{"id":"https://openalex.org/W2182148130","doi":"https://doi.org/10.14778/2752939.2752946","title":"Divide & conquer-based inclusion dependency discovery","display_name":"Divide & conquer-based inclusion dependency discovery","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W2182148130","doi":"https://doi.org/10.14778/2752939.2752946","mag":"2182148130"},"language":"en","primary_location":{"id":"doi:10.14778/2752939.2752946","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2752939.2752946","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/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 (HPI), Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute (HPI), 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 (HPI), Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute (HPI), Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083942725","display_name":"Jorge-Arnulfo Quian\u00e9-Ruiz","orcid":"https://orcid.org/0000-0002-9001-825X"},"institutions":[{"id":"https://openalex.org/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Jorge-Arnulfo Quian\u00e9-Ruiz","raw_affiliation_strings":["Qatar Computing Research Institute (QCRI), Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute (QCRI), Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]},{"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 (HPI), Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute (HPI), Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.0193,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.98211364,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"8","issue":"7","first_page":"774","last_page":"785"},"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":0.9894999861717224,"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":0.989300012588501,"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/unary-operation","display_name":"Unary operation","score":0.8540070652961731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7673244476318359},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6590253114700317},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5949923396110535},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.5453223586082458},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.45672518014907837},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.45064881443977356},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4254131317138672},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.42486658692359924},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.42329901456832886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4184833765029907},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3977264165878296},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33348435163497925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30789631605148315},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2347344160079956},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2237091064453125},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20310136675834656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1011822521686554}],"concepts":[{"id":"https://openalex.org/C78023250","wikidata":"https://www.wikidata.org/wiki/Q657596","display_name":"Unary operation","level":2,"score":0.8540070652961731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673244476318359},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6590253114700317},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5949923396110535},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.5453223586082458},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.45672518014907837},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.45064881443977356},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4254131317138672},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.42486658692359924},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42329901456832886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4184833765029907},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3977264165878296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33348435163497925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30789631605148315},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2347344160079956},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2237091064453125},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20310136675834656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1011822521686554},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2752939.2752946","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2752939.2752946","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.8100000023841858,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W204601728","https://openalex.org/W1482752581","https://openalex.org/W1506285740","https://openalex.org/W1819449330","https://openalex.org/W2029570660","https://openalex.org/W2089711563","https://openalex.org/W2094407133","https://openalex.org/W2096461223","https://openalex.org/W2099725016","https://openalex.org/W2112129552","https://openalex.org/W2116790080","https://openalex.org/W2125552274","https://openalex.org/W2126848435","https://openalex.org/W2140523882","https://openalex.org/W2155906821","https://openalex.org/W2159186077","https://openalex.org/W2162294668"],"related_works":["https://openalex.org/W2361361118","https://openalex.org/W2087937280","https://openalex.org/W4229010838","https://openalex.org/W2897069984","https://openalex.org/W4319975904","https://openalex.org/W2153508518","https://openalex.org/W2167598145","https://openalex.org/W2896100497","https://openalex.org/W1583074514","https://openalex.org/W2182148130"],"abstract_inverted_index":{"The":[0],"discovery":[1],"of":[2,14,23,44,54,56,75,105,110,152],"all":[3],"inclusion":[4],"dependencies":[5],"(INDs)":[6],"in":[7,52,157],"a":[8,86],"dataset":[9],"is":[10,73,83,167],"an":[11,68,99,139],"important":[12,100],"part":[13],"any":[15],"data":[16,32],"profiling":[17],"effort.":[18],"Apart":[19],"from":[20],"the":[21,42,103,106,149,155],"detection":[22,43,70],"foreign":[24],"key":[25],"relationships,":[26],"INDs":[27,45],"can":[28],"help":[29],"to":[30,93,115,169],"perform":[31],"integration,":[33],"query":[34],"optimization,":[35],"integrity":[36],"checking,":[37],"or":[38],"schema":[39],"(re-)design.":[40],"However,":[41],"gets":[46],"harder":[47],"as":[48,58,60],"datasets":[49,97,131],"become":[50],"larger":[51],"terms":[53],"number":[55],"tuples":[57],"well":[59],"attributes.":[61],"To":[62],"this":[63],"end,":[64],"we":[65,119],"propose":[66],"Binder,":[67],"IND":[69,164],"system":[71],"that":[72,129],"capable":[74],"detecting":[76],"both":[77,158],"unary":[78,159],"and":[79,141,161,174],"n-ary":[80,162],"INDs.":[81],"It":[82],"based":[84],"on":[85,102,123],"divide":[87],"&":[88],"conquer":[89],"approach,":[90],"which":[91],"allows":[92],"handle":[94],"very":[95],"large":[96],"--":[98],"property":[101],"face":[104],"ever":[107],"increasing":[108],"size":[109],"today's":[111],"data.":[112],"In":[113],"contrast":[114],"most":[116],"related":[117],"works,":[118],"do":[120],"not":[121],"rely":[122],"existing":[124],"database":[125],"functionality":[126],"nor":[127],"assume":[128],"inspected":[130],"fit":[132],"into":[133],"main":[134],"memory.":[135],"This":[136],"renders":[137],"Binder":[138,153,166],"efficient":[140],"scalable":[142],"competitor.":[143],"Our":[144],"exhaustive":[145],"experimental":[146],"evaluation":[147],"shows":[148],"high":[150],"superiority":[151],"over":[154],"state-of-the-art":[156],"(Spider)":[160],"(Mind)":[163],"discovery.":[165],"up":[168],"26x":[170],"faster":[171,178],"than":[172,176,179],"Spider":[173],"more":[175],"2500x":[177],"Mind.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}