{"id":"https://openalex.org/W4393202813","doi":"https://doi.org/10.1145/3639298","title":"Discovering Functional Dependencies through Hitting Set Enumeration","display_name":"Discovering Functional Dependencies through Hitting Set Enumeration","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4393202813","doi":"https://doi.org/10.1145/3639298"},"language":"en","primary_location":{"id":"doi:10.1145/3639298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639298","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639298","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042896292","display_name":"Tobias Bleifu\u00df","orcid":"https://orcid.org/0009-0006-9517-7707"},"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"]},{"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":true,"raw_author_name":"Tobias Bleifu\u00df","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"raw_orcid":"https://orcid.org/0009-0006-9517-7707","affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047144042","display_name":"Thorsten Papenbrock","orcid":"https://orcid.org/0000-0002-4019-8221"},"institutions":[{"id":"https://openalex.org/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Papenbrock","raw_affiliation_strings":["Philipps University of Marburg, Marburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4019-8221","affiliations":[{"raw_affiliation_string":"Philipps University of Marburg, Marburg, Germany","institution_ids":["https://openalex.org/I161103922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058590949","display_name":"Thomas Bl\u00e4sius","orcid":"https://orcid.org/0000-0003-2450-744X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Bl\u00e4sius","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2450-744X","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008898604","display_name":"Martin Schirneck","orcid":"https://orcid.org/0000-0001-7086-5577"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Martin Schirneck","raw_affiliation_strings":["University of Vienna, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0001-7086-5577","affiliations":[{"raw_affiliation_string":"University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"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"]},{"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":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4483-1389","affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042896292"],"corresponding_institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":3.1872,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91464595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"24"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9865999817848206,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9815999865531921,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7869354486465454},{"id":"https://openalex.org/keywords/enumeration","display_name":"Enumeration","score":0.7845017910003662},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7471216917037964},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6139544248580933},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6050093770027161},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.5692244172096252},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5471261739730835},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.478390097618103},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4737033545970917},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.41329699754714966},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3862585127353668},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.3726998567581177},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35974958539009094},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27139371633529663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12819573283195496},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10928916931152344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869354486465454},{"id":"https://openalex.org/C156340839","wikidata":"https://www.wikidata.org/wiki/Q2704791","display_name":"Enumeration","level":2,"score":0.7845017910003662},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7471216917037964},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6139544248580933},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6050093770027161},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.5692244172096252},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5471261739730835},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.478390097618103},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4737033545970917},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.41329699754714966},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3862585127353668},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3726998567581177},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35974958539009094},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27139371633529663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12819573283195496},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10928916931152344},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639298","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3639298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639298","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393202813.pdf","grobid_xml":"https://content.openalex.org/works/W4393202813.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W760598031","https://openalex.org/W1502954553","https://openalex.org/W1537955876","https://openalex.org/W1556771345","https://openalex.org/W1571341547","https://openalex.org/W1881756506","https://openalex.org/W1976127067","https://openalex.org/W2024443169","https://openalex.org/W2051200809","https://openalex.org/W2077053297","https://openalex.org/W2113607096","https://openalex.org/W2126493028","https://openalex.org/W2153531471","https://openalex.org/W2162294668","https://openalex.org/W2185907055","https://openalex.org/W2232417456","https://openalex.org/W2266772167","https://openalex.org/W2439326083","https://openalex.org/W2532748481","https://openalex.org/W2626926457","https://openalex.org/W2752618741","https://openalex.org/W2788537315","https://openalex.org/W2952207484","https://openalex.org/W2955045665","https://openalex.org/W2964055388","https://openalex.org/W2970388188","https://openalex.org/W2970727798","https://openalex.org/W2983641625","https://openalex.org/W2995343792","https://openalex.org/W3081970771","https://openalex.org/W3082197983","https://openalex.org/W3139384714","https://openalex.org/W3171487259","https://openalex.org/W3183283998","https://openalex.org/W4280616428","https://openalex.org/W4366660144"],"related_works":["https://openalex.org/W2039445786","https://openalex.org/W2185054849","https://openalex.org/W2884840983","https://openalex.org/W2361244046","https://openalex.org/W2126493028","https://openalex.org/W1822025191","https://openalex.org/W2582695666","https://openalex.org/W1629972737","https://openalex.org/W2212845119","https://openalex.org/W1504218574"],"abstract_inverted_index":{"Functional":[0],"dependencies":[1],"(FDs)":[2],"are":[3,28,43,49],"among":[4],"the":[5,37,61,153,167],"most":[6],"important":[7],"integrity":[8],"constraints":[9],"in":[10,60,97],"databases.":[11],"They":[12],"serve":[13],"to":[14,23,31,51,76,141],"normalize":[15],"datasets":[16,78,160],"and":[17,26,74,123],"thus":[18],"resolve":[19],"redundancies,":[20],"they":[21,27,66],"contribute":[22],"query":[24],"optimization,":[25],"frequently":[29],"used":[30],"guide":[32],"data":[33],"cleaning":[34],"efforts.":[35],"Because":[36],"FDs":[38,96,157],"of":[39,72,79,138,155],"a":[40,69,86,98,111,135],"particular":[41],"dataset":[42],"usually":[44],"unknown,":[45],"automatic":[46],"profiling":[47],"algorithms":[48,55,145],"needed":[50],"discover":[52],"them.":[53],"These":[54],"have":[56],"made":[57],"considerable":[58],"advances":[59],"past":[62],"few":[63],"years,":[64],"but":[65],"still":[67],"require":[68],"significant":[70],"amount":[71],"time":[73],"memory":[75],"process":[77],"practically":[80],"relevant":[81],"sizes.":[82],"We":[83],"present":[84],"FDHits,":[85,129],"novel":[87],"FD":[88,143],"discovery":[89,107,144,154],"algorithm":[90],"that":[91,109,128,161],"finds":[92],"all":[93,156],"valid,":[94],"minimal":[95],"given":[99],"relational":[100],"dataset.":[101],"FDHits":[102],"is":[103],"based":[104],"on":[105,159],"several":[106],"optimizations":[108],"include":[110],"hybrid":[112],"validation":[113],"approach,":[114],"effective":[115],"hitting":[116],"set":[117],"enumeration":[118],"techniques,":[119],"one-pass":[120],"candidate":[121],"validations,":[122],"parallelization.":[124],"Our":[125],"experiments":[126],"show":[127],"even":[130,158],"without":[131],"parallel":[132],"execution,":[133],"has":[134],"median":[136],"speedup":[137],"8.1":[139],"compared":[140],"state-of-the-art":[142],"while":[146],"using":[147],"significantly":[148],"less":[149],"memory.":[150],"This":[151],"allows":[152],"could":[162],"not":[163],"be":[164],"processed":[165],"by":[166],"current":[168],"state-of-the-art.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2025-10-10T00:00:00"}
