{"id":"https://openalex.org/W2032775418","doi":"https://doi.org/10.1145/2723372.2723713","title":"Learning Generalized Linear Models Over Normalized Data","display_name":"Learning Generalized Linear Models Over Normalized Data","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2032775418","doi":"https://doi.org/10.1145/2723372.2723713","mag":"2032775418"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2723713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2723713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103749365","display_name":"Arun Kumar","orcid":null},"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":"Arun Kumar","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"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/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":"Jeffrey Naughton","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"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, Madison, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":148,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1969","last_page":"1984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9976999759674072,"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/joins","display_name":"Joins","score":0.8975074887275696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.861602246761322},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5779604315757751},{"id":"https://openalex.org/keywords/relational-database-management-system","display_name":"Relational database management system","score":0.503044068813324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4890514314174652},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4706365764141083},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.4416118562221527},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.42745858430862427},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41730836033821106},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4049752354621887},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3992142677307129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38917604088783264},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23192545771598816}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8975074887275696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.861602246761322},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5779604315757751},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.503044068813324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4890514314174652},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4706365764141083},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.4416118562221527},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.42745858430862427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41730836033821106},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4049752354621887},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3992142677307129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38917604088783264},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23192545771598816},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2723372.2723713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2723713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.688.4532","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.688.4532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://pages.cs.wisc.edu/%7Earun/orion/LearningOverJoinsSIGMOD.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W594141172","https://openalex.org/W1480376833","https://openalex.org/W1538786304","https://openalex.org/W1554944419","https://openalex.org/W1761301028","https://openalex.org/W1860880244","https://openalex.org/W1896160955","https://openalex.org/W2011039300","https://openalex.org/W2013373704","https://openalex.org/W2028659807","https://openalex.org/W2044849727","https://openalex.org/W2056102316","https://openalex.org/W2058978608","https://openalex.org/W2060322444","https://openalex.org/W2060791232","https://openalex.org/W2090850279","https://openalex.org/W2096689597","https://openalex.org/W2099102906","https://openalex.org/W2099655235","https://openalex.org/W2102458936","https://openalex.org/W2103201239","https://openalex.org/W2118038484","https://openalex.org/W2119400430","https://openalex.org/W2138542364","https://openalex.org/W2153329411","https://openalex.org/W2157462866","https://openalex.org/W2169486917","https://openalex.org/W2184623761","https://openalex.org/W2247380138","https://openalex.org/W2406996511","https://openalex.org/W2479567345","https://openalex.org/W2753710282","https://openalex.org/W3029645440","https://openalex.org/W3098547670","https://openalex.org/W3149201378","https://openalex.org/W4301014524","https://openalex.org/W6632489444","https://openalex.org/W6842097421","https://openalex.org/W7018146823"],"related_works":["https://openalex.org/W2098812463","https://openalex.org/W4247095193","https://openalex.org/W2505630977","https://openalex.org/W2383709723","https://openalex.org/W2626533837","https://openalex.org/W2375584934","https://openalex.org/W2761120596","https://openalex.org/W1575529579","https://openalex.org/W2525788546","https://openalex.org/W1988380406"],"abstract_inverted_index":{"Enterprise":[0],"data":[1,9,28,96],"analytics":[2],"is":[3,43,193,201],"a":[4,40,44,103,113,142,154,207],"booming":[5],"area":[6],"in":[7,131,169],"the":[8,37,70,176,198,204],"management":[10,29],"industry.":[11],"Many":[12],"companies":[13],"are":[14,51,125,145],"racing":[15],"to":[16,39,58,87,95,139,147,218,224],"develop":[17],"toolkits":[18,34],"that":[19,36,124,144,160,190],"closely":[20],"integrate":[21],"statistical":[22],"and":[23,91,107,166,172,185],"machine":[24,117],"learning":[25,41,68,76,109,118,159,192],"techniques":[26,119],"with":[27],"systems.":[30],"Almost":[31],"all":[32,180,215],"such":[33],"assume":[35],"input":[38],"algorithm":[42],"single":[45,55],"table.":[46],"However,":[47],"most":[48],"relational":[49],"datasets":[50],"not":[52,202],"stored":[53],"as":[54,221,223],"tables":[56],"due":[57,94],"normalization.":[59],"Thus,":[60],"analysts":[61],"often":[62,194],"perform":[63],"key-foreign":[64],"key":[65],"joins":[66,78,111,165,220],"before":[67],"on":[69],"join":[71,143],"output.":[72],"This":[73],"strategy":[74],"of":[75,116,214],"after":[77],"introduces":[79],"redundancy":[80,168],"avoided":[81],"by":[82],"normalization,":[83],"which":[84],"could":[85],"lead":[86],"poorer":[88],"end-to-end":[89],"performance":[90],"maintenance":[92],"overheads":[93],"duplication.":[97],"In":[98],"this":[99],"work,":[100],"we":[101],"take":[102],"step":[104],"towards":[105],"enabling":[106],"optimizing":[108],"over":[110,141,149],"for":[112,179],"common":[114],"class":[115],"called":[120],"generalized":[121],"linear":[122],"models":[123],"solved":[126],"using":[127],"gradient":[128],"descent":[129],"algorithms":[130],"an":[132],"RDBMS":[133],"setting.":[134],"We":[135,152,174,210],"present":[136],"alternative":[137],"approaches":[138,182,217],"learn":[140],"easy":[146],"implement":[148],"existing":[150],"RDBMSs.":[151],"introduce":[153],"new":[155],"approach":[156],"named":[157],"factorized":[158,191],"pushes":[161],"ML":[162],"computations":[163],"through":[164],"avoids":[167],"both":[170,183],"I/O":[171],"computations.":[173],"study":[175],"tradeoff":[177],"space":[178],"our":[181,216],"analytically":[184],"empirically.":[186],"Our":[187],"results":[188],"show":[189],"substantially":[195],"faster":[196],"than":[197],"alternatives,":[199],"but":[200],"always":[203],"fastest,":[205],"necessitating":[206],"cost-based":[208],"approach.":[209],"also":[211],"discuss":[212],"extensions":[213],"multi-table":[219],"well":[222],"Hive.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}