{"id":"https://openalex.org/W4297796148","doi":"https://doi.org/10.1145/3548785.3548793","title":"Synthetic Data Generation: A Comparative Study","display_name":"Synthetic Data Generation: A Comparative Study","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4297796148","doi":"https://doi.org/10.1145/3548785.3548793"},"language":"en","primary_location":{"id":"doi:10.1145/3548785.3548793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548785.3548793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Database Engineered Applications Symposium","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/A5046756404","display_name":"Markus Endres","orcid":"https://orcid.org/0000-0002-6436-559X"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Markus Endres","raw_affiliation_strings":["University of Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025700243","display_name":"Asha Mannarapotta Venugopal","orcid":null},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Asha Mannarapotta Venugopal","raw_affiliation_strings":["University of Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111179029","display_name":"Tung S Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tung Son Tran","raw_affiliation_strings":["University of Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046756404"],"corresponding_institution_ids":["https://openalex.org/I186354981"],"apc_list":null,"apc_paid":null,"fwci":5.4161,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96231873,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9979000091552734,"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":0.9979000091552734,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751608490943909},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.7161777019500732},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.54262375831604},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5245733261108398},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.5132055282592773},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49461671710014343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4899689257144928},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.48991483449935913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.450010746717453},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.44498729705810547},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.4284762740135193},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4176172912120819},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36953169107437134},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2254256010055542},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.18376019597053528},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08066648244857788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751608490943909},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.7161777019500732},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.54262375831604},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5245733261108398},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.5132055282592773},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49461671710014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4899689257144928},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.48991483449935913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450010746717453},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.44498729705810547},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.4284762740135193},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4176172912120819},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36953169107437134},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2254256010055542},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.18376019597053528},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08066648244857788},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3548785.3548793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548785.3548793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Database Engineered Applications Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:96769","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/96769","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W282035811","https://openalex.org/W2565167788","https://openalex.org/W2622579191","https://openalex.org/W2792626417","https://openalex.org/W2899071785","https://openalex.org/W2921914364","https://openalex.org/W4234268021","https://openalex.org/W4311415873","https://openalex.org/W4399588179"],"related_works":["https://openalex.org/W2883697671","https://openalex.org/W3172329356","https://openalex.org/W2924440852","https://openalex.org/W2951578466","https://openalex.org/W2594717275","https://openalex.org/W3126767825","https://openalex.org/W3111180383","https://openalex.org/W4300436850","https://openalex.org/W4221167279","https://openalex.org/W4386597559"],"abstract_inverted_index":{"Generating":[0],"synthetic":[1,25],"data":[2,6,12,15,23,26,54,115,137,140,151],"similar":[3],"to":[4,18,55,113,118],"realistic":[5],"is":[7,70,161],"a":[8,67],"crucial":[9],"task":[10],"in":[11],"augmentation":[13],"and":[14,32,108,126,138,154],"production.":[16],"Due":[17],"the":[19,46,74,123,147,155,166],"preservation":[20],"of":[21,29,76,149,158,165],"authentic":[22],"distribution,":[24],"provide":[27],"concealment":[28],"sensitive":[30],"information":[31],"therefore":[33],"enable":[34],"Big":[35],"Data":[36,93,97,128],"acquisition":[37],"for":[38,141],"model":[39,160],"training":[40],"without":[41],"facing":[42],"privacy":[43],"challenges.":[44],"Nevertheless,":[45],"obstacles":[47],"arise":[48],"starting":[49],"with":[50,99,116],"acquiring":[51],"real-world":[52],"open-source":[53],"effectively":[56],"synthesizing":[57],"new":[58],"samples":[59],"as":[60,62,131,163],"genuine":[61],"possible.":[63],"In":[64],"this":[65,144],"paper,":[66],"comparative":[68],"study":[69],"conducted":[71],"by":[72],"considering":[73],"efficacy":[75],"different":[77],"generative":[78],"models":[79],"like":[80],"Generative":[81,104],"Adversarial":[82,105],"Networks":[83,106],"(GAN),":[84],"Variational":[85],"Autoencoder":[86],"(VAE),":[87],"Synthetic":[88,96,127],"Minority":[89],"Oversampling":[90],"Technique":[91],"(SMOTE),":[92],"Synthesizer":[94],"(DS),":[95],"Vault":[98],"Gaussian":[100],"Copula":[101],"(SDV-G),":[102],"Conditional":[103],"(SDV-GAN),":[107],"SynthPop":[109],"Non-Parametric":[110],"(SP-NP)":[111],"approach":[112],"synthesize":[114],"regard":[117],"various":[119,150],"datasets.":[120],"We":[121],"used":[122],"pairwise":[124],"correlation":[125],"(SD)":[129],"metrics":[130],"utility":[132],"measures":[133],"respectively":[134],"between":[135],"real":[136],"generated":[139],"evaluation.":[142],"Accordingly,":[143],"paper":[145],"investigates":[146],"effects":[148],"generation":[152],"models,":[153],"processing":[156],"time":[157],"every":[159],"included":[162],"one":[164],"evaluation":[167],"metrics.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}