{"id":"https://openalex.org/W2079874670","doi":"https://doi.org/10.1145/2618243.2618251","title":"Detecting correlated columns in relational databases with mixed data types","display_name":"Detecting correlated columns in relational databases with mixed data types","publication_year":2014,"publication_date":"2014-06-24","ids":{"openalex":"https://openalex.org/W2079874670","doi":"https://doi.org/10.1145/2618243.2618251","mag":"2079874670"},"language":"en","primary_location":{"id":"doi:10.1145/2618243.2618251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2618243.2618251","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 International Conference on Scientific and Statistical Database 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/A5103009100","display_name":"Hoang Vu Nguyen","orcid":"https://orcid.org/0009-0003-9053-3221"},"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":true,"raw_author_name":"Hoang Vu Nguyen","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Germany","Karlsruhe Institute of Technology (KIT),Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT),Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053906729","display_name":"Emmanuel M\u00fcller","orcid":"https://orcid.org/0000-0002-5409-6875"},"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"]},{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE","DE"],"is_corresponding":false,"raw_author_name":"Emmanuel M\u00fcller","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Germany and University of Antwerp, Belgium"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Germany and University of Antwerp, Belgium","institution_ids":["https://openalex.org/I102335020","https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377124","display_name":"Periklis Andritsos","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Periklis Andritsos","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049768806","display_name":"Klemens B\u00f6hm","orcid":"https://orcid.org/0000-0002-1706-1913"},"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":"Klemens B\u00f6hm","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Germany","Karlsruhe Institute of Technology (KIT),Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT),Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103009100"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.27213328,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.58432304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9926000237464905,"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/T10050","display_name":"Multi-Criteria Decision Making","score":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.734190821647644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7236536145210266},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.719771146774292},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5878040194511414},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5327876210212708},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5250782370567322},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5166481137275696},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5111401677131653},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4793301820755005},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47478291392326355},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4331507384777069},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3395369350910187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1344744861125946},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12965908646583557},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.090800940990448}],"concepts":[{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.734190821647644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236536145210266},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.719771146774292},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5878040194511414},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5327876210212708},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5250782370567322},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5166481137275696},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5111401677131653},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4793301820755005},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47478291392326355},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4331507384777069},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3395369350910187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1344744861125946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12965908646583557},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.090800940990448},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2618243.2618251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2618243.2618251","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 International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W206885600","https://openalex.org/W579871118","https://openalex.org/W1510305954","https://openalex.org/W1520619721","https://openalex.org/W1565838812","https://openalex.org/W1742512077","https://openalex.org/W1965021696","https://openalex.org/W1994166982","https://openalex.org/W2000661457","https://openalex.org/W2017052417","https://openalex.org/W2042035594","https://openalex.org/W2042389627","https://openalex.org/W2057593859","https://openalex.org/W2064379477","https://openalex.org/W2096281132","https://openalex.org/W2099111195","https://openalex.org/W2101460669","https://openalex.org/W2102489964","https://openalex.org/W2117704606","https://openalex.org/W2119309048","https://openalex.org/W2123878016","https://openalex.org/W2126391818","https://openalex.org/W2131626681","https://openalex.org/W2137156898","https://openalex.org/W2140609014","https://openalex.org/W2145836846","https://openalex.org/W2160200253","https://openalex.org/W2165700458","https://openalex.org/W2165997484","https://openalex.org/W2167826316","https://openalex.org/W2168846860","https://openalex.org/W2171235719","https://openalex.org/W2171928062","https://openalex.org/W2241277057","https://openalex.org/W2396635388","https://openalex.org/W2404301904","https://openalex.org/W3021359550"],"related_works":["https://openalex.org/W1971174658","https://openalex.org/W2099195351","https://openalex.org/W4256429076","https://openalex.org/W2012063272","https://openalex.org/W2348092930","https://openalex.org/W2138685729","https://openalex.org/W2062850566","https://openalex.org/W4308716484","https://openalex.org/W2098284475","https://openalex.org/W1968154277"],"abstract_inverted_index":{"In":[0],"a":[1,80,96,103],"database,":[2],"besides":[3],"known":[4,31],"dependencies":[5],"among":[6,62],"columns":[7,63],"(e.g.,":[8],"foreign":[9],"key":[10,13],"and":[11,41,68],"primary":[12],"constraints),":[14],"there":[15],"are":[16],"many":[17],"other":[18],"correlations":[19,29],"unknown":[20],"to":[21,32,50,55,101],"the":[22,45,51,111],"database":[23,39],"users.":[24],"Extraction":[25],"of":[26,53,64,92,113],"such":[27],"hidden":[28],"is":[30,47],"be":[33],"useful":[34],"for":[35],"various":[36],"tasks":[37],"in":[38],"optimization":[40],"data":[42,66],"analytics.":[43],"However,":[44],"task":[46],"challenging":[48],"due":[49],"lack":[52],"measures":[54],"quantify":[56],"column":[57,81],"correlations.":[58],"Correlations":[59],"may":[60,82],"exist":[61],"different":[65],"types":[67],"value":[69,76],"domains,":[70],"which":[71,86],"makes":[72],"techniques":[73],"based":[74],"on":[75],"matching":[77],"inapplicable.":[78],"Besides,":[79],"have":[83],"multiple":[84],"semantics,":[85],"does":[87],"not":[88],"allow":[89],"disjoint":[90],"partitioning":[91],"columns.":[93,114],"Finally,":[94],"from":[95],"computational":[97],"perspective,":[98],"one":[99],"has":[100],"consider":[102],"huge":[104],"search":[105],"space":[106],"that":[107],"grows":[108],"exponentially":[109],"with":[110],"number":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}