{"id":"https://openalex.org/W2266772167","doi":"https://doi.org/10.14778/2794367.2794377","title":"Functional dependency discovery","display_name":"Functional dependency discovery","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W2266772167","doi":"https://doi.org/10.14778/2794367.2794377","mag":"2266772167"},"language":"en","primary_location":{"id":"doi:10.14778/2794367.2794377","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2794367.2794377","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/A5047144042","display_name":"Thorsten Papenbrock","orcid":"https://orcid.org/0000-0002-4019-8221"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Papenbrock","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028539259","display_name":"Jens Ehrlich","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Ehrlich","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072935927","display_name":"Jannik Marten","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jannik Marten","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031711924","display_name":"Tommy Neubert","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tommy Neubert","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048100179","display_name":"Jan-Peer Rudolph","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan-Peer Rudolph","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078782922","display_name":"Martin Sch\u00f6nberg","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Sch\u00f6nberg","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081248497","display_name":"Jakob Zwiener","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Zwiener","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"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/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":23.4655,"has_fulltext":false,"cited_by_count":213,"citation_normalized_percentile":{"value":0.99640948,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"8","issue":"10","first_page":"1082","last_page":"1093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9941999912261963,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8022162318229675},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.7190327048301697},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.5299987196922302},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5193532705307007},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.47993260622024536},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4771782457828522},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4464676082134247},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.438510924577713},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.42212027311325073},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35011905431747437},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31147801876068115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2825245261192322},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.17958813905715942},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09354197978973389},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.08756449818611145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022162318229675},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.7190327048301697},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.5299987196922302},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5193532705307007},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.47993260622024536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4771782457828522},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4464676082134247},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.438510924577713},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.42212027311325073},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35011905431747437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31147801876068115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2825245261192322},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.17958813905715942},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09354197978973389},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.08756449818611145},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2794367.2794377","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2794367.2794377","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":19,"referenced_works":["https://openalex.org/W144096106","https://openalex.org/W1502954553","https://openalex.org/W1506285740","https://openalex.org/W1537955876","https://openalex.org/W1539166981","https://openalex.org/W1569990199","https://openalex.org/W1571341547","https://openalex.org/W1881756506","https://openalex.org/W1994962776","https://openalex.org/W2024443169","https://openalex.org/W2029570660","https://openalex.org/W2044108498","https://openalex.org/W2051200809","https://openalex.org/W2084095551","https://openalex.org/W2089711563","https://openalex.org/W2102489964","https://openalex.org/W2159328231","https://openalex.org/W2166549982","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W2392606101","https://openalex.org/W2072918301","https://openalex.org/W3162070149","https://openalex.org/W2489943546","https://openalex.org/W2385315033","https://openalex.org/W2362842011","https://openalex.org/W1845544376","https://openalex.org/W1839867872","https://openalex.org/W2085316814","https://openalex.org/W2048090520"],"abstract_inverted_index":{"Functional":[0],"dependencies":[1,20],"are":[2],"important":[3,73],"metadata":[4],"used":[5],"for":[6,54,140,164],"schema":[7],"normalization,":[8],"data":[9,142],"cleansing":[10],"and":[11,30,65,71,129,144],"many":[12],"other":[13],"tasks.":[14],"The":[15,101],"efficient":[16],"discovery":[17],"of":[18,116,119],"functional":[19,136],"in":[21,27],"tables":[22],"is":[23,47],"a":[24,55,123],"well-known":[25],"challenge":[26],"database":[28],"research":[29],"has":[31],"seen":[32],"several":[33],"approaches.":[34],"Because":[35],"no":[36],"comprehensive":[37],"comparison":[38],"between":[39],"these":[40],"algorithms":[41,84,96,121,138],"exist":[42],"at":[43],"the":[44,51,67,83,107],"time,":[45],"it":[46],"hard":[48],"to":[49,149],"choose":[50,150],"best":[52],"algorithm":[53],"given":[56],"dataset.":[57],"In":[58,153],"this":[59,77],"experimental":[60],"paper,":[61],"we":[62,81],"describe,":[63],"evaluate,":[64],"compare":[66],"seven":[68],"most":[69,72],"cited":[70],"algorithms,":[74],"all":[75,95,120,135,156],"solving":[76],"same":[78],"problem.":[79],"First,":[80],"classify":[82],"into":[85],"three":[86],"different":[87],"categories,":[88],"explaining":[89],"their":[90,98],"commonalities.":[91],"We":[92,132],"then":[93],"describe":[94],"with":[97],"main":[99],"ideas.":[100],"descriptions":[102],"provide":[103,145],"additional":[104],"details":[105],"where":[106],"original":[108],"papers":[109],"were":[110],"ambiguous":[111],"or":[112],"incomplete.":[113],"Our":[114],"evaluation":[115],"careful":[117],"re-implementations":[118],"spans":[122],"broad":[124],"test":[125],"space":[126],"including":[127],"synthetic":[128],"real-world":[130],"data.":[131],"show":[133],"that":[134],"dependency":[137],"optimize":[139],"certain":[141],"characteristics":[143],"hints":[146],"on":[147],"when":[148],"which":[151],"algorithm.":[152],"summary,":[154],"however,":[155],"current":[157],"approaches":[158],"scale":[159],"surprisingly":[160],"poorly,":[161],"showing":[162],"potential":[163],"future":[165],"research.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
