"from":[25],"dataset":[27,34],"S,":[28],"of":[29,69,89,158,160,179],"every":[30],"point":[31],"in":[32,62,66,108,129,148,162],"R.":[35],"Since":[36],"it":[37],"involves":[38],"both":[39,163],"join":[41],"NN":[44],"search,":[45],"performing":[46],"joins":[48,100,136],"efficiently":[49,101],"challenging":[52],"task.":[53],"Meanwhile,":[54],"continue":[56],"witness":[58],"quick":[60],"(exponential":[61],"some":[63],"cases)":[64],"increase":[65],"amount":[68],"be":[72],"processed.":[73],"A":[74],"popular":[75],"model":[76],"nowadays":[77],"for":[78],"large-scale":[79],"processing":[81],"shared-nothing":[84],"cluster":[85,111],"on":[86,102,137],"number":[88],"commodity":[90],"machines":[91],"using":[92,144],"MapReduce":[93,110,130],"[6].":[94],"Hence,":[95],"how":[96],"execute":[98],"large":[103,138,149],"that":[105,116],"are":[106],"stored":[107],"an":[113],"intriguing":[114],"problem":[115],"meets":[117],"many":[118],"practical":[119],"needs.":[120],"This":[121],"work":[122],"proposes":[123],"novel":[124],"(exact":[125],"approximate)":[127],"algorithms":[128],"perform":[132],"efficient":[133],"parallel":[134],"data.":[139],"We":[140],"demonstrate":[141],"our":[142,180],"ideas":[143],"Hadoop.":[145],"Extensive":[146],"experiments":[147],"real":[150],"synthetic":[152],"datasets,":[153],"with":[154],"tens":[155],"or":[156],"hundreds":[157],"millions":[159],"records":[161],"R":[164],"S":[166],"up":[168],"30":[170],"dimensions,":[171],"have":[172],"demonstrated":[173],"efficiency,":[175],"effectiveness,":[176],"scalability":[178],"methods.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":39},{"year":2015,"cited_by_count":39},{"year":2014,"cited_by_count":28},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}