{"id":"https://openalex.org/W2563724055","doi":"https://doi.org/10.14778/3137628.3137633","title":"Towards linear algebra over normalized data","display_name":"Towards linear algebra over normalized data","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2563724055","doi":"https://doi.org/10.14778/3137628.3137633","mag":"2563724055"},"language":"en","primary_location":{"id":"doi:10.14778/3137628.3137633","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137633","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/A5003134390","display_name":"Lingjiao Chen","orcid":"https://orcid.org/0009-0001-4473-7544"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lingjiao Chen","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103749365","display_name":"Arun Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Kumar","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017678555","display_name":"Jeffrey F. Naughton","orcid":"https://orcid.org/0000-0002-3710-8096"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Naughton","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003134390"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":6.8376,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.97193941,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"10","issue":"11","first_page":"1214","last_page":"1225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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":0.9973000288009644,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.7539400458335876},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6497396230697632},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.6409389972686768},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5936577916145325},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5645268559455872},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47846007347106934},{"id":"https://openalex.org/keywords/relational-algebra","display_name":"Relational algebra","score":0.4712306261062622},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.43252119421958923},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.43237632513046265},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.429340124130249},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4291684031486511},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4277447462081909},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.41215604543685913},{"id":"https://openalex.org/keywords/algebraic-operation","display_name":"Algebraic operation","score":0.41122400760650635},{"id":"https://openalex.org/keywords/algebraic-number","display_name":"Algebraic number","score":0.350193053483963},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28238844871520996},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23915529251098633},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1941606104373932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12016350030899048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539400458335876},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6497396230697632},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6409389972686768},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5936577916145325},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5645268559455872},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47846007347106934},{"id":"https://openalex.org/C95916125","wikidata":"https://www.wikidata.org/wiki/Q840540","display_name":"Relational algebra","level":3,"score":0.4712306261062622},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.43252119421958923},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.43237632513046265},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.429340124130249},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4291684031486511},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4277447462081909},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.41215604543685913},{"id":"https://openalex.org/C136003732","wikidata":"https://www.wikidata.org/wiki/Q3854337","display_name":"Algebraic operation","level":3,"score":0.41122400760650635},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.350193053483963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28238844871520996},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23915529251098633},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1941606104373932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12016350030899048},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3137628.3137633","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137633","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/9","display_name":"Industry, innovation and infrastructure","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1538786304","https://openalex.org/W1580960713","https://openalex.org/W1761301028","https://openalex.org/W1973761208","https://openalex.org/W1988425770","https://openalex.org/W2016653720","https://openalex.org/W2017369298","https://openalex.org/W2032775418","https://openalex.org/W2038469228","https://openalex.org/W2044849727","https://openalex.org/W2056102316","https://openalex.org/W2058978608","https://openalex.org/W2085140829","https://openalex.org/W2090850279","https://openalex.org/W2099655235","https://openalex.org/W2138542364","https://openalex.org/W2184623761","https://openalex.org/W2185864411","https://openalex.org/W2247380138","https://openalex.org/W2284514301","https://openalex.org/W2292590056","https://openalex.org/W2357449897","https://openalex.org/W2411006959","https://openalex.org/W2444650685","https://openalex.org/W2535724050","https://openalex.org/W2547190417","https://openalex.org/W2548695101","https://openalex.org/W2585098096","https://openalex.org/W2610857016","https://openalex.org/W2753710282","https://openalex.org/W2949742316","https://openalex.org/W2953384591","https://openalex.org/W3098547670","https://openalex.org/W3149201378","https://openalex.org/W4229666556","https://openalex.org/W4229706427"],"related_works":["https://openalex.org/W2583155143","https://openalex.org/W4321317949","https://openalex.org/W1974358179","https://openalex.org/W4285303061","https://openalex.org/W4379518721","https://openalex.org/W2143880790","https://openalex.org/W2117467617","https://openalex.org/W1977662461","https://openalex.org/W2045058631","https://openalex.org/W2138414916"],"abstract_inverted_index":{"Providing":[0],"machine":[1],"learning":[2],"(ML)":[3],"over":[4,155,160],"relational":[5],"data":[6,12,23,37,48,132,137,157,205],"is":[7,105],"a":[8,28,62,76,86,113,129,140,148],"mainstream":[9],"requirement":[10],"for":[11,61],"analytics":[13],"systems.":[14],"While":[15],"almost":[16],"all":[17],"ML":[18,57,65,69,80,96,123,174,190],"tools":[19],"require":[20,75],"the":[21,119,188],"input":[22],"to":[24,39,47,94,107,117,134,146,169,215],"be":[25],"presented":[26],"as":[27],"single":[29],"table,":[30],"many":[31,122],"datasets":[32],"are":[33],"multi-table.":[34],"This":[35],"forces":[36],"scientists":[38],"join":[40],"those":[41],"tables":[42],"first,":[43],"which":[44],"often":[45],"leads":[46],"redundancy":[49],"and":[50,138,178,193,202],"runtime":[51],"waste.":[52],"Recent":[53],"works":[54],"on":[55,217],"\"factorized\"":[56],"mitigate":[58,108],"this":[59,99,109,166],"issue":[60],"few":[63],"specific":[64],"algorithms":[66],"by":[67,111],"pushing":[68],"through":[70],"joins.":[71],"But":[72],"their":[73],"approaches":[74],"manual":[77],"rewrite":[78,144],"of":[79,121,142,151],"implementations.":[81],"Such":[82],"piecemeal":[83],"methods":[84],"create":[85],"massive":[87],"development":[88],"overhead":[89,110],"when":[90],"extending":[91],"such":[92],"ideas":[93],"other":[95],"algorithms.":[97],"In":[98],"paper,":[100],"we":[101],"show":[102,164,206],"that":[103,207],"it":[104],"possible":[106],"leveraging":[112],"popular":[114,173,189],"formal":[115],"algebra":[116,153],"represent":[118,135],"computations":[120],"algorithms:":[124],"linear":[125,152],"algebra.":[126],"We":[127,163,183],"introduce":[128],"new":[130],"logical":[131],"type":[133],"normalized":[136,161,204],"devise":[139],"framework":[141,186,209],"algebraic":[143],"rules":[145],"convert":[147],"large":[149],"set":[150],"operations":[154,159],"denormalized":[156],"into":[158],"data.":[162,219],"how":[165],"enables":[167],"us":[168],"automatically":[170],"\"factorize\"":[171],"several":[172,180],"algorithms,":[175],"thus":[176],"unifying":[177],"generalizing":[179],"prior":[181],"works.":[182],"prototype":[184],"our":[185,208],"in":[187],"environment":[191],"R":[192],"an":[194],"industrial":[195],"R-over-RDBMS":[196],"tool.":[197],"Experiments":[198],"with":[199],"both":[200],"synthetic":[201],"real":[203,218],"also":[210],"yields":[211],"significant":[212],"speed-ups,":[213],"up":[214],"36x":[216]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":7},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}