{"id":"https://openalex.org/W4244567253","doi":"https://doi.org/10.1007/s41019-019-00104-1","title":"Selectivity Estimation on Set Containment Search","display_name":"Selectivity Estimation on Set Containment Search","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W4244567253","doi":"https://doi.org/10.1007/s41019-019-00104-1"},"language":"en","primary_location":{"id":"doi:10.1007/s41019-019-00104-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-00104-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00104-1.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00104-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100397607","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-4840-3023"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4840-3023","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385498","display_name":"Wenjie Zhang","orcid":"https://orcid.org/0000-0001-6572-2600"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenjie Zhang","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659938","display_name":"Xuemin Lin","orcid":"https://orcid.org/0000-0003-2396-7225"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Xuemin Lin","raw_affiliation_strings":["East China Normal University, Shanghai, China","University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402281","display_name":"Liping Wang","orcid":"https://orcid.org/0000-0003-3049-9917"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Wang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100397607"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":{"value":1290,"currency":"USD","value_usd":1290},"apc_paid":{"value":1290,"currency":"USD","value_usd":1290},"fwci":0.4631,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67168263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":"3","first_page":"254","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9959999918937683,"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":0.9959999918937683,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9890999794006348,"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/T11719","display_name":"Data Quality and Management","score":0.9832000136375427,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822540402412415},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6991585493087769},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6658762097358704},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.5993759036064148},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5244641304016113},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.476016104221344},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46059998869895935},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4593390226364136},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3335791230201721},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22710168361663818},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.18699896335601807},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.16590458154678345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1557328701019287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822540402412415},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6991585493087769},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6658762097358704},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.5993759036064148},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5244641304016113},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.476016104221344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46059998869895935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4593390226364136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3335791230201721},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22710168361663818},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.18699896335601807},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.16590458154678345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1557328701019287},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s41019-019-00104-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-00104-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00104-1.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4573800450894db28c33ecfc15b71daf","is_oa":true,"landing_page_url":"https://doaj.org/article/4573800450894db28c33ecfc15b71daf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science and Engineering, Vol 4, Iss 3, Pp 254-268 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s41019-019-00104-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-00104-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-00104-1.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4244567253.pdf","grobid_xml":"https://content.openalex.org/works/W4244567253.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1455310343","https://openalex.org/W1502634995","https://openalex.org/W1519865830","https://openalex.org/W1660390307","https://openalex.org/W1785933978","https://openalex.org/W1984629602","https://openalex.org/W1992363839","https://openalex.org/W2002919217","https://openalex.org/W2010454887","https://openalex.org/W2017645867","https://openalex.org/W2041500280","https://openalex.org/W2097184821","https://openalex.org/W2111967310","https://openalex.org/W2121269638","https://openalex.org/W2128056631","https://openalex.org/W2141469207","https://openalex.org/W2151930506","https://openalex.org/W2157011656","https://openalex.org/W2167847032","https://openalex.org/W2207067200","https://openalex.org/W2255183403","https://openalex.org/W2615445578","https://openalex.org/W2963174348","https://openalex.org/W6600135713"],"related_works":["https://openalex.org/W104884668","https://openalex.org/W3112332783","https://openalex.org/W2120071517","https://openalex.org/W2406489341","https://openalex.org/W2344797854","https://openalex.org/W2113746559","https://openalex.org/W2080508516","https://openalex.org/W180471195","https://openalex.org/W1521051179","https://openalex.org/W2029271007"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2,65],"paper,":[3],"we":[4,31,105,172],"study":[5],"the":[6,38,81,87,99,103,152,168,191,206],"problem":[7,66],"of":[8,40,44,83,95,102,210],"selectivity":[9,39,177],"estimation":[10,178],"on":[11,129,201],"set":[12,41,175],"containment":[13,42,176],"search.":[14],"Given":[15],"a":[16,21,154],"query":[17,45],"record":[18,22],"Q":[19,46],"and":[20,35,67,72,98,110,114,132,135,146,179,208],"dataset":[23],"$${\\mathcal":[24,48],"{S}}$$":[25,49],"<mml:math":[26,50],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[27,51],"<mml:mi>S</mml:mi>":[28,52],"</mml:math>":[29,53],",":[30,159],"aim":[32],"to":[33,63,107,166],"accurately":[34],"efficiently":[36],"estimate":[37],"search":[43],"over":[47],".":[54,77,124,148,187],"We":[55,78,188],"first":[56],"extend":[57],"existing":[58,96],"distinct":[59],"value":[60],"estimating":[61],"techniques":[62,97,193],"solve":[64],"develop":[68],"an":[69,116,163],"inverted":[70],"list":[71],"G-KMV":[73],"sketch-based":[74],"approach":[75,121,184],"IL-GKMV":[76,84,147],"analyze":[79,190],"that":[80],"performance":[82],"degrades":[85],"with":[86,141,162],"increase":[88],"in":[89],"vocabulary":[90],"size.":[91],"Motivated":[92],"by":[93],"limitations":[94],"inherent":[100],"challenges":[101],"problem,":[104],"resort":[106],"developing":[108],"effective":[109],"efficient":[111],"sampling":[112,120,144,156,183],"approaches":[113],"propose":[115],"ordered":[117],"trie":[118],"structure-based":[119],"named":[122,185],"OT-Sampling":[123,125],"partitions":[126],"records":[127],"based":[128],"element":[130],"frequency":[131],"occurrence":[133],"patterns":[134],"is":[136,160],"significantly":[137],"more":[138],"accurate":[139],"compared":[140],"simple":[142],"random":[143,182],"method":[145],"To":[149],"further":[150],"enhance":[151],"performance,":[153],"divide-and-conquer-based":[155],"approach,":[157],"DC-Sampling":[158],"presented":[161],"inclusion/exclusion":[164],"prefix":[165],"explore":[167],"pruning":[169],"opportunities.":[170],"Meanwhile,":[171],"consider":[173],"weighted":[174],"devise":[180],"stratified":[181],"StrRS":[186],"theoretically":[189],"proposed":[192,212],"regarding":[194],"various":[195],"accuracy":[196],"estimators.":[197],"Our":[198],"comprehensive":[199],"experiments":[200],"nine":[202],"real":[203],"datasets":[204],"verify":[205],"effectiveness":[207],"efficiency":[209],"our":[211],"techniques.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}