{"id":"https://openalex.org/W2115215982","doi":"https://doi.org/10.14778/1453856.1453883","title":"Hashed samples","display_name":"Hashed samples","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2115215982","doi":"https://doi.org/10.14778/1453856.1453883","mag":"2115215982"},"language":"en","primary_location":{"id":"doi:10.14778/1453856.1453883","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453883","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/A5058831095","display_name":"Marios Hadjieleftheriou","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marios Hadjieleftheriou","raw_affiliation_strings":["AT&T Labs-Research, Florham Park NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research, Florham Park NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071285426","display_name":"Xiaohui Yu","orcid":"https://orcid.org/0000-0001-8170-2327"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaohui Yu","raw_affiliation_strings":["York University, Toronto ON, Canada","York University , Toronto , ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University, Toronto ON, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"York University , Toronto , ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035257754","display_name":"Nick Koudas","orcid":"https://orcid.org/0000-0001-5648-0638"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nick Koudas","raw_affiliation_strings":["University of Toronto, Toronto ON, Canada","University of Toronto, Toronto, On, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto ON, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, On, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T Labs-Research, Florham Park NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research, Florham Park NJ","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1698,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.97821257,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"201","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7276796102523804},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.719807505607605},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.71380615234375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6988505125045776},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5984063744544983},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5901099443435669},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5421931743621826},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5148147940635681},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48667269945144653},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46647363901138306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2955169677734375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22774311900138855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22714054584503174},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2049536406993866}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7276796102523804},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.719807505607605},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.71380615234375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988505125045776},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5984063744544983},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5901099443435669},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5421931743621826},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5148147940635681},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48667269945144653},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46647363901138306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2955169677734375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22774311900138855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22714054584503174},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2049536406993866},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1453856.1453883","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453883","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":32,"referenced_works":["https://openalex.org/W1578664299","https://openalex.org/W1660390307","https://openalex.org/W1974995373","https://openalex.org/W1992363839","https://openalex.org/W1993831977","https://openalex.org/W2024605621","https://openalex.org/W2025051251","https://openalex.org/W2029538739","https://openalex.org/W2041912938","https://openalex.org/W2052207834","https://openalex.org/W2055721472","https://openalex.org/W2058991275","https://openalex.org/W2067566391","https://openalex.org/W2096598900","https://openalex.org/W2097880962","https://openalex.org/W2111998194","https://openalex.org/W2119885577","https://openalex.org/W2121516976","https://openalex.org/W2122971142","https://openalex.org/W2127675794","https://openalex.org/W2138593246","https://openalex.org/W2147440220","https://openalex.org/W2151065878","https://openalex.org/W2154952480","https://openalex.org/W2161936973","https://openalex.org/W2162102353","https://openalex.org/W2167439683","https://openalex.org/W2168459716","https://openalex.org/W2171903035","https://openalex.org/W6637101025","https://openalex.org/W6674576723","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2389818373","https://openalex.org/W2220831889","https://openalex.org/W2056226831","https://openalex.org/W3013312691","https://openalex.org/W3027421045","https://openalex.org/W4312683641","https://openalex.org/W2576320324","https://openalex.org/W3215994059","https://openalex.org/W2980386803","https://openalex.org/W2319823519"],"abstract_inverted_index":{"We":[0,103,120],"study":[1,55],"selectivity":[2,45],"estimation":[3],"techniques":[4],"for":[5,15,116],"set":[6],"similarity":[7,13,33,40],"queries.":[8],"A":[9],"wide":[10],"variety":[11],"of":[12,31,62,124,137],"measures":[14,34],"sets":[16],"have":[17],"been":[18],"proposed":[19],"in":[20,73,98],"the":[21,29,56,75,122],"past.":[22],"In":[23],"this":[24],"work":[25],"we":[26,54],"concentrate":[27],"on":[28,48,113],"class":[30],"weighted":[32],"(e.g.,":[35],"TF/IDF":[36],"and":[37,41,43,65,100,128,143],"BM25":[38],"cosine":[39],"variants)":[42],"design":[44],"estimators":[46],"based":[47,112],"a":[49,110],"priori":[50],"constructed":[51],"samples.":[52],"First,":[53],"pitfalls":[57],"associated":[58],"with":[59],"straightforward":[60],"applications":[61],"random":[63,80],"sampling,":[64],"argue":[66],"that":[67],"care":[68],"needs":[69],"to":[70,106],"be":[71],"taken":[72],"how":[74,105],"samples":[76,109],"are":[77],"constructed;":[78],"uniform":[79],"sampling":[81,90],"yields":[82],"very":[83,145],"low":[84],"accuracy,":[85],"while":[86],"query":[87],"sensitive":[88],"realtime":[89],"is":[91,135],"more":[92],"expensive":[93],"than":[94,140],"exact":[95,141],"solutions":[96,142],"(both":[97],"CPU":[99],"I/O":[101],"cost).":[102],"show":[104],"build":[107],"robust":[108],"priori,":[111],"existing":[114],"synopses":[115],"distinct":[117],"value":[118],"estimation.":[119],"prove":[121],"accuracy":[123],"our":[125],"technique":[126],"theoretically,":[127],"verify":[129],"its":[130],"performance":[131],"experimentally.":[132],"Our":[133],"algorithm":[134],"orders":[136],"magnitude":[138],"faster":[139],"has":[144],"small":[146],"space":[147],"overhead.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}