{"id":"https://openalex.org/W2088269487","doi":"https://doi.org/10.1145/2448556.2448627","title":"A MapReduce-based filtering algorithm for vector similarity join","display_name":"A MapReduce-based filtering algorithm for vector similarity join","publication_year":2013,"publication_date":"2013-01-17","ids":{"openalex":"https://openalex.org/W2088269487","doi":"https://doi.org/10.1145/2448556.2448627","mag":"2088269487"},"language":"en","primary_location":{"id":"doi:10.1145/2448556.2448627","doi":"https://doi.org/10.1145/2448556.2448627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2448556.2448627","pdf_url":null,"source":{"id":"https://openalex.org/S4363608555","display_name":"International Conference on Ubiquitous Information Management and Communication (IMCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5053759078","display_name":"Byoungju Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoungju Yang","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039254529","display_name":"Jaeseok Myung","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeseok Myung","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015505425","display_name":"Sang\u2010Goo Lee","orcid":"https://orcid.org/0000-0003-0699-0765","observed_orcids":["https://orcid.org/0000-0003-0699-0765"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-goo Lee","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101481496","display_name":"Dong-Joo Lee","orcid":"https://orcid.org/0000-0002-0937-7643","observed_orcids":["https://orcid.org/0000-0002-0937-7643","https://orcid.org/0000-0003-0562-5643"]},"institutions":[{"id":"https://openalex.org/I4405259277","display_name":"Samsung Electronics (South Korea)","ror":"https://ror.org/020m7t761","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4405259277"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongjoo Lee","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Suwon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Suwon, Korea","institution_ids":["https://openalex.org/I4405259277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.116,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74670764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.4440999925136566,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.4440999925136566,"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/T11719","display_name":"Data Quality and Management","score":0.23229999840259552,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.15970000624656677,"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/mapreduce","display_name":"MapReduce","score":0.9010000228881836},{"id":"https://openalex.org/keywords/filtering-algorithms","display_name":"filtering algorithms","score":0.7680000066757202},{"id":"https://openalex.org/keywords/feature-vectors","display_name":"feature vectors","score":0.7120000123977661},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.5910000205039978},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239544987678528},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6880213022232056},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6859044432640076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6051217317581177},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4980597496032715},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4482925236225128},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4467867612838745},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.4144511818885803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3851689100265503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22824335098266602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16131532192230225},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2448556.2448627","doi":"https://doi.org/10.1145/2448556.2448627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2448556.2448627","pdf_url":null,"source":{"id":"https://openalex.org/S4363608555","display_name":"International Conference on Ubiquitous Information Management and Communication (IMCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4487608193","display_name":null,"funder_award_id":"20120005695","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1530303756","https://openalex.org/W2097184821","https://openalex.org/W2104599107","https://openalex.org/W2128017662","https://openalex.org/W2151930506"],"related_works":["https://openalex.org/W839173409","https://openalex.org/W2612161256","https://openalex.org/W2565984961","https://openalex.org/W2775634440","https://openalex.org/W3187487646","https://openalex.org/W2020967497","https://openalex.org/W2093050254","https://openalex.org/W2188179155","https://openalex.org/W101869314","https://openalex.org/W2544930775"],"abstract_inverted_index":{"Vector":[0,35,107],"Similarity":[1,36,108],"Join":[2,37],"is":[3,8,29,38,46],"a":[4,39,101],"fundamental":[5],"operation":[6],"that":[7,104,156],"utilized":[9],"in":[10],"data":[11],"cleaning":[12],"and":[13],"analysis.":[14],"Since":[15],"most":[16],"objects":[17,28],"can":[18],"be":[19],"represented":[20],"as":[21],"feature":[22],"vectors,":[23],"finding":[24],"similar":[25],"pairs":[26,135],"of":[27,51,54,114,125,136,150],"quite":[30],"an":[31],"important":[32],"task.":[33],"However,":[34],"heavy":[40],"computational":[41,61],"job,":[42],"because":[43],"its":[44,60],"complexity":[45],"proportional":[47],"to":[48,58,73,83,121,146],"the":[49,52,88,111,123,137,148],"square":[50],"number":[53,124],"vectors.":[55],"In":[56,71,96,110],"order":[57],"diminish":[59],"load,":[62],"many":[63],"filtering":[64,120],"techniques":[65],"have":[66,80],"been":[67,81],"proposed":[68],"so":[69],"far.":[70],"addition":[72],"that,":[74],"algorithms":[75],"for":[76],"distributed":[77],"systems":[78],"also":[79,91],"researched":[82],"manage":[84],"large":[85],"datasets.":[86],"But,":[87],"state-of-the-art":[89,160],"studies":[90],"suffer":[92],"from":[93,133],"voluminous":[94],"computations.":[95],"this":[97],"paper,":[98],"we":[99,117],"propose":[100],"MapReduce":[102,161],"algorithm":[103,158],"efficiently":[105],"executes":[106],"Join.":[109],"first":[112,138],"stage":[113,130],"our":[115,151,157],"algorithm,":[116],"use":[118],"prefix":[119],"reduce":[122],"candidate":[126,134],"pairs.":[127],"The":[128],"second":[129],"calculates":[131],"similarities":[132],"stage.":[139],"We":[140],"present":[141],"candidates":[142],"quantity":[143],"prediction":[144],"formulas":[145],"demonstrate":[147],"effectiveness":[149],"algorithm.":[152],"Experimental":[153],"results":[154],"show":[155],"outperforms":[159],"algorithms.":[162]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}