{"id":"https://openalex.org/W2439326083","doi":"https://doi.org/10.1145/2882903.2915203","title":"A Hybrid Approach to Functional Dependency Discovery","display_name":"A Hybrid Approach to Functional Dependency Discovery","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2439326083","doi":"https://doi.org/10.1145/2882903.2915203","mag":"2439326083"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2915203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-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":true,"raw_author_name":"Thorsten Papenbrock","raw_affiliation_strings":["Hasso Plattner Institute, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, 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 Institute, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047144042"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":17.8043,"has_fulltext":false,"cited_by_count":154,"citation_normalized_percentile":{"value":0.9926374,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"821","last_page":"833"},"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":0.9851999878883362,"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":0.9847999811172485,"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/functional-dependency","display_name":"Functional dependency","score":0.824007511138916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143026828765869},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6403070688247681},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5658484697341919},{"id":"https://openalex.org/keywords/dependency-theory","display_name":"Dependency theory (database theory)","score":0.5340624451637268},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5198267102241516},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.49252352118492126},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.46559250354766846},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4437553286552429},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31331244111061096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2773575186729431},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.20684897899627686}],"concepts":[{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.824007511138916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143026828765869},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6403070688247681},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5658484697341919},{"id":"https://openalex.org/C40683218","wikidata":"https://www.wikidata.org/wiki/Q5260625","display_name":"Dependency theory (database theory)","level":4,"score":0.5340624451637268},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5198267102241516},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.49252352118492126},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.46559250354766846},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4437553286552429},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31331244111061096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2773575186729431},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.20684897899627686},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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:10.1145/2882903.2915203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-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/W144096106","https://openalex.org/W1502954553","https://openalex.org/W1506285740","https://openalex.org/W1537955876","https://openalex.org/W1569990199","https://openalex.org/W1571341547","https://openalex.org/W1580074955","https://openalex.org/W1612155886","https://openalex.org/W1881756506","https://openalex.org/W2005389515","https://openalex.org/W2024443169","https://openalex.org/W2029570660","https://openalex.org/W2051200809","https://openalex.org/W2089711563","https://openalex.org/W2120220749","https://openalex.org/W2126493028","https://openalex.org/W2153531471","https://openalex.org/W2162294668","https://openalex.org/W2165467455","https://openalex.org/W2166549982","https://openalex.org/W2168440643","https://openalex.org/W2185907055","https://openalex.org/W2232207765","https://openalex.org/W2232417456","https://openalex.org/W2266772167","https://openalex.org/W2286662104","https://openalex.org/W6689392195","https://openalex.org/W7000471415"],"related_works":["https://openalex.org/W2072918301","https://openalex.org/W2392606101","https://openalex.org/W2133756937","https://openalex.org/W3162070149","https://openalex.org/W2489943546","https://openalex.org/W2362842011","https://openalex.org/W1845544376","https://openalex.org/W59130053","https://openalex.org/W2048090520","https://openalex.org/W1839867872"],"abstract_inverted_index":{"Functional":[0],"dependencies":[1,27,100],"are":[2,32,56],"structural":[3],"metadata":[4],"that":[5],"can":[6],"be":[7],"used":[8],"for":[9,50],"schema":[10],"normalization,":[11],"data":[12,14,19,109],"integration,":[13],"cleansing,":[15],"and":[16,35,72],"many":[17],"other":[18],"management":[20],"tasks.":[21],"Despite":[22],"their":[23],"importance,":[24],"the":[25],"functional":[26,51,99],"of":[28,61],"a":[29,73,78,102],"specific":[30],"dataset":[31],"usually":[33],"unknown":[34],"almost":[36],"impossible":[37],"to":[38,58,95,121],"discover":[39],"manually.":[40],"For":[41],"this":[42],"reason,":[43],"database":[44],"research":[45],"has":[46],"proposed":[47],"various":[48],"algorithms":[49],"dependency":[52],"discovery.":[53],"None,":[54],"however,":[55],"able":[57],"process":[59],"datasets":[60,66],"typical":[62],"real-world":[63],"size,":[64],"e.g.,":[65],"with":[67,89],"more":[68],"than":[69],"50":[70],"attributes":[71],"million":[74],"records.":[75],"We":[76],"present":[77],"hybrid":[79],"discovery":[80],"algorithm":[81],"called":[82],"HyFD,":[83],"which":[84],"combines":[85],"fast":[86],"approximation":[87],"techniques":[88,92],"efficient":[90],"validation":[91],"in":[93,101],"order":[94],"find":[96],"all":[97,115],"minimal":[98],"given":[103],"dataset.":[104],"While":[105],"operating":[106],"on":[107],"compact":[108],"structures,":[110],"HyFD":[111],"not":[112],"only":[113],"outperforms":[114],"existing":[116],"approaches,":[117],"it":[118],"also":[119],"scales":[120],"much":[122],"larger":[123],"datasets.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}
