{"id":"https://openalex.org/W4242142158","doi":"https://doi.org/10.1145/3186728.3164145","title":"Cardinality estimation","display_name":"Cardinality estimation","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W4242142158","doi":"https://doi.org/10.1145/3186728.3164145"},"language":"en","primary_location":{"id":"doi:10.1145/3186728.3164145","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3186728.3164145","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/A5008534205","display_name":"Hazar Harmouch","orcid":"https://orcid.org/0000-0001-9967-5347"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hazar Harmouch","raw_affiliation_strings":["University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008534205"],"corresponding_institution_ids":["https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":2.1554,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.88982082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"11","issue":"4","first_page":"499","last_page":"512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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":0.9988999962806702,"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/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9983000159263611,"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/cardinality","display_name":"Cardinality (data modeling)","score":0.8286646604537964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483206987380981},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.710954487323761},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7018108367919922},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4723043441772461},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.46068835258483887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43682169914245605},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.42571038007736206},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4228046238422394},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3589879274368286},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08863523602485657}],"concepts":[{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.8286646604537964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483206987380981},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.710954487323761},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7018108367919922},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4723043441772461},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.46068835258483887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43682169914245605},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.42571038007736206},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4228046238422394},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3589879274368286},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08863523602485657},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3186728.3164145","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3186728.3164145","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":28,"referenced_works":["https://openalex.org/W70607902","https://openalex.org/W760598031","https://openalex.org/W1555239021","https://openalex.org/W1571874655","https://openalex.org/W1982092405","https://openalex.org/W1992363839","https://openalex.org/W2002576896","https://openalex.org/W2005731313","https://openalex.org/W2008365755","https://openalex.org/W2012251118","https://openalex.org/W2025051251","https://openalex.org/W2034302520","https://openalex.org/W2047061289","https://openalex.org/W2053113436","https://openalex.org/W2058991275","https://openalex.org/W2064379477","https://openalex.org/W2065014987","https://openalex.org/W2080234606","https://openalex.org/W2083966857","https://openalex.org/W2095595785","https://openalex.org/W2099480861","https://openalex.org/W2112400233","https://openalex.org/W2154096150","https://openalex.org/W2194545593","https://openalex.org/W2232417456","https://openalex.org/W2494756716","https://openalex.org/W2914354916","https://openalex.org/W4251602148"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248"],"abstract_inverted_index":{"Data":[0],"preparation":[1],"and":[2,9,18,27,83,102,120,140,145,159],"data":[3,23],"profiling":[4],"comprise":[5],"many":[6,68],"both":[7],"basic":[8],"complex":[10],"tasks":[11],"to":[12,66,76,84,105],"analyze":[13],"a":[14,44,86],"dataset":[15],"at":[16],"hand":[17],"extract":[19],"metadata,":[20],"such":[21],"as":[22,48],"distributions,":[24],"key":[25],"candidates,":[26],"functional":[28],"dependencies.":[29],"Among":[30],"the":[31,38,49,62,78,96,107,127,136],"most":[32],"important":[33],"types":[34],"of":[35,40,72,80,90,109],"metadata":[36],"is":[37,75],"number":[39],"distinct":[41],"values":[42],"in":[43,61,155,157],"column,":[45],"also":[46],"known":[47],"zeroth-frequency":[50],"moment.":[51],"Cardinality":[52],"estimation":[53,82,111,132],"itself":[54],"has":[55],"been":[56],"an":[57],"active":[58],"research":[59],"topic":[60],"past":[63],"decades":[64],"due":[65],"its":[67],"applications.":[69],"The":[70],"aim":[71],"this":[73],"paper":[74],"review":[77],"literature":[79],"cardinality":[81,110,131],"present":[85],"detailed":[87],"experimental":[88,123],"study":[89],"twelve":[91,130],"algorithms,":[92],"scaling":[93],"far":[94],"beyond":[95],"original":[97],"experiments.":[98],"First,":[99],"we":[100,113,160],"outline":[101],"classify":[103],"approaches":[104],"solve":[106],"problem":[108],"-":[112],"describe":[114],"their":[115,162],"main":[116],"idea,":[117],"error-guarantees,":[118],"advantages,":[119],"disadvantages.":[121],"Our":[122,148],"survey":[124],"then":[125],"compares":[126],"performance":[128],"all":[129],"algorithms.":[133],"We":[134],"evaluate":[135],"algorithms'":[137],"accuracy,":[138],"runtime,":[139],"memory":[141],"consumption":[142],"using":[143],"synthetic":[144],"real-world":[146],"datasets.":[147],"results":[149],"show":[150],"that":[151],"different":[152,156],"algorithms":[153],"excel":[154],"categories,":[158],"highlight":[161],"trade-offs.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}