{"id":"https://openalex.org/W2532748481","doi":"https://doi.org/10.1145/2983323.2983781","title":"Approximate Discovery of Functional Dependencies for Large Datasets","display_name":"Approximate Discovery of Functional Dependencies for Large Datasets","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2532748481","doi":"https://doi.org/10.1145/2983323.2983781","mag":"2532748481"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","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/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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tobias Bleifu\u00df","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":"middle","author":{"id":"https://openalex.org/A5079922261","display_name":"Susanne B\u00fclow","orcid":null},"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":"Susanne B\u00fclow","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":"middle","author":{"id":"https://openalex.org/A5054765105","display_name":"Johannes Frohnhofen","orcid":null},"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":"Johannes Frohnhofen","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":"middle","author":{"id":"https://openalex.org/A5069499219","display_name":"Julian Risch","orcid":null},"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":"Julian Risch","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":"middle","author":{"id":"https://openalex.org/A5048834095","display_name":"Georg Wiese","orcid":null},"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":"Georg Wiese","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":"middle","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":false,"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":"middle","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":false,"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":8,"corresponding_author_ids":["https://openalex.org/A5042896292"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":2.5134,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90426468,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1803","last_page":"1812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9832000136375427,"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":0.8096603155136108},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.6706379652023315},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6385058164596558},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5931762456893921},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5449948310852051},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.5127273797988892},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41181686520576477},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34000203013420105},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.1942099928855896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8096603155136108},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.6706379652023315},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6385058164596558},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5931762456893921},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5449948310852051},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.5127273797988892},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41181686520576477},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34000203013420105},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.1942099928855896},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/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/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6772957391","display_name":null,"funder_award_id":"FOR 1306","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W43035074","https://openalex.org/W760598031","https://openalex.org/W1510305954","https://openalex.org/W1571341547","https://openalex.org/W1881756506","https://openalex.org/W1965280952","https://openalex.org/W1994962776","https://openalex.org/W2006519067","https://openalex.org/W2024443169","https://openalex.org/W2029570660","https://openalex.org/W2098932141","https://openalex.org/W2102489964","https://openalex.org/W2166549982","https://openalex.org/W2266772167","https://openalex.org/W2439326083"],"related_works":["https://openalex.org/W2997590552","https://openalex.org/W4240309520","https://openalex.org/W2571761423","https://openalex.org/W1585267848","https://openalex.org/W3185542772","https://openalex.org/W2584736212","https://openalex.org/W2439326083","https://openalex.org/W2266772167","https://openalex.org/W2532748481","https://openalex.org/W2521016955"],"abstract_inverted_index":{"Functional":[0],"dependencies":[1],"(FDs)":[2],"are":[3,41],"an":[4,26],"important":[5],"prerequisite":[6],"for":[7],"various":[8],"data":[9,19],"management":[10],"tasks,":[11],"such":[12],"as":[13],"schema":[14],"normalization,":[15],"query":[16],"optimization,":[17],"and":[18,30,51],"cleansing.":[20],"However,":[21],"automatic":[22],"FD":[23,38],"discovery":[24,39],"entails":[25],"exponentially":[27],"growing":[28],"search":[29],"solution":[31],"space,":[32],"so":[33],"that":[34],"even":[35],"today's":[36],"fastest":[37],"algorithms":[40],"limited":[42],"to":[43,48],"small":[44],"datasets":[45],"only,":[46],"due":[47],"long":[49],"runtimes":[50],"high":[52],"memory":[53],"consumptions.":[54]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
