{"id":"https://openalex.org/W2140609014","doi":"https://doi.org/10.1145/1007568.1007650","title":"Information-theoretic tools for mining database structure from large data sets","display_name":"Information-theoretic tools for mining database structure from large data sets","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2140609014","doi":"https://doi.org/10.1145/1007568.1007650","mag":"2140609014"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007650","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","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/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":true,"raw_author_name":"Periklis Andritsos","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"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":"Ren\u00e9e J. Miller","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066962453","display_name":"Panayiotis Tsaparas","orcid":"https://orcid.org/0000-0002-3490-1507"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Panayiotis Tsaparas","raw_affiliation_strings":["Univ. of Rome, \"La Sapienza\""],"affiliations":[{"raw_affiliation_string":"Univ. of Rome, \"La Sapienza\"","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000377124"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":6.306,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.96393986,"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":"731","last_page":"742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9990000128746033,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7782552242279053},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7199006080627441},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.692342221736908},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6307497620582581},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48175787925720215},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.462878942489624},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4218141734600067},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41864213347435},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3996073007583618},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.272702693939209},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21564564108848572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782552242279053},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7199006080627441},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.692342221736908},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6307497620582581},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48175787925720215},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.462878942489624},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4218141734600067},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41864213347435},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3996073007583618},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.272702693939209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21564564108848572},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1007568.1007650","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.321.6115","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.321.6115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/sigmodpods04/sigmod/pdf/R-674.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.709.5859","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.709.5859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uoi.gr/%7Etsap/publications/sigmod04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.70","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.70","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/~periklis/pubs/sigmod04.pdf","raw_type":"text"},{"id":"pmh:oai:iris.unitn.it:11572/77761","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/77761","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1502954553","https://openalex.org/W1551385575","https://openalex.org/W1558832481","https://openalex.org/W1559390933","https://openalex.org/W1560541823","https://openalex.org/W1676212923","https://openalex.org/W1918349060","https://openalex.org/W1971778458","https://openalex.org/W1984566373","https://openalex.org/W2011039300","https://openalex.org/W2012644520","https://openalex.org/W2024770506","https://openalex.org/W2039795745","https://openalex.org/W2063601856","https://openalex.org/W2067566391","https://openalex.org/W2095897464","https://openalex.org/W2098506386","https://openalex.org/W2099111195","https://openalex.org/W2103723258","https://openalex.org/W2106895292","https://openalex.org/W2114679600","https://openalex.org/W2139086573","https://openalex.org/W2158763191","https://openalex.org/W2159793945","https://openalex.org/W2166549982","https://openalex.org/W2166559705","https://openalex.org/W2289787335","https://openalex.org/W2293122579","https://openalex.org/W2978337448","https://openalex.org/W2979454998","https://openalex.org/W4206031975","https://openalex.org/W4245927080","https://openalex.org/W6633513001","https://openalex.org/W6637108112","https://openalex.org/W6675471587"],"related_works":["https://openalex.org/W2002428578","https://openalex.org/W2897258045","https://openalex.org/W3005646551","https://openalex.org/W2018406690","https://openalex.org/W2072332896","https://openalex.org/W2951748633","https://openalex.org/W2057691131","https://openalex.org/W2542042335","https://openalex.org/W2952039693","https://openalex.org/W4280621979"],"abstract_inverted_index":{"Data":[0],"design":[1,12,153],"has":[2],"been":[3],"characterized":[4],"as":[5,50],"a":[6,11,38,44,51,104,174,184],"process":[7],"of":[8,18,21,53,62,82,89,106,121,146,156,183,192,199],"arriving":[9],"at":[10],"that":[13,26,46,113,155,187],"maximizes":[14],"the":[15,42,60,70,80,118,122,144,189,193,200],"information":[16,119,190],"content":[17,30,120,191],"each":[19],"piece":[20],"data":[22,64,128,140,163,204],"(or":[23,31],"equivalently,":[24],"one":[25,150],"minimizes":[27],"redundancy).":[28],"Information":[29],"redundancy)":[32],"is":[33,47,73],"measured":[34],"with":[35],"respect":[36],"to":[37,178],"prescribed":[39,71],"model":[40,45,72],"for":[41,109,133],"data,":[43,90,123],"often":[48],"expressed":[49],"set":[52,105],"constraints.":[54],"In":[55],"this":[56],"work,":[57],"we":[58,78],"consider":[59,79],"problem":[61,81],"doing":[63],"redesign":[65],"in":[66,86,116,127,149],"an":[67,87,91,197],"environment":[68],"where":[69],"unknown":[74],"or":[75],"incomplete.":[76],"Specifically,":[77],"finding":[83,110],"structural":[84,111],"clues":[85],"instance":[88,92],"which":[93],"may":[94],"contain":[95],"errors,":[96],"missing":[97],"values,":[98],"and":[99,124],"duplicate":[100],"records.":[101],"We":[102,130,142,165,195],"propose":[103],"information-theoretic":[107],"tools":[108],"summaries":[112,136,148],"are":[114],"useful":[115,126],"characterizing":[117],"ultimately":[125],"design.":[129],"provide":[131],"algorithms":[132],"creating":[134],"these":[135,147],"over":[137],"large,":[138],"categorical":[139],"sets.":[141,205],"study":[143],"use":[145],"specific":[151],"physical":[152,175],"task,":[154],"ranking":[157,169],"functional":[158],"dependencies":[159],"based":[160],"on":[161,202],"their":[162],"redundancy.":[164],"show":[166],"how":[167],"our":[168],"can":[170],"be":[171],"used":[172],"by":[173],"data-design":[176],"tool":[177],"find":[179],"good":[180],"vertical":[181],"decompositions":[182],"relation":[185],"(decompositions":[186],"improve":[188],"design).":[194],"present":[196],"evaluation":[198],"approach":[201],"real":[203]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}