{"id":"https://openalex.org/W2614126964","doi":"https://doi.org/10.1109/icde.2017.21","title":"A Generic Method for Accelerating LSH-Based Similarity Join Processing (Extended Abstract)","display_name":"A Generic Method for Accelerating LSH-Based Similarity Join Processing (Extended Abstract)","publication_year":2017,"publication_date":"2017-04-01","ids":{"openalex":"https://openalex.org/W2614126964","doi":"https://doi.org/10.1109/icde.2017.21","mag":"2614126964"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2017.21","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2017.21","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 33rd International Conference on Data Engineering (ICDE)","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/A5050042433","display_name":"Chenyun Yu","orcid":"https://orcid.org/0000-0001-9774-1590"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chenyun Yu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071030042","display_name":"Sarana Nutanong","orcid":"https://orcid.org/0000-0003-1068-850X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sarana Nutanong","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724756","display_name":"Hangyu Li","orcid":"https://orcid.org/0000-0002-9659-3634"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hangyu Li","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390514","display_name":"Cong Wang","orcid":"https://orcid.org/0000-0003-0547-315X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064553444","display_name":"Xingliang Yuan","orcid":"https://orcid.org/0000-0002-3701-4946"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xingliang Yuan","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.04465913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9991999864578247,"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":0.9991999864578247,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9945999979972839,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9940000176429749,"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/join","display_name":"Join (topology)","score":0.8765921592712402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6859307289123535},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6084420680999756},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36686283349990845},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35375258326530457},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3345174789428711},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32486823201179504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1885097622871399},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16775453090667725},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07843726873397827}],"concepts":[{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8765921592712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859307289123535},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6084420680999756},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36686283349990845},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35375258326530457},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3345174789428711},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32486823201179504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1885097622871399},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16775453090667725},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07843726873397827},{"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:10.1109/icde.2017.21","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2017.21","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 33rd International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2294518132","https://openalex.org/W2566913073","https://openalex.org/W6731527723"],"related_works":["https://openalex.org/W4205996836","https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W2093960938","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4248476017","https://openalex.org/W2807741550","https://openalex.org/W2964879389","https://openalex.org/W2970426051"],"abstract_inverted_index":{"Locality":[0],"sensitive":[1],"hashing":[2],"(LSH)":[3],"is":[4],"an":[5],"efficient":[6],"method":[7,57,73,98,129,176],"for":[8,118,142,194],"solving":[9],"the":[10,29,36,47,60,76,87,102,109,125,133,146,178,199],"problem":[11],"of":[12,38,49,62,71,82,89,104,127,174,198],"approximate":[13],"similarity":[14,23,151],"search":[15],"in":[16,28,75],"high-dimensional":[17,22],"spaces.":[18],"Through":[19],"LSH,":[20],"a":[21,55,80],"join":[24],"can":[25,99,136],"be":[26,137],"processed":[27],"same":[30,110,134],"way":[31,77],"as":[32],"hash":[33],"join,":[34],"making":[35],"cost":[37],"joining":[39,63],"two":[40,64],"large":[41,65],"datasets":[42,66,165],"linear.":[43],"By":[44],"judicially":[45],"analyzing":[46],"properties":[48],"multiple":[50],"LSH":[51,90,116,140,180,192],"algorithms,":[52],"we":[53,78,123,187],"propose":[54],"generic":[56],"to":[58,85,114,139,182,190],"accelerate":[59],"process":[61],"using":[67,163],"LSH.":[68],"The":[69],"crux":[70],"our":[72,96,128,167,175],"lies":[74],"identify":[79],"set":[81],"representative":[83],"points":[84],"reduce":[86,101],"number":[88,103],"lookups.":[91],"Theoretical":[92],"analyses":[93,169],"show":[94,171],"that":[95,132],"proposed":[97],"greatly":[100],"lookup":[105],"operations":[106],"and":[107,154,170],"retain":[108],"result":[111],"accuracy":[112],"compared":[113],"executing":[115],"lookups":[117,193],"every":[119],"query":[120,200],"point.":[121],"Furthermore,":[122],"demonstrate":[124],"generality":[126],"by":[130],"showing":[131],"principle":[135],"applied":[138],"algorithms":[141],"three":[143],"different":[144],"metrics:":[145],"Euclidean":[147],"distance":[148,156],"(QALSH),":[149],"Jaccard":[150],"measure":[152],"(MinHash),":[153],"Hamming":[155],"(sequence":[157],"hashing).":[158],"Results":[159],"from":[160],"experimental":[161],"studies":[162],"real":[164],"confirm":[166],"error":[168],"significant":[172],"improvements":[173],"over":[177,184],"state-of-the-art":[179],"method:":[181],"achieve":[183],"0.95":[185],"recall,":[186],"only":[188],"need":[189],"operate":[191],"at":[195],"most":[196],"15%":[197],"points.":[201]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}