{"id":"https://openalex.org/W3139909695","doi":"https://doi.org/10.1145/3448016.3458456","title":"Correlation Sketches for Approximate Join-Correlation Queries","display_name":"Correlation Sketches for Approximate Join-Correlation Queries","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3139909695","doi":"https://doi.org/10.1145/3448016.3458456","mag":"3139909695"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3458456","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3458456","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3458456","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3458456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101972578","display_name":"A\u00e9cio Santos","orcid":"https://orcid.org/0000-0002-5124-7770"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A\u00e9cio Santos","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019389664","display_name":"Aline Bessa","orcid":"https://orcid.org/0009-0009-5486-4641"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aline Bessa","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042920909","display_name":"Fernando Chirigati","orcid":"https://orcid.org/0000-0002-9566-5835"},"institutions":[{"id":"https://openalex.org/I4210113551","display_name":"Springer Nature (United States)","ror":"https://ror.org/01xsmwp79","country_code":"US","type":"company","lineage":["https://openalex.org/I1313014049","https://openalex.org/I4210113551"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fernando Chirigati","raw_affiliation_strings":["Springer Nature, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Springer Nature, New York, NY, USA","institution_ids":["https://openalex.org/I4210113551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018420180","display_name":"Christopher Musco","orcid":"https://orcid.org/0000-0002-3118-4848"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Musco","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101972578"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":5.0916,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96234869,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1531","last_page":"1544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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":0.9993000030517578,"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/column","display_name":"Column (typography)","score":0.8080448508262634},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.797120988368988},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7958232164382935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7074311375617981},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5524935126304626},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5239450931549072},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4762166440486908},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45453789830207825},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.43234166502952576},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32198572158813477},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.21788308024406433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19606837630271912},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08398398756980896}],"concepts":[{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.8080448508262634},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.797120988368988},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7958232164382935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074311375617981},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5524935126304626},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5239450931549072},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4762166440486908},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45453789830207825},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.43234166502952576},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32198572158813477},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.21788308024406433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19606837630271912},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08398398756980896},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3448016.3458456","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3458456","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3458456","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.03353","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.03353","pdf_url":"https://arxiv.org/pdf/2104.03353","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3448016.3458456","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3458456","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3458456","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1578773895","display_name":null,"funder_award_id":"D3M