{"id":"https://openalex.org/W3080831182","doi":"https://doi.org/10.1145/3394486.3403178","title":"Discovering Approximate Functional Dependencies using Smoothed Mutual Information","display_name":"Discovering Approximate Functional Dependencies using Smoothed Mutual Information","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3080831182","doi":"https://doi.org/10.1145/3394486.3403178","mag":"3080831182"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Discovering_Approximate_Functional_Dependencies_using_Smoothed_Mutual_Information/24613392","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051878238","display_name":"Fr\u00e9d\u00e9ric Pennerath","orcid":null},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Fr\u00e9d\u00e9ric Pennerath","raw_affiliation_strings":["Universit\u00e9 de Lorraine & CentraleSup\u00e9lec, Metz, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine & CentraleSup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I4210107720","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039816648","display_name":"Panagiotis Mandros","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Panagiotis Mandros","raw_affiliation_strings":["Max Planck Institute for Informatics & Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics & Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712","https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043872748","display_name":"Jilles Vreeken","orcid":"https://orcid.org/0000-0002-2310-2806"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jilles Vreeken","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210128801"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051878238"],"corresponding_institution_ids":["https://openalex.org/I4210107720","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":0.272,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.64433673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1254","last_page":"1264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10136","display_name":"Statistical Methods and Inference","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/smoothing","display_name":"Smoothing","score":0.6967267990112305},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6785262823104858},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6124751567840576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6061335206031799},{"id":"https://openalex.org/keywords/dependency-theory","display_name":"Dependency theory (database theory)","score":0.5747052431106567},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.5387917160987854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48266103863716125},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4677484333515167},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.44115757942199707},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4173315465450287},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33210161328315735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3316879868507385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21941310167312622},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09985479712486267},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.09787049889564514}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6967267990112305},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6785262823104858},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6124751567840576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6061335206031799},{"id":"https://openalex.org/C40683218","wikidata":"https://www.wikidata.org/wiki/Q5260625","display_name":"Dependency theory (database theory)","level":4,"score":0.5747052431106567},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.5387917160987854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48266103863716125},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4677484333515167},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.44115757942199707},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4173315465450287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33210161328315735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3316879868507385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21941310167312622},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09985479712486267},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.09787049889564514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3394486.3403178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24613392","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Discovering_Approximate_Functional_Dependencies_using_Smoothed_Mutual_Information/24613392","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.60882/cispa.24613392.v1","is_oa":true,"landing_page_url":"https://doi.org/10.60882/cispa.24613392.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050916","display_name":"CISPA Helmholtz Center","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24613392","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Discovering_Approximate_Functional_Dependencies_using_Smoothed_Mutual_Information/24613392","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1767574678","https://openalex.org/W1770458422","https://openalex.org/W2006714754","https://openalex.org/W2018891628","https://openalex.org/W2067211778","https://openalex.org/W2077737382","https://openalex.org/W2099111195","https://openalex.org/W2101985079","https://openalex.org/W2115482638","https://openalex.org/W2156504490","https://openalex.org/W2161642932","https://openalex.org/W2164524421","https://openalex.org/W2166549982","https://openalex.org/W2266772167","https://openalex.org/W2564078846","https://openalex.org/W2618188015","https://openalex.org/W2891500072","https://openalex.org/W2913172081","https://openalex.org/W2964313895","https://openalex.org/W2975316662","https://openalex.org/W2998216295","https://openalex.org/W3106124465","https://openalex.org/W4289543894"],"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":{"We":[0],"consider":[1,71],"the":[2,6,37,106,117,122,140],"task":[3],"of":[4,62,142],"discovering":[5],"top-K":[7,123],"reliable":[8],"approximate":[9],"functional":[10,146],"dependencies":[11],"X":[12],"->":[13],"Y":[14],"from":[15],"high":[16,25],"dimensional":[17,26],"data.":[18],"While":[19],"naively":[20],"maximizing":[21],"mutual":[22],"information":[23],"involving":[24],"entropies":[27],"over":[28],"empirical":[29,38],"data":[30,41,78],"is":[31,131],"subject":[32],"to":[33,45,88,112,139],"false":[34],"discoveries,":[35],"correcting":[36,57],"estimator":[39,108],"against":[40],"sparsity":[42,79],"can":[43],"lead":[44],"efficient":[46,90],"exact":[47],"algorithms":[48],"for":[49,105,121],"robust":[50,92],"dependency":[51],"discovery.":[52],"Previous":[53],"approaches":[54],"focused":[55],"on":[56],"by":[58],"subtracting":[59],"expected":[60],"values":[61],"different":[63,73],"null":[64],"hypothesis":[65],"models.":[66],"In":[67,95],"this":[68],"paper,":[69],"we":[70,97],"a":[72],"correction":[74],"strategy":[75],"and":[76,83,91,101,137,144],"counter":[77],"using":[80],"uniform":[81],"priors":[82],"smoothing":[84],"techniques,":[85],"that":[86,109,128],"leads":[87,138],"an":[89,99],"estimating":[93],"process.":[94],"addition,":[96],"derive":[98],"admissible":[100],"tight":[102],"bounding":[103],"function":[104],"smoothed":[107],"allows":[110],"us":[111],"efficiently":[113],"solve":[114],"via":[115],"branch-and-bound":[116],"hard":[118],"search":[119],"problem":[120],"dependencies.":[124,147],"Our":[125],"experiments":[126],"show":[127],"our":[129],"approach":[130],"much":[132],"faster":[133],"than":[134],"previous":[135],"proposals,":[136],"discovery":[141],"sparse":[143],"informative":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2025-10-10T00:00:00"}