{"id":"https://openalex.org/W2804287455","doi":"https://doi.org/10.1145/3209889.3209899","title":"Learning Efficiently Over Heterogeneous Databases","display_name":"Learning Efficiently Over Heterogeneous Databases","publication_year":2018,"publication_date":"2018-05-14","ids":{"openalex":"https://openalex.org/W2804287455","doi":"https://doi.org/10.1145/3209889.3209899","mag":"2804287455"},"language":"en","primary_location":{"id":"doi:10.1145/3209889.3209899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209889.3209899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Data Management for End-To-End Machine Learning","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/A5103080785","display_name":"Jose Picado","orcid":"https://orcid.org/0000-0001-8265-1509"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jose Picado","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008664449","display_name":"Arash Termehchy","orcid":"https://orcid.org/0009-0007-2213-6303"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arash Termehchy","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014917444","display_name":"Sudhanshu Pathak","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudhanshu Pathak","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103080785"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05533698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9894000291824341,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9832000136375427,"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/tuple","display_name":"Tuple","score":0.8793665170669556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786348819732666},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.7424512505531311},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.7060593962669373},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6838756799697876},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5950263738632202},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5601518750190735},{"id":"https://openalex.org/keywords/database-theory","display_name":"Database theory","score":0.5137258768081665},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45819956064224243},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.4489341676235199},{"id":"https://openalex.org/keywords/relational-algebra","display_name":"Relational algebra","score":0.4228064715862274},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4213697612285614},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3852000832557678},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3483242392539978},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32377946376800537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11720806360244751},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09751099348068237}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8793665170669556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786348819732666},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.7424512505531311},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.7060593962669373},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6838756799697876},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5950263738632202},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5601518750190735},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.5137258768081665},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45819956064224243},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.4489341676235199},{"id":"https://openalex.org/C95916125","wikidata":"https://www.wikidata.org/wiki/Q840540","display_name":"Relational algebra","level":3,"score":0.4228064715862274},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4213697612285614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3852000832557678},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3483242392539978},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32377946376800537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11720806360244751},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09751099348068237},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3209889.3209899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209889.3209899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Data Management for End-To-End Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1583537937","https://openalex.org/W1964786778","https://openalex.org/W2569536984","https://openalex.org/W2962895701"],"related_works":["https://openalex.org/W2046615742","https://openalex.org/W2015372451","https://openalex.org/W1951450271","https://openalex.org/W584886505","https://openalex.org/W3083095045","https://openalex.org/W1577967548","https://openalex.org/W1502610062","https://openalex.org/W1989645082","https://openalex.org/W2607324466","https://openalex.org/W4245496680"],"abstract_inverted_index":{"Given":[0],"a":[1,8,15,32,55,125],"relational":[2,11,33],"database":[3,126],"and":[4,49,74,115,156],"training":[5,113],"examples":[6],"for":[7,17],"target":[9,19,116],"relation,":[10],"learning":[12,34,105,142],"algorithms":[13],"learn":[14,154],"definition":[16,117],"the":[18,24,28,79,91,108,112,141],"relation":[20],"in":[21,27,97,124,134],"terms":[22],"of":[23,57,81,94],"existing":[25],"relations":[26],"database.":[29],"We":[30],"propose":[31],"system":[35],"called":[36,60],"CastorX,":[37],"which":[38],"learns":[39],"efficiently":[40,155],"across":[41,68,118],"multiple":[42,69,119],"heterogeneous":[43],"databases.":[44,99,120],"The":[45],"user":[46],"specifies":[47],"connections":[48],"relationships":[50],"between":[51],"different":[52,92,98],"databases":[53,70,136],"using":[54],"set":[56],"declarative":[58],"constraints":[59,103],"matching":[61],"dependencies":[62],"(MDs).":[63],"Each":[64],"MD":[65],"connects":[66],"tuples":[67,133],"that":[71],"are":[72],"related":[73],"can":[75],"meaningfully":[76],"join":[77,83],"but":[78],"values":[80,96],"their":[82],"attributes":[84],"may":[85,127],"not":[86],"be":[87,128],"equal":[88],"due":[89],"to":[90,106,111,130,138,153],"representations":[93],"these":[95,102],"CastorX":[100,149],"leverages":[101],"during":[104],"find":[107],"information":[109],"relevant":[110],"data":[114],"Since":[121],"each":[122],"tuple":[123],"connected":[129],"too":[131],"many":[132],"other":[135],"according":[137],"an":[139],"MD,":[140],"process":[143],"will":[144],"become":[145],"very":[146],"slow.":[147],"Hence,":[148],"uses":[150],"sampling":[151],"techniques":[152],"output":[157],"accurate":[158],"definitions.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}