{"id":"https://openalex.org/W2118499545","doi":"https://doi.org/10.14778/2732296.2732297","title":"A principled approach to bridging the gap between graph data and their schemas","display_name":"A principled approach to bridging the gap between graph data and their schemas","publication_year":2014,"publication_date":"2014-04-01","ids":{"openalex":"https://openalex.org/W2118499545","doi":"https://doi.org/10.14778/2732296.2732297","mag":"2118499545"},"language":"en","primary_location":{"id":"doi:10.14778/2732296.2732297","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2732296.2732297","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/A5011691423","display_name":"Marcelo Arenas","orcid":"https://orcid.org/0000-0003-3678-1868"},"institutions":[{"id":"https://openalex.org/I162148367","display_name":"Pontificia Universidad Cat\u00f3lica de Chile","ror":"https://ror.org/04teye511","country_code":"CL","type":"education","lineage":["https://openalex.org/I162148367"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Marcelo Arenas","raw_affiliation_strings":["Pontificia Universidad Cat\u00f3lica de Chile and University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Cat\u00f3lica de Chile and University of Oxford","institution_ids":["https://openalex.org/I162148367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015082669","display_name":"Gonzalo I. Diaz","orcid":"https://orcid.org/0000-0001-6937-7904"},"institutions":[{"id":"https://openalex.org/I162148367","display_name":"Pontificia Universidad Cat\u00f3lica de Chile","ror":"https://ror.org/04teye511","country_code":"CL","type":"education","lineage":["https://openalex.org/I162148367"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Gonzalo D\u00edaz","raw_affiliation_strings":["Pontificia Universidad Cat\u00f3lica de Chile","Pontificia universidad catolica de chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Cat\u00f3lica de Chile","institution_ids":["https://openalex.org/I162148367"]},{"raw_affiliation_string":"Pontificia universidad catolica de chile","institution_ids":["https://openalex.org/I162148367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062643837","display_name":"Achille Fokoue","orcid":"https://orcid.org/0000-0003-1137-1344"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Achille Fokoue","raw_affiliation_strings":["IBM T.J. Watson Research Center","IBM T.J. Watson research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center","institution_ids":[]},{"raw_affiliation_string":"IBM T.J. Watson research Center","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014087838","display_name":"Anastasios Kementsietsidis","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anastasios Kementsietsidis","raw_affiliation_strings":["IBM T.J. Watson Research Center","IBM T.J. Watson research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center","institution_ids":[]},{"raw_affiliation_string":"IBM T.J. Watson research Center","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085594669","display_name":"Kavitha Srinivas","orcid":"https://orcid.org/0000-0003-4610-967X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kavitha Srinivas","raw_affiliation_strings":["IBM T.J. Watson Research Center","IBM T.J. Watson research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center","institution_ids":[]},{"raw_affiliation_string":"IBM T.J. Watson research Center","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011691423"],"corresponding_institution_ids":["https://openalex.org/I162148367"],"apc_list":null,"apc_paid":null,"fwci":2.9595,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92414094,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":"8","first_page":"601","last_page":"612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9940000176429749,"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/T11719","display_name":"Data Quality and Management","score":0.9940000176429749,"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/rdf","display_name":"RDF","score":0.7794656753540039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532588243484497},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5647321939468384},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4955030679702759},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.47671952843666077},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.4436522126197815},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3456329107284546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32427531480789185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31838974356651306},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2975050210952759},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.26700443029403687}],"concepts":[{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.7794656753540039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532588243