{"id":"https://openalex.org/W3040722616","doi":"https://doi.org/10.1145/3392778","title":"Efficient Discovery of Matching Dependencies","display_name":"Efficient Discovery of Matching Dependencies","publication_year":2020,"publication_date":"2020-07-07","ids":{"openalex":"https://openalex.org/W3040722616","doi":"https://doi.org/10.1145/3392778","mag":"3040722616"},"language":"en","primary_location":{"id":"doi:10.1145/3392778","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3392778","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-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/A5080483816","display_name":"Philipp Schirmer","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"]},{"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":"Philipp Schirmer","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of 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/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":"Thorsten Papenbrock","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035100665","display_name":"Ioannis Koumarelas","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"]},{"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":"Ioannis Koumarelas","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"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, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3426,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.89132234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"45","issue":"3","first_page":"1","last_page":"33"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.967199981212616,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9070000052452087,"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/computer-science","display_name":"Computer science","score":0.8255392909049988},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6194508075714111},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5587754249572754},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4980006217956543},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.49540650844573975},{"id":"https://openalex.org/keywords/dependency-theory","display_name":"Dependency theory (database theory)","score":0.4685538709163666},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4616158902645111},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4503364861011505},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.44541481137275696},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.40661299228668213},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40187716484069824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33920979499816895},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.25237560272216797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24466603994369507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11347454786300659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255392909049988},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6194508075714111},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5587754249572754},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4980006217956543},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.49540650844573975},{"id":"https://openalex.org/C40683218","wikidata":"https://www.wikidata.org/wiki/Q5260625","display_name":"Dependency theory (database theory)","level":4,"score":0.4685538709163666},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4616158902645111},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4503364861011505},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44541481137275696},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.40661299228668213},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40187716484069824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33920979499816895},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.25237560272216797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24466603994369507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11347454786300659},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3392778","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3392778","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:kobv.de-opus4-uni-potsdam:57449","is_oa":false,"landing_page_url":"https://publishup.uni-potsdam.de/frontdoor/index/index/docId/57449","pdf_url":null,"source":{"id":"https://openalex.org/S4377196346","display_name":"publish.UP (University of Potsdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176453806","host_organization_name":"University of Potsdam","host_organization_lineage":["https://openalex.org/I176453806"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1881756506","https://openalex.org/W1964786778","https://openalex.org/W1973001156","https://openalex.org/W2000794276","https://openalex.org/W2006285370","https://openalex.org/W2008896880","https://openalex.org/W2024895566","https://openalex.org/W2051200809","https://openalex.org/W2059009730","https://openalex.org/W2078501237","https://openalex.org/W2100986433","https://openalex.org/W2114764731","https://openalex.org/W2121269638","https://openalex.org/W2135223301","https://openalex.org/W2145346822","https://openalex.org/W2150916025","https://openalex.org/W2162294668","https://openalex.org/W2166549982","https://openalex.org/W2169940602","https://openalex.org/W2185907055","https://openalex.org/W2186686397","https://openalex.org/W2232417456","https://openalex.org/W2439326083","https://openalex.org/W2732517469","https://openalex.org/W2775696413","https://openalex.org/W2911964244","https://openalex.org/W3008440336","https://openalex.org/W3023590196","https://openalex.org/W3099883947","https://openalex.org/W4242744113","https://openalex.org/W4254788633"],"related_works":["https://openalex.org/W1968137129","https://openalex.org/W2125223317","https://openalex.org/W1593881241","https://openalex.org/W2148956898","https://openalex.org/W1512401680","https://openalex.org/W2072918301","https://openalex.org/W2111203646","https://openalex.org/W158126298","https://openalex.org/W2039445786","https://openalex.org/W2142968084"],"abstract_inverted_index":{"Matching":[0],"dependencies":[1,25],"(MDs)":[2],"are":[3,8,20,161],"data":[4,12,14,106],"profiling":[5,40],"results":[6,159],"that":[7,83,160,174],"often":[9],"used":[10],"for":[11,100,202],"integration,":[13],"cleaning,":[15],"and":[16,130,150,188],"entity":[17],"matching.":[18],"They":[19],"a":[21,78,171],"generalization":[22],"of":[23,47,65,108,197],"functional":[24],"(FDs)":[26],"matching":[27],"similar":[28],"rather":[29],"than":[30,219],"same":[31],"elements.":[32],"As":[33],"their":[34,51],"discovery":[35,64,81,125,156,181],"is":[36,53,117,169,208],"very":[37],"difficult,":[38],"existing":[39],"algorithms":[41],"find":[42],"either":[43],"only":[44,56],"small":[45,57],"subsets":[46],"all":[48,66,85,203],"MDs":[49,68,88,103],"or":[50],"scope":[52],"limited":[54],"to":[55,121,153,211],"datasets.":[58,71],"We":[59],"focus":[60,154],"on":[61,143,157],"the":[62,96,101,105,118,123,136,144,155,176,194,206],"efficient":[63],"interesting":[67],"in":[69,127,183],"real-world":[70],"For":[72,113],"this":[73,114],"purpose,":[74],"we":[75],"propose":[76],"HyMD,":[77],"novel":[79],"MD":[80,124,204],"algorithm":[82,94,137,207],"finds":[84],"minimal,":[86],"non-trivial":[87],"within":[89],"given":[90],"similarity":[91,98,111,200],"boundaries.":[92],"The":[93],"extracts":[95],"exact":[97,129,199],"thresholds":[99,201],"individual":[102],"from":[104,190],"instead":[107],"using":[109],"predefined":[110],"thresholds.":[112],"reason,":[115],"it":[116],"first":[119],"approach":[120,173],"solve":[122],"problem":[126],"an":[128],"truly":[131],"complete":[132],"way.":[133],"If":[134],"needed,":[135],"can,":[138],"however,":[139],"enforce":[140],"certain":[141],"properties":[142],"reported":[145],"MDs,":[146],"such":[147,158],"as":[148],"disjointness":[149],"minimum":[151],"support,":[152],"actually":[162],"required":[163],"by":[164],"downstream":[165],"use":[166],"cases.":[167],"HyMD":[168],"technically":[170],"hybrid":[172],"combines":[175],"two":[177],"most":[178],"popular":[179],"dependency":[180],"strategies":[182],"related":[184],"work:":[185],"lattice":[186],"traversal":[187],"inference":[189],"record":[191],"pairs.":[192],"Despite":[193],"additional":[195],"effort":[196],"finding":[198],"candidates,":[205],"still":[209],"able":[210],"efficiently":[212],"process":[213],"large":[214],"datasets,":[215],"e.g.,":[216],"datasets":[217],"larger":[218],"3":[220],"GB.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}