{"id":"https://openalex.org/W3081465174","doi":"https://doi.org/10.1145/3394486.3403193","title":"Discovering Functional Dependencies from Mixed-Type Data","display_name":"Discovering Functional Dependencies from Mixed-Type Data","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3081465174","doi":"https://doi.org/10.1145/3394486.3403193","mag":"3081465174"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403193","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403193","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403193","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":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403193","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Panagiotis Mandros","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039895505","display_name":"David Kaltenpoth","orcid":null},"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":"David Kaltenpoth","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047835257","display_name":"Mario Boley","orcid":"https://orcid.org/0000-0002-0704-4968"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mario Boley","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"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"],"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":4,"corresponding_author_ids":["https://openalex.org/A5039816648"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":1.6689,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88397664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1404","last_page":"1414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9947999715805054,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9947999715805054,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9868999719619751,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9850000143051147,"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/discretization","display_name":"Discretization","score":0.7877954244613647},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.7632026076316833},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7019687294960022},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.6629053950309753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6440353393554688},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5467868447303772},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.48866990208625793},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4635006785392761},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.45676732063293457},{"id":"https://openalex.org/keywords/univariate","display_name":"Univariate","score":0.43480321764945984},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41874125599861145},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.41717758774757385},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4151732325553894},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3293040990829468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32433509826660156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23436540365219116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.222889244556427},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17539429664611816}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7877954244613647},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7632026076316833},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7019687294960022},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.6629053950309753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6440353393554688},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5467868447303772},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.48866990208625793},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4635006785392761},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.45676732063293457},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.43480321764945984},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41874125599861145},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.41717758774757385},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4151732325553894},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3293040990829468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32433509826660156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23436540365219116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.222889244556427},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17539429664611816},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3394486.3403193","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403193","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403193","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/24613389","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Discovering_Functional_Dependencies_from_Mixed-Type_Data/24613389","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.24613389.v1","is_oa":true,"landing_page_url":"https://doi.org/10.60882/cispa.24613389.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":"doi:10.1145/3394486.3403193","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403193","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403193","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081465174.pdf","grobid_xml":"https://content.openalex.org/works/W3081465174.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W232667783","https://openalex.org/W1548849615","https://openalex.org/W1559063789","https://openalex.org/W1770458422","https://openalex.org/W1989151402","https://openalex.org/W2067211778","https://openalex.org/W2077737382","https://openalex.org/W2092939357","https://openalex.org/W2109433950","https://openalex.org/W2113054345","https://openalex.org/W2127234432","https://openalex.org/W2149350210","https://openalex.org/W2161642932","https://openalex.org/W2165700458","https://openalex.org/W2171141156","https://openalex.org/W2182722412","https://openalex.org/W2266772167","https://openalex.org/W2333317916","https://openalex.org/W2564078846","https://openalex.org/W2618188015","https://openalex.org/W2750765126","https://openalex.org/W2796833833","https://openalex.org/W2884586244","https://openalex.org/W2891500072","https://openalex.org/W2913172081","https://openalex.org/W2962680664","https://openalex.org/W2963180359","https://openalex.org/W2964313895","https://openalex.org/W2975316662","https://openalex.org/W3106124465"],"related_works":["https://openalex.org/W1847721586","https://openalex.org/W2514374512","https://openalex.org/W2213307371","https://openalex.org/W2937317703","https://openalex.org/W2046754321","https://openalex.org/W2123791177","https://openalex.org/W2072918301","https://openalex.org/W2113868862","https://openalex.org/W2354804553","https://openalex.org/W1845544376"],"abstract_inverted_index":{"Given":[0],"complex":[1],"data":[2],"collections,":[3],"practitioners":[4],"can":[5],"perform":[6],"non-parametric":[7],"functional":[8],"dependency":[9,65,88],"discovery":[10],"(FDD)":[11],"to":[12,27,85,103,109,117,132,175],"uncover":[13],"relationships":[14],"between":[15],"variables":[16,34,55,115],"that":[17,135,162],"were":[18],"previously":[19,152],"unknown.":[20],"However,":[21],"known":[22],"FDD":[23,154,177],"methods":[24],"are":[25,35],"applicable":[26,131],"nominal":[28],"data,":[29],"and":[30,53,98,142,170,173],"in":[31,38],"practice":[32],"non-nominal":[33],"discretized,":[36],"e.g.,":[37],"a":[39,49,79,86,105,110,151],"pre-processing":[40],"step.":[41],"This":[42],"is":[43,56,70,76,167],"problematic":[44],"because,":[45],"as":[46,48,102],"soon":[47],"mix":[50],"of":[51,60,113,120],"discrete":[52],"continuous":[54],"involved,":[57],"the":[58,63,68,163],"interaction":[59],"discretization":[61,81,106],"with":[62,148],"various":[64],"measures":[66],"from":[67,140],"literature":[69],"poorly":[71],"understood.":[72],"In":[73,90],"particular,":[74],"it":[75],"unclear":[77],"whether":[78],"given":[80],"method":[82],"even":[83],"leads":[84,116,174],"consistent":[87,118],"estimate.":[89],"this":[91,149],"paper,":[92],"we":[93,126,146],"analyze":[94],"these":[95,124],"fundamental":[96],"questions":[97],"derive":[99,127],"formal":[100],"criteria":[101],"when":[104],"process":[107],"applied":[108],"mixed":[111],"set":[112],"random":[114],"estimates":[119],"mutual":[121,138],"information.":[122],"With":[123],"insights,":[125],"an":[128],"estimator":[129,166],"framework":[130,150],"any":[133],"task":[134],"involves":[136],"estimating":[137],"information":[139],"multivariate":[141],"mixed-type":[143,180],"data.":[144,181],"Last,":[145],"extend":[147],"proposed":[153],"approach":[155],"for":[156,179],"reliable":[157,165],"dependencies.":[158],"Experimental":[159],"evaluation":[160],"shows":[161],"derived":[164],"both":[168],"computationally":[169],"statistically":[171],"efficient,":[172],"effective":[176],"algorithms":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}