{"id":"https://openalex.org/W2798658665","doi":"https://doi.org/10.14778/3192965.3192968","title":"Efficient discovery of approximate dependencies","display_name":"Efficient discovery of approximate dependencies","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2798658665","doi":"https://doi.org/10.14778/3192965.3192968","mag":"2798658665"},"language":"en","primary_location":{"id":"doi:10.14778/3192965.3192968","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3192965.3192968","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/A5064504598","display_name":"Sebastian Kruse","orcid":"https://orcid.org/0000-0002-1587-7994"},"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":"Sebastian Kruse","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/A5064504598"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":11.858,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.98669396,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"11","issue":"7","first_page":"759","last_page":"772"},"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":0.9743000268936157,"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":0.9728999733924866,"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":0.7504546642303467},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.6779383420944214},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6324670314788818},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6010560393333435},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5395431518554688},{"id":"https://openalex.org/keywords/dependency-theory","display_name":"Dependency theory (database theory)","score":0.539114236831665},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45671194791793823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3638298511505127},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.33764535188674927},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3258441686630249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23301655054092407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20568424463272095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504546642303467},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.6779383420944214},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6324670314788818},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6010560393333435},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5395431518554688},{"id":"https://openalex.org/C40683218","wikidata":"https://www.wikidata.org/wiki/Q5260625","display_name":"Dependency theory (database theory)","level":4,"score":0.539114236831665},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45671194791793823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3638298511505127},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.33764535188674927},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3258441686630249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23301655054092407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20568424463272095},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3192965.3192968","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3192965.3192968","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W43035074","https://openalex.org/W220709619","https://openalex.org/W760598031","https://openalex.org/W1506285740","https://openalex.org/W1839867872","https://openalex.org/W1881756506","https://openalex.org/W1965280952","https://openalex.org/W1969592497","https://openalex.org/W1976732638","https://openalex.org/W1988622605","https://openalex.org/W1992376331","https://openalex.org/W1994962776","https://openalex.org/W2024443169","https://openalex.org/W2029570660","https://openalex.org/W2047745978","https://openalex.org/W2064853889","https://openalex.org/W2081186682","https://openalex.org/W2098102356","https://openalex.org/W2102489964","https://openalex.org/W2102998074","https://openalex.org/W2112840274","https://openalex.org/W2125227861","https://openalex.org/W2162294668","https://openalex.org/W2166549982","https://openalex.org/W2167101736","https://openalex.org/W2168846860","https://openalex.org/W2186686397","https://openalex.org/W2232417456","https://openalex.org/W2241277057","https://openalex.org/W2249542348","https://openalex.org/W2266772167","https://openalex.org/W2396309311","https://openalex.org/W2401610261","https://openalex.org/W2439326083","https://openalex.org/W2518778694","https://openalex.org/W2532748481","https://openalex.org/W2574683263","https://openalex.org/W2604250586","https://openalex.org/W2613390631","https://openalex.org/W2618188015","https://openalex.org/W2767992112","https://openalex.org/W3106124465","https://openalex.org/W3138538843","https://openalex.org/W4252403066","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2072918301","https://openalex.org/W2392606101","https://openalex.org/W2039445786","https://openalex.org/W2133756937","https://openalex.org/W3162070149","https://openalex.org/W2489943546","https://openalex.org/W2362842011","https://openalex.org/W2884840983","https://openalex.org/W2185054849","https://openalex.org/W1845544376"],"abstract_inverted_index":{"Functional":[0],"dependencies":[1,28,72],"(FDs)":[2],"and":[3,23,94,105,123,148],"unique":[4],"column":[5],"combinations":[6],"(UCCs)":[7],"form":[8],"a":[9,111,138],"valuable":[10],"ingredient":[11],"for":[12],"many":[13],"data":[14,19,62,66],"management":[15],"tasks,":[16],"such":[17],"as":[18],"cleaning,":[20],"schema":[21],"recovery,":[22],"query":[24],"optimization.":[25],"Because":[26],"these":[27],"are":[29,57],"unknown":[30],"in":[31,55],"most":[32],"scenarios,":[33],"their":[34,74],"automatic":[35],"discovery":[36,75,135],"has":[37],"been":[38],"well":[39],"researched.":[40],"However,":[41],"existing":[42,134],"methods":[43],"mostly":[44],"discover":[45,101],"only":[46],"exact":[47,84],"dependencies,":[48,54],"i.e.,":[49],"those":[50],"without":[51],"violations.":[52],"Real-world":[53],"contrast,":[56],"frequently":[58],"approximate":[59,71,103,106],"due":[60],"to":[61,70,100,142,145],"exceptions,":[63],"ambiguities,":[64],"or":[65],"errors.":[67],"This":[68],"relaxation":[69],"renders":[73],"an":[76],"even":[77],"harder":[78],"task":[79],"than":[80],"the":[81,92,150,154],"already":[82],"challenging":[83],"dependency":[85,121],"discovery.":[86],"To":[87],"this":[88],"end,":[89],"we":[90],"propose":[91],"novel":[93],"highly":[95],"efficient":[96],"algorithm":[97],"P":[98,108,131],"yro":[99,109,132],"both":[102],"FDs":[104],"UCCs.":[107],"combines":[110],"separate-and-conquer":[112],"search":[113],"strategy":[114],"with":[115],"sampling-based":[116],"guidance":[117],"that":[118],"quickly":[119],"detects":[120],"candidates":[122],"verifies":[124],"them.":[125],"In":[126],"our":[127],"broad":[128],"experimental":[129],"evaluation,":[130],"outperforms":[133],"algorithms":[136],"by":[137],"factor":[139],"of":[140],"up":[141],"33,":[143],"scales":[144],"larger":[146],"datasets,":[147],"at":[149],"same":[151],"time":[152],"requires":[153],"least":[155],"main":[156],"memory.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}