{"id":"https://openalex.org/W2444650685","doi":"https://doi.org/10.1145/2882903.2882952","title":"To Join or Not to Join?","display_name":"To Join or Not to Join?","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2444650685","doi":"https://doi.org/10.1145/2882903.2882952","mag":"2444650685"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2882952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2882952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","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/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":true,"raw_author_name":"Arun Kumar","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"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"],"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/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"],"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/A5103428074","display_name":"Xiaojin Zhu","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":"Xiaojin Zhu","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI, USA"],"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":4,"corresponding_author_ids":["https://openalex.org/A5103749365"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":19.2815,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.99257421,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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":0.9987999796867371,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9980999827384949,"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":0.9694134593009949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8330892324447632},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6576307415962219},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6298097372055054},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6280632615089417},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.578948974609375},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5229083895683289},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4373972713947296},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42660874128341675},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32563573122024536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32532334327697754},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11784663796424866}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9694134593009949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330892324447632},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6576307415962219},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6298097372055054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6280632615089417},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.578948974609375},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5229083895683289},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4373972713947296},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42660874128341675},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32563573122024536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32532334327697754},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11784663796424866},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2882903.2882952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2882952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W26271068","https://openalex.org/W53188351","https://openalex.org/W138217685","https://openalex.org/W607505555","https://openalex.org/W1480376833","https://openalex.org/W1521062204","https://openalex.org/W1532325895","https://openalex.org/W1554944419","https://openalex.org/W1558832481","https://openalex.org/W1564381193","https://openalex.org/W1606829490","https://openalex.org/W1817561967","https://openalex.org/W1849729440","https://openalex.org/W1922017469","https://openalex.org/W2017337590","https://openalex.org/W2032775418","https://openalex.org/W2044102377","https://openalex.org/W2044849727","https://openalex.org/W2050599941","https://openalex.org/W2054141820","https://openalex.org/W2060791232","https://openalex.org/W2096689597","https://openalex.org/W2097360283","https://openalex.org/W2099102906","https://openalex.org/W2099655235","https://openalex.org/W2102458936","https://openalex.org/W2135105491","https://openalex.org/W2138542364","https://openalex.org/W2140785063","https://openalex.org/W2150630976","https://openalex.org/W2156571267","https://openalex.org/W2156909104","https://openalex.org/W2158515176","https://openalex.org/W2159080219","https://openalex.org/W2161336914","https://openalex.org/W2181574135","https://openalex.org/W2184623761","https://openalex.org/W2357449897","https://openalex.org/W2406996511","https://openalex.org/W2520381032","https://openalex.org/W2753710282","https://openalex.org/W2952817049","https://openalex.org/W2964244261","https://openalex.org/W3149201378","https://openalex.org/W4236362309","https://openalex.org/W4285719527","https://openalex.org/W4294541781","https://openalex.org/W6638875480","https://openalex.org/W7018146823"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"Closer":[0],"integration":[1],"of":[2,72,133,136,201],"machine":[3],"learning":[4],"(ML)":[5],"with":[6,69,169],"data":[7,16,138],"processing":[8],"is":[9,29,154],"a":[10,30,61],"booming":[11],"area":[12],"in":[13,84,115,159,190,198],"both":[14],"the":[15,27,70,81,105,131,199],"management":[17],"industry":[18],"and":[19,59,118,129,189],"academia.":[20],"Almost":[21],"all":[22,56],"ML":[23,94],"toolkits":[24],"assume":[25],"that":[26,80,109,175],"input":[28],"single":[31,40],"table,":[32],"but":[33],"many":[34],"datasets":[35,173],"are":[36,178],"not":[37],"stored":[38],"as":[39],"tables":[41,58],"due":[42],"to":[43,52,113,145,150,156,161,180,195],"normalization.":[44],"Thus,":[45],"analysts":[46,163],"often":[47,89],"perform":[48],"key-foreign":[49],"key":[50],"joins":[51,87,101,158,184],"obtain":[53],"features":[54,82],"from":[55],"base":[57],"apply":[60,142],"feature":[62,204],"selection":[63,205],"method,":[64],"either":[65],"explicitly":[66],"or":[67],"implicitly,":[68],"aim":[71],"improving":[73],"accuracy.":[74,140],"In":[75],"this":[76,120,165,193],"work,":[77],"we":[78,98,125],"show":[79,174],"brought":[83],"by":[85],"such":[86],"can":[88,99,185],"be":[90,186],"ignored":[91],"without":[92],"affecting":[93],"accuracy":[95,112],"significantly,":[96],"i.e.,":[97],"\"avoid":[100],"safely.\"":[102],"We":[103,141],"identify":[104],"core":[106],"technical":[107],"issue":[108,121],"could":[110],"cause":[111],"decrease":[114],"some":[116,191,202],"cases":[117],"analyze":[119],"theoretically.":[122],"Using":[123],"simulations,":[124],"validate":[126],"our":[127,143,176],"analysis":[128,144],"measure":[130],"effects":[132],"various":[134],"properties":[135],"normalized":[137,172],"on":[139],"design":[146],"easy-to-understand":[147],"decision":[148],"rules":[149,177],"predict":[151,182],"when":[152,183],"it":[153],"safe":[155],"avoid":[157],"order":[160],"help":[162],"exploit":[164],"runtime-accuracy":[166],"trade-off.":[167],"Experiments":[168],"multiple":[170],"real":[171],"able":[179],"accurately":[181],"avoided":[187],"safely,":[188],"cases,":[192],"led":[194],"significant":[196],"reductions":[197],"runtime":[200],"popular":[203],"methods.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}