program","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5456246324","display_name":null,"funder_award_id":"OAC-1640864","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7478733536","display_name":null,"funder_award_id":"1640864","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3139909695.pdf","grobid_xml":"https://content.openalex.org/works/W3139909695.grobid-xml"},"referenced_works_count":103,"referenced_works":["https://openalex.org/W588498316","https://openalex.org/W821334680","https://openalex.org/W1525949272","https://openalex.org/W1601435884","https://openalex.org/W1721994796","https://openalex.org/W1785933978","https://openalex.org/W1964082513","https://openalex.org/W1968829657","https://openalex.org/W1985110668","https://openalex.org/W1988790616","https://openalex.org/W1990750581","https://openalex.org/W1992363839","https://openalex.org/W1995945562","https://openalex.org/W1996771719","https://openalex.org/W2002070806","https://openalex.org/W2020584928","https://openalex.org/W2022858489","https://openalex.org/W2033582154","https://openalex.org/W2058991275","https://openalex.org/W2065259291","https://openalex.org/W2066588467","https://openalex.org/W2069870183","https://openalex.org/W2083966857","https://openalex.org/W2084757499","https://openalex.org/W2085845250","https://openalex.org/W2086043714","https://openalex.org/W2090403603","https://openalex.org/W2103012681","https://openalex.org/W2108223890","https://openalex.org/W2111495793","https://openalex.org/W2111669400","https://openalex.org/W2111806841","https://openalex.org/W2113952909","https://openalex.org/W2120908895","https://openalex.org/W2144982963","https://openalex.org/W2145979309","https://openalex.org/W2151310484","https://openalex.org/W2153406069","https://openalex.org/W2163855617","https://openalex.org/W2164175562","https://openalex.org/W2194630773","https://openalex.org/W2243803726","https://openalex.org/W2266594083","https://openalex.org/W2309293092","https://openalex.org/W2341748398","https://openalex.org/W2372409997","https://openalex.org/W2403035479","https://openalex.org/W2403749440","https://openalex.org/W2418258478","https://openalex.org/W2508349224","https://openalex.org/W2585438896","https://openalex.org/W2585664214","https://openalex.org/W2612048434","https://openalex.org/W2752061190","https://openalex.org/W2752350618","https://openalex.org/W2752494670","https://openalex.org/W2788550262","https://openalex.org/W2792538726","https://openalex.org/W2795089200","https://openalex.org/W2796799528","https://openalex.org/W2796930440","https://openalex.org/W2798664493","https://openalex.org/W2890276152","https://openalex.org/W2902030547","https://openalex.org/W2926805670","https://openalex.org/W2948163032","https://openalex.org/W2950817225","https://openalex.org/W2962766560","https://openalex.org/W2962868088","https://openalex.org/W2962979766","https://openalex.org/W2963174348","https://openalex.org/W2963699114","https://openalex.org/W2991530444","https://openalex.org/W2993137170","https://openalex.org/W3000710917","https://openalex.org/W3004210300","https://openalex.org/W3008881932","https://openalex.org/W3032215537","https://openalex.org/W3037352346","https://openalex.org/W3037852608","https://openalex.org/W3103317839","https://openalex.org/W3106063097","https://openalex.org/W3124277639","https://openalex.org/W4229725817","https://openalex.org/W4230112007","https://openalex.org/W4230435573","https://openalex.org/W4233413206","https://openalex.org/W4236706032","https://openalex.org/W4237055612","https://openalex.org/W4237345428","https://openalex.org/W4238472918","https://openalex.org/W4238970143","https://openalex.org/W4241185933","https://openalex.org/W4242142158","https://openalex.org/W4256327889","https://openalex.org/W4287824882","https://openalex.org/W4294570726","https://openalex.org/W4297813916","https://openalex.org/W4299841484","https://openalex.org/W4310299640","https://openalex.org/W6637783698","https://openalex.org/W6733170484","https://openalex.org/W6744529318"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W2172084996","https://openalex.org/W1966967794","https://openalex.org/W1501284171","https://openalex.org/W2397450670"],"abstract_inverted_index":{"The":[0],"increasing":[1],"availability":[2],"of":[3,38,113,136,143],"structured":[4],"datasets,":[5],"from":[6,53],"Web":[7],"tables":[8,59,100,144],"and":[9,21,48,74,101,105,110,145,153,186,197],"open-data":[10],"portals":[11],"to":[12,18,92,202],"enterprise":[13],"data,":[14,188],"opens":[15],"up":[16],"opportunities":[17],"enrich":[19],"analytics":[20],"improve":[22],"machine":[23],"learning":[24],"models":[25],"through":[26],"relational":[27],"data":[28,39],"augmentation.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,126],"introduce":[34],"a":[35,45,49,54,62,77,129,140,179],"new":[36],"class":[37],"augmentation":[40],"queries:":[41],"join-correlation":[42,151],"queries.":[43],"Given":[44],"column":[46,51,78,124],"Q":[47,84,109],"join":[50],"KQ":[52,73],"query":[55,163],"table":[56],"TQ,":[57],"retrieve":[58],"TX":[60,67,81],"in":[61],"dataset":[63],"collection":[64],"such":[65,82],"that":[66,83,132,146,159,191],"is":[68,76,85,117],"joinable":[69,99],"with":[70,87,173],"TQ":[71],"on":[72,166],"there":[75],"C":[79],"\u2208":[80],"correlated":[86,123,172],"C.":[88],"A":[89],"na\u00efve":[90],"approach":[91],"evaluate":[93],"these":[94],"queries,":[95,152],"which":[96,189],"first":[97],"finds":[98],"then":[102],"explicitly":[103],"joins":[104],"computes":[106],"correlations":[107],"between":[108],"all":[111],"columns":[112,170],"the":[114,134,162,169,174,198],"discovered":[115],"tables,":[116],"prohibitively":[118],"expensive.":[119],"To":[120],"efficiently":[121],"support":[122],"discovery,":[125],"1)":[127],"propose":[128],"sketching":[130],"method":[131],"enables":[133],"construction":[135],"an":[137],"index":[138],"for":[139,150],"large":[141],"number":[142],"provides":[147],"accurate":[148],"estimates":[149],"2)":[154],"explore":[155],"different":[156],"scoring":[157,199],"strategies":[158,200],"effectively":[160],"rank":[161],"results":[164],"based":[165],"how":[167],"well":[168],"are":[171],"query.":[175],"We":[176],"carry":[177],"out":[178],"detailed":[180],"experimental":[181],"evaluation,":[182],"using":[183],"both":[184],"synthetic":[185],"real":[187],"shows":[190],"our":[192],"sketches":[193],"attain":[194],"high":[195],"accuracy":[196],"lead":[201],"high-quality":[203],"rankings.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}