{"id":"https://openalex.org/W3197182341","doi":"https://doi.org/10.14778/3476249.3476299","title":"Tailoring data source distributions for fairness-aware data integration","display_name":"Tailoring data source distributions for fairness-aware data integration","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3197182341","doi":"https://doi.org/10.14778/3476249.3476299","mag":"3197182341"},"language":"en","primary_location":{"id":"doi:10.14778/3476249.3476299","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476299","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Tailoring_data_source_distributions_for_fairness-aware_data_integration/20246190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012572863","display_name":"Fatemeh Nargesian","orcid":"https://orcid.org/0000-0002-4710-8719"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatemeh Nargesian","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027319416","display_name":"Abolfazl Asudeh","orcid":"https://orcid.org/0000-0002-5251-6186"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abolfazl Asudeh","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087012731","display_name":"H. V. Jagadish","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. V. Jagadish","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9386,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92491408,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"14","issue":"11","first_page":"2519","last_page":"2532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.6994445323944092},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5437155961990356},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5266758799552917},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5131338238716125},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5076338052749634},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4573184847831726},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3422204554080963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13288894295692444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6994445323944092},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5437155961990356},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5266758799552917},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5131338238716125},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5076338052749634},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4573184847831726},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3422204554080963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13288894295692444},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/3476249.3476299","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476299","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"},{"id":"pmh:oai:figshare.com:article/20246190","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Tailoring_data_source_distributions_for_fairness-aware_data_integration/20246190","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.25417/uic.20246190.v1","is_oa":true,"landing_page_url":"https://doi.org/10.25417/uic.20246190.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407051395","display_name":"University of Illinois Chicago","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20246190","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Tailoring_data_source_distributions_for_fairness-aware_data_integration/20246190","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1819662813","https://openalex.org/W1961345416","https://openalex.org/W1993220166","https://openalex.org/W2014352947","https://openalex.org/W2049934117","https://openalex.org/W2057513751","https://openalex.org/W2066806792","https://openalex.org/W2096454106","https://openalex.org/W2103012681","https://openalex.org/W2115457429","https://openalex.org/W2116984840","https://openalex.org/W2118309135","https://openalex.org/W2132808937","https://openalex.org/W2148143831","https://openalex.org/W2148738951","https://openalex.org/W2150997454","https://openalex.org/W2162670686","https://openalex.org/W2193968147","https://openalex.org/W2274184223","https://openalex.org/W2293940046","https://openalex.org/W2345920755","https://openalex.org/W2421547754","https://openalex.org/W2433074751","https://openalex.org/W2563852449","https://openalex.org/W2594166818","https://openalex.org/W2666919929","https://openalex.org/W2792572948","https://openalex.org/W2798497570","https://openalex.org/W2798499404","https://openalex.org/W2798664493","https://openalex.org/W2798997222","https://openalex.org/W2807251972","https://openalex.org/W2896331720","https://openalex.org/W2926805670","https://openalex.org/W2946370960","https://openalex.org/W2948096245","https://openalex.org/W2948130259","https://openalex.org/W2948212284","https://openalex.org/W2950506967","https://openalex.org/W2950929549","https://openalex.org/W2951087162","https://openalex.org/W2952154529","https://openalex.org/W2960963589","https://openalex.org/W2962762307","https://openalex.org/W2963174348","https://openalex.org/W2963174898","https://openalex.org/W2963598698","https://openalex.org/W2963785012","https://openalex.org/W2963917042","https://openalex.org/W2985924367","https://openalex.org/W2987103574","https://openalex.org/W3012348758","https://openalex.org/W3020963419","https://openalex.org/W3023309920","https://openalex.org/W3030541197","https://openalex.org/W3030787447","https://openalex.org/W3031292160","https://openalex.org/W3037852608","https://openalex.org/W3082499364","https://openalex.org/W3083037709","https://openalex.org/W3085666889","https://openalex.org/W3086107884","https://openalex.org/W3086663505","https://openalex.org/W3102780245","https://openalex.org/W3104279192","https://openalex.org/W3123374861","https://openalex.org/W3167386453","https://openalex.org/W3174324482","https://openalex.org/W4206275166","https://openalex.org/W4220820301","https://openalex.org/W6638208828","https://openalex.org/W6704789600"],"related_works":["https://openalex.org/W2027108423","https://openalex.org/W2383918176","https://openalex.org/W1855666948","https://openalex.org/W2622997728","https://openalex.org/W2758561209","https://openalex.org/W2594414941","https://openalex.org/W1548095260","https://openalex.org/W2781711915","https://openalex.org/W2112817590","https://openalex.org/W1555291398"],"abstract_inverted_index":{"Data":[0],"scientists":[1],"often":[2,78],"develop":[3,151],"data":[4,13,25,44,54,57,73,89,116,122,171],"sets":[5],"for":[6,28,96,108],"analysis":[7,29],"by":[8],"drawing":[9],"upon":[10],"sources":[11,76,117,123],"of":[12,34,72,115,166,184],"available":[14],"to":[15,21,86],"them.":[16],"A":[17],"major":[18],"challenge":[19],"is":[20,45,77],"ensure":[22],"that":[23,139,160,180],"the":[24,56,65,91,112,128,145,162,182],"set":[26],"used":[27],"has":[30],"an":[31,105,136,152],"appropriate":[32],"representation":[33],"relevant":[35],"(demographic)":[36],"groups:":[37],"it":[38],"meets":[39],"desired":[40,66],"distribution":[41,67],"requirements.":[42,68],"Whether":[43],"collected":[46],"through":[47],"some":[48,53],"experiment":[49],"or":[50],"obtained":[51],"from":[52,58,74],"provider,":[55],"any":[59],"single":[60],"source":[61],"may":[62],"not":[63],"meet":[64],"Therefore,":[69],"a":[70,157],"union":[71],"multiple":[75],"required.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,134,150,176],"study":[84],"how":[85],"acquire":[87],"such":[88],"in":[90,101,142,169],"most":[92],"cost":[93,98,163],"effective":[94],"manner,":[95],"typical":[97],"functions":[99],"observed":[100],"practice.":[102,143],"We":[103],"present":[104],"optimal":[106],"solution":[107],"binary":[109],"groups":[110],"when":[111],"underlying":[113,146],"distributions":[114,147,168],"are":[118,148],"known":[119],"and":[120,164],"all":[121],"have":[124],"equal":[125],"costs.":[126],"For":[127],"generic":[129],"case":[130],"with":[131,156],"unequal":[132],"costs,":[133],"design":[135],"approximation":[137],"algorithm":[138],"performs":[140],"well":[141],"When":[144],"unknown,":[149],"exploration-exploitation":[153],"based":[154],"strategy":[155],"reward":[158],"function":[159],"captures":[161],"approximations":[165],"group":[167],"each":[170],"source.":[172],"Besides":[173],"theoretical":[174],"analysis,":[175],"conduct":[177],"comprehensive":[178],"experiments":[179],"confirm":[181],"effectiveness":[183],"our":[185],"algorithms.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}