{"id":"https://openalex.org/W4367046778","doi":"https://doi.org/10.1145/3543507.3583297","title":"Preserving Missing Data Distribution in Synthetic Data","display_name":"Preserving Missing Data Distribution in Synthetic Data","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367046778","doi":"https://doi.org/10.1145/3543507.3583297","pmid":"https://pubmed.ncbi.nlm.nih.gov/39871994"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583297","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107953724","display_name":"Xinyue Wang","orcid":"https://orcid.org/0000-0002-5837-5361"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinyue Wang","raw_affiliation_strings":["Rutgers University, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034833184","display_name":"Hafiz Asif","orcid":"https://orcid.org/0000-0001-9674-7747"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hafiz Asif","raw_affiliation_strings":["Rutgers University, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034878799","display_name":"Jaideep Vaidya","orcid":"https://orcid.org/0000-0002-7420-6947"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaideep Vaidya","raw_affiliation_strings":["Rutgers University, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107953724"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":1.2098,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82679432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2023","issue":null,"first_page":"2110","last_page":"2121"},"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/T11719","display_name":"Data Quality and Management","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"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/missing-data","display_name":"Missing data","score":0.858062207698822},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7669181227684021},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7247445583343506},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.7173987030982971},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6176146268844604},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6137401461601257},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4738849997520447},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18522042036056519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1726406216621399},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1437058448791504}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.858062207698822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669181227684021},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7247445583343506},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.7173987030982971},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6176146268844604},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6137401461601257},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4738849997520447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18522042036056519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1726406216621399},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1437058448791504}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3543507.3583297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583297","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmid:39871994","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39871994","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... International World-Wide Web Conference. International WWW Conference","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11771246","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11771246","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11771246/pdf/nihms-2047066.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Int World Wide Web Conf","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3543507.3583297","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583297","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583297","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1211196991","display_name":null,"funder_award_id":"R35GM134927","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3450060113","display_name":null,"funder_award_id":"35GM134927","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367046778.pdf","grobid_xml":"https://content.openalex.org/works/W4367046778.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1511986666","https://openalex.org/W1529181327","https://openalex.org/W2001580090","https://openalex.org/W2040367556","https://openalex.org/W2078965693","https://openalex.org/W2109426455","https://openalex.org/W2114112206","https://openalex.org/W2115744219","https://openalex.org/W2145166639","https://openalex.org/W2146332392","https://openalex.org/W2159024459","https://openalex.org/W2187089797","https://openalex.org/W2191264216","https://openalex.org/W2227067661","https://openalex.org/W2486604124","https://openalex.org/W2773662615","https://openalex.org/W2787776426","https://openalex.org/W2794022343","https://openalex.org/W2806276686","https://openalex.org/W2921353139","https://openalex.org/W2921914364","https://openalex.org/W2944102862","https://openalex.org/W2963398989","https://openalex.org/W2963601856","https://openalex.org/W2964239418","https://openalex.org/W2965372408","https://openalex.org/W2970971581","https://openalex.org/W2990982392","https://openalex.org/W2997591727","https://openalex.org/W3010878551","https://openalex.org/W3011809564","https://openalex.org/W3012576969","https://openalex.org/W3031844875","https://openalex.org/W3055194044","https://openalex.org/W3071470454","https://openalex.org/W3082181878","https://openalex.org/W3106445281","https://openalex.org/W3106873467","https://openalex.org/W3123788974","https://openalex.org/W3141199462","https://openalex.org/W3176539131","https://openalex.org/W3176855411","https://openalex.org/W3177624059","https://openalex.org/W3197295672","https://openalex.org/W4300035993","https://openalex.org/W4307823721"],"related_works":["https://openalex.org/W2181530120","https://openalex.org/W4211215373","https://openalex.org/W2024529227","https://openalex.org/W2055961818","https://openalex.org/W2903115227","https://openalex.org/W1574575415","https://openalex.org/W3144172081","https://openalex.org/W3179858851","https://openalex.org/W3028371478","https://openalex.org/W2081476516"],"abstract_inverted_index":{"Data":[0],"from":[1,5,23,39],"Web":[2,7],"artifacts":[3],"and":[4,11,94,109],"the":[6,24,40,46,92,95,114],"is":[8,27,65,72],"often":[9],"sensitive":[10],"cannot":[12],"be":[13],"directly":[14],"shared":[15],"for":[16],"data":[17,21,26,38,76,88,97],"analysis.":[18,60],"Therefore,":[19],"synthetic":[20,75,87],"generated":[22],"real":[25,37,110],"increasingly":[28],"used":[29,73],"as":[30],"a":[31,104],"privacy-preserving":[32],"substitute.":[33],"In":[34,78],"many":[35],"cases,":[36],"web":[41],"has":[42],"missing":[43,96],"values":[44],"where":[45],"missingness":[47],"itself":[48],"possesses":[49],"important":[50],"informational":[51],"content,":[52],"which":[53],"domain":[54],"experts":[55],"leverage":[56],"to":[57,85],"improve":[58],"their":[59],"However,":[61],"this":[62,79],"information":[63],"content":[64],"lost":[66],"if":[67],"either":[68],"imputation":[69],"or":[70],"deletion":[71],"before":[74],"generation.":[77],"paper,":[80],"we":[81],"propose":[82],"several":[83],"methods":[84],"generate":[86],"that":[89],"preserve":[90],"both":[91],"observable":[93],"distributions.":[98],"An":[99],"extensive":[100],"empirical":[101],"evaluation":[102],"over":[103],"range":[105],"of":[106,116],"carefully":[107],"fabricated":[108],"world":[111],"datasets":[112],"demonstrates":[113],"effectiveness":[115],"our":[117],"approach.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}