{"id":"https://openalex.org/W2000482994","doi":"https://doi.org/10.14778/1978665.1978666","title":"Similarity join size estimation using locality sensitive hashing","display_name":"Similarity join size estimation using locality sensitive hashing","publication_year":2011,"publication_date":"2011-03-01","ids":{"openalex":"https://openalex.org/W2000482994","doi":"https://doi.org/10.14778/1978665.1978666","mag":"2000482994"},"language":"en","primary_location":{"id":"doi:10.14778/1978665.1978666","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1978665.1978666","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5081157085","display_name":"Hongrae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hongrae Lee","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113567130","display_name":"Raymond T. Ng","orcid":"https://orcid.org/0000-0003-3692-8524"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Raymond T. Ng","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049064713","display_name":"Kyuseok Shim","orcid":"https://orcid.org/0000-0001-8818-0963"},"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":"Kyuseok Shim","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.377,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95286506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"4","issue":"6","first_page":"338","last_page":"349"},"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":0.9986000061035156,"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":0.9986000061035156,"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/T11106","display_name":"Data Management and Algorithms","score":0.9965000152587891,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9876000285148621,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.9180348515510559},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7167587280273438},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7053162455558777},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.70501309633255},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6208541989326477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6107566356658936},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5021464824676514},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4883289039134979},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.485504150390625},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.48191526532173157},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.47189435362815857},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44349968433380127},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3773965835571289},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35598868131637573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2721484899520874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2543100118637085},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.15911558270454407}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.9180348515510559},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7167587280273438},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7053162455558777},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.70501309633255},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6208541989326477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6107566356658936},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5021464824676514},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4883289039134979},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.485504150390625},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.48191526532173157},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.47189435362815857},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44349968433380127},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3773965835571289},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35598868131637573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2721484899520874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2543100118637085},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.15911558270454407},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1978665.1978666","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1978665.1978666","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1964857063","https://openalex.org/W1968829657","https://openalex.org/W2007069074","https://openalex.org/W2012833704","https://openalex.org/W2013092187","https://openalex.org/W2090403603","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2113380734","https://openalex.org/W2115215982","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2132069633","https://openalex.org/W2147033904","https://openalex.org/W2147717514","https://openalex.org/W2295428206","https://openalex.org/W4237172715","https://openalex.org/W6674576723","https://openalex.org/W6679663036","https://openalex.org/W6845883598"],"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/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"Similarity":[0],"joins":[1],"are":[2],"important":[3],"operations":[4],"with":[5,105],"a":[6,27,76],"broad":[7],"range":[8,128],"of":[9,18,29,51],"applications.":[10],"In":[11],"this":[12],"paper,":[13],"we":[14],"study":[15],"the":[16,30,52,62,70,102,109,125],"problem":[17,39],"vector":[19],"similarity":[20,34,56,72,126],"join":[21,35,57,63],"size":[22,36,58,64],"estimation":[23,37,59],"(VSJ).":[24],"It":[25],"is":[26,60],"generalization":[28],"previously":[31],"studied":[32],"set":[33],"(SSJ)":[38],"and":[40,108,117,129],"can":[41,65],"handle":[42],"more":[43,121],"interesting":[44],"cases":[45],"such":[46],"as":[47],"TF-IDF":[48],"vectors.":[49],"One":[50],"key":[53],"challenges":[54],"in":[55],"that":[61,80],"change":[66],"dramatically":[67],"depending":[68],"on":[69],"input":[71],"threshold.":[73],"We":[74,100],"propose":[75],"sampling":[77,95,107],"based":[78],"algorithm":[79,86],"uses":[81,88],"Locality-Sensitive-Hashing":[82],"(LSH).":[83],"The":[84],"proposed":[85,103],"LSH-SS":[87,119],"an":[89],"LSH":[90],"index":[91],"to":[92,115],"enable":[93],"effective":[94],"even":[96],"at":[97],"high":[98],"thresholds.":[99],"compare":[101],"technique":[104,111],"random":[106],"state-of-the-art":[110],"for":[112],"SSJ":[113],"(adapted":[114],"VSJ)":[116],"demonstrate":[118],"offers":[120],"accurate":[122],"estimates":[123],"throughout":[124],"threshold":[127],"small":[130],"variance":[131],"using":[132],"real-world":[133],"data":[134],"sets.":[135]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}