484497},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5647321939468384},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4955030679702759},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47671952843666077},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.4436522126197815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3456329107284546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32427531480789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31838974356651306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2975050210952759},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.26700443029403687}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/2732296.2732297","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2732296.2732297","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.432.5438","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.432.5438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol7/p601-arenas.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.768.7042","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.768.7042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1308.5703.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W43013837","https://openalex.org/W52491673","https://openalex.org/W100933818","https://openalex.org/W156656192","https://openalex.org/W1488941320","https://openalex.org/W1514770182","https://openalex.org/W1582937643","https://openalex.org/W1603311785","https://openalex.org/W1758759808","https://openalex.org/W1983094331","https://openalex.org/W2045988182","https://openalex.org/W2158454296","https://openalex.org/W2162833336","https://openalex.org/W2613995098","https://openalex.org/W2773438364","https://openalex.org/W4205241946","https://openalex.org/W6629194798","https://openalex.org/W6844091418"],"related_works":["https://openalex.org/W2283287182","https://openalex.org/W2776293731","https://openalex.org/W1485690712","https://openalex.org/W82112649","https://openalex.org/W2058923328","https://openalex.org/W3128827045","https://openalex.org/W2945730294","https://openalex.org/W199330785","https://openalex.org/W2054214855","https://openalex.org/W2400121884"],"abstract_inverted_index":{"Although":[0],"RDF":[1,16,83,104,139,251],"graph":[2,84,105,140],"data":[3,17,28,59,65],"often":[4],"come":[5],"with":[6,122,208],"an":[7,51,82,103,138],"associated":[8,181],"schema,":[9],"recent":[10],"studies":[11],"have":[12,50,74],"proven":[13],"that":[14,176,228,238,256],"real":[15,210],"rarely":[18],"conform":[19,66],"to":[20,41,49,67,101,107,132,136,182],"their":[21],"perceived":[22],"schemas.":[23],"Since":[24],"a":[25,86,91,108,115,130,134,153,156,169,191,243,263],"number":[26],"of":[27,54,57,78,81,151,155,194,234,250,266],"management":[29],"decisions,":[30],"including":[31],"storage":[32],"layouts,":[33],"indexing,":[34],"and":[35,188,213,216,253],"efficient":[36],"query":[37],"processing,":[38],"use":[39],"schemas":[40],"guide":[42],"the":[43,55,58,64,68,76,79,99,149,161,177,221,229,235,248,257],"decision":[44,179],"making,":[45],"it":[46],"is":[47,167,186,260],"imperative":[48],"accurate":[52],"description":[53],"structuredness":[56,80,95,120,166,222],"at":[60],"hand":[61],"(how":[62],"well":[63],"schema).":[69],"In":[70,110,172],"this":[71,183,195,205],"paper,":[72],"we":[73,89,112,124,147,174,189,203,254],"approached":[75],"study":[77],"in":[85,223],"principled":[87],"way:":[88],"propose":[90],"framework":[92],"for":[93,118,246,262],"specifying":[94,119],"functions,":[96],"which":[97,102,137,219],"gauge":[98,220],"degree":[100],"conforms":[106],"schema.":[109],"particular,":[111,173],"first":[113],"define":[114],"formal":[116],"language":[117,128,240],"functions":[121],"expressions":[123],"call":[125],"rules.":[126],"This":[127],"allows":[129],"user":[131],"state":[133],"rule":[135],"may":[141],"fully":[142],"or":[143],"partially":[144],"conform.":[145],"Then":[146],"consider":[148],"issue":[150],"discovering":[152],"refinement":[154,184],"sort":[157],"(type)":[158],"by":[159],"partitioning":[160],"dataset":[162],"into":[163,197],"subsets":[164],"whose":[165],"over":[168],"specified":[170],"threshold.":[171],"prove":[175],"natural":[178,192],"problem":[180,185,196],"NP-complete,":[187],"provide":[190],"translation":[193],"Integer":[198],"Linear":[199],"Programming":[200],"(ILP).":[201],"Finally,":[202],"test":[204],"ILP":[206,258],"solution":[207,259],"three":[209,214],"world":[211],"datasets":[212],"different":[215,224],"intuitive":[217],"rules,":[218],"ways.":[225],"We":[226],"show":[227,255],"rules":[230],"give":[231],"meaningful":[232],"refinements":[233],"datasets,":[236],"showing":[237],"our":[239],"can":[241],"be":[242],"powerful":[244],"tool":[245],"understanding":[247],"structure":[249],"data,":[252],"practical":[261],"large":[264],"fraction":[265],"existing":[267],"data.":[268]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}