{"id":"https://openalex.org/W2803396353","doi":"https://doi.org/10.14778/3204028.3204032","title":"Discovery of genuine functional dependencies from relational data with missing values","display_name":"Discovery of genuine functional dependencies from relational data with missing values","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2803396353","doi":"https://doi.org/10.14778/3204028.3204032","mag":"2803396353"},"language":"en","primary_location":{"id":"doi:10.14778/3204028.3204032","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3204028.3204032","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":true,"oa_status":"green","oa_url":"https://hal.science/hal-01795311","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091872345","display_name":"Laure Berti\u2010\u00c9quille","orcid":"https://orcid.org/0000-0002-8046-0570"},"institutions":[{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Laure Berti-\u00c9quille","raw_affiliation_strings":["Aix-Marseille Univ., Marseille, France"],"affiliations":[{"raw_affiliation_string":"Aix-Marseille Univ., Marseille, France","institution_ids":["https://openalex.org/I21491767"]}]},{"author_position":"middle","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":false,"raw_author_name":"Hazar Harmouch","raw_affiliation_strings":["University of Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"middle","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, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040379412","display_name":"No\u00ebl Novelli","orcid":null},"institutions":[{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"No\u00ebl Novelli","raw_affiliation_strings":["Aix-Marseille Univ., Marseille, France"],"affiliations":[{"raw_affiliation_string":"Aix-Marseille Univ., Marseille, France","institution_ids":["https://openalex.org/I21491767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066004392","display_name":"Saravanan Thirumuruganathan","orcid":"https://orcid.org/0000-0002-1517-480X"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Saravanan Thirumuruganathan","raw_affiliation_strings":["HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091872345"],"corresponding_institution_ids":["https://openalex.org/I21491767"],"apc_list":null,"apc_paid":null,"fwci":4.829,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.95038296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"11","issue":"8","first_page":"880","last_page":"892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9930999875068665,"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/T11106","display_name":"Data Management and Algorithms","score":0.9923999905586243,"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/missing-data","display_name":"Missing data","score":0.7818927764892578},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7175947427749634},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.7006416320800781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6735453009605408},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6013901233673096},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6004770994186401},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.5633091926574707},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4825962781906128},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4815526306629181},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.45325949788093567},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.36951369047164917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2859041690826416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21270835399627686},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07074561715126038}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7818927764892578},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7175947427749634},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.7006416320800781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735453009605408},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6013901233673096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6004770994186401},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.5633091926574707},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4825962781906128},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4815526306629181},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.45325949788093567},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.36951369047164917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2859041690826416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21270835399627686},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07074561715126038},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/3204028.3204032","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3204028.3204032","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"},{"id":"pmh:oai:HAL:hal-01795311v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01795311","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 44th International Conference on Very Large Data Bases (VLDB), Aug 2018, Rio de Janeiro, Brazil. &#x27E8;10.14778/3204028.3204032&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:kobv.de-opus4-uni-potsdam:53152","is_oa":false,"landing_page_url":"https://publishup.uni-potsdam.de/frontdoor/index/index/docId/53152","pdf_url":null,"source":{"id":"https://openalex.org/S4306400594","display_name":"publish.UP (University of Potsdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176453806","host_organization_name":"University of Potsdam","host_organization_lineage":["https://openalex.org/I176453806"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01795311v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01795311","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 44th International Conference on Very Large Data Bases (VLDB), Aug 2018, Rio de Janeiro, Brazil. &#x27E8;10.14778/3204028.3204032&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W102383941","https://openalex.org/W1537955876","https://openalex.org/W1781748254","https://openalex.org/W1836162701","https://openalex.org/W1985239372","https://openalex.org/W1994962776","https://openalex.org/W2021746604","https://openalex.org/W2029570660","https://openalex.org/W2045566234","https://openalex.org/W2078686663","https://openalex.org/W2099376460","https://openalex.org/W2099637074","https://openalex.org/W2100142798","https://openalex.org/W2112840274","https://openalex.org/W2134592632","https://openalex.org/W2142472956","https://openalex.org/W2153531471","https://openalex.org/W2161163216","https://openalex.org/W2169600045","https://openalex.org/W2171332293","https://openalex.org/W2186686397","https://openalex.org/W2266772167","https://openalex.org/W2282784388","https://openalex.org/W2401565948","https://openalex.org/W2411740706","https://openalex.org/W2532748481","https://openalex.org/W2573378428","https://openalex.org/W2604250586","https://openalex.org/W3000214033","https://openalex.org/W6736299510"],"related_works":["https://openalex.org/W2056177422","https://openalex.org/W2039445786","https://openalex.org/W2185054849","https://openalex.org/W4213040784","https://openalex.org/W1994193726","https://openalex.org/W2884840983","https://openalex.org/W2053046287","https://openalex.org/W2361244046","https://openalex.org/W2126493028","https://openalex.org/W2582695666"],"abstract_inverted_index":{"Functional":[0],"dependencies":[1,113],"(FDs)":[2],"play":[3],"an":[4],"important":[5],"role":[6],"in":[7],"maintaining":[8],"data":[9,17],"quality.":[10],"They":[11],"can":[12,64,99],"be":[13,53,65,100],"used":[14,101],"to":[15,20,57,89,102,151],"enforce":[16],"consistency":[18],"and":[19,36,86,129,148],"guide":[21],"repairs":[22],"over":[23,126],"a":[24,76,82,95],"database.":[25],"In":[26],"this":[27],"work,":[28],"we":[29],"investigate":[30],"the":[31,91,104,108,117,121],"problem":[32],"of":[33,84,94,110,123],"missing":[34,58,73],"values":[35,59,74],"its":[37],"impact":[38],"on":[39,116],"FD":[40,45,146],"discovery.":[41],"When":[42],"using":[43],"existing":[44],"discovery":[46],"algorithms,":[47],"some":[48,61],"genuine":[49,105,154],"FDs":[50,63,106],"could":[51],"not":[52],"detected":[54],"precisely":[55],"due":[56],"or":[60],"non-genuine":[62],"discovered":[66,96],"even":[67],"though":[68],"they":[69],"are":[70],"caused":[71],"by":[72],"with":[75,132],"certain":[77],"NULL":[78],"semantics.":[79],"We":[80,119],"define":[81],"notion":[83],"genuineness":[85,92],"propose":[87],"algorithms":[88],"compute":[90],"score":[93],"FD.":[97],"This":[98],"identify":[103],"among":[107],"set":[109],"all":[111],"valid":[112],"that":[114,138],"hold":[115],"data.":[118],"evaluate":[120],"quality":[122],"our":[124,139],"method":[125,140],"various":[127],"real-world":[128],"semi-synthetic":[130],"datasets":[131],"extensive":[133],"experiments.":[134],"The":[135],"results":[136],"show":[137],"performs":[141],"well":[142],"for":[143],"relatively":[144],"large":[145],"sets":[147],"is":[149],"able":[150],"accurately":[152],"capture":[153],"FDs.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
