{"id":"https://openalex.org/W4379511063","doi":"https://doi.org/10.21428/594757db.4c0ffb71","title":"Improved Techniques for Training Tabular GANs Using Cramer\u2019s V Statistics","display_name":"Improved Techniques for Training Tabular GANs Using Cramer\u2019s V Statistics","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4379511063","doi":"https://doi.org/10.21428/594757db.4c0ffb71"},"language":"en","primary_location":{"id":"doi:10.21428/594757db.4c0ffb71","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.4c0ffb71","pdf_url":"https://caiac.pubpub.org/pub/0jwi0koo/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://caiac.pubpub.org/pub/0jwi0koo/download/pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092096317","display_name":"Melle Mendikowski","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Melle Mendikowski","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034157309","display_name":"B. Schindler","orcid":null},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Schindler","raw_affiliation_strings":["Universit\u00e4t Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033728229","display_name":"Thomas Schmid","orcid":"https://orcid.org/0000-0002-2849-4730"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]},{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Schmid","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg, Germany and Lancaster University in Leipzig, Germany and Universit\u00e4t Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg, Germany and Lancaster University in Leipzig, Germany and Universit\u00e4t Leipzig, Germany","institution_ids":["https://openalex.org/I68956291","https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083490672","display_name":"Ralf M\u00f6ller","orcid":"https://orcid.org/0000-0001-7389-3696"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf M\u00f6ller","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005456287","display_name":"Mattis Hartwig","orcid":"https://orcid.org/0000-0002-1507-7647"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mattis Hartwig","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Germany and singularIT GmbH, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Germany and singularIT GmbH, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092096317"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70079936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9973999857902527,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9973999857902527,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9922000169754028,"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/categorical-variable","display_name":"Categorical variable","score":0.8231217861175537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6712334156036377},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6085569858551025},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5330305099487305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5276519060134888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5030011534690857},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4859949052333832},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4529496729373932},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4490547478199005},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4165959060192108},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4129467010498047}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8231217861175537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712334156036377},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6085569858551025},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5330305099487305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5276519060134888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5030011534690857},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4859949052333832},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4529496729373932},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4490547478199005},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4165959060192108},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4129467010498047},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21428/594757db.4c0ffb71","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.4c0ffb71","pdf_url":"https://caiac.pubpub.org/pub/0jwi0koo/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21428/594757db.4c0ffb71","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.4c0ffb71","pdf_url":"https://caiac.pubpub.org/pub/0jwi0koo/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379511063.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W299440670","https://openalex.org/W1511986666","https://openalex.org/W2102148524","https://openalex.org/W2110774171","https://openalex.org/W2125389028","https://openalex.org/W2151485302","https://openalex.org/W2405756170","https://openalex.org/W2419501139","https://openalex.org/W2475287302","https://openalex.org/W2605287558","https://openalex.org/W2617573776","https://openalex.org/W2739748921","https://openalex.org/W2771630689","https://openalex.org/W2806276686","https://openalex.org/W2904367110","https://openalex.org/W2905831066","https://openalex.org/W2953141406","https://openalex.org/W2962793481","https://openalex.org/W2963090522","https://openalex.org/W2963373786","https://openalex.org/W2963809789","https://openalex.org/W3034739183","https://openalex.org/W3081380767","https://openalex.org/W3091123787","https://openalex.org/W3100321043","https://openalex.org/W3118215210","https://openalex.org/W3135287914","https://openalex.org/W3155914460","https://openalex.org/W3166254754","https://openalex.org/W3182500753","https://openalex.org/W3193917007","https://openalex.org/W3199209662","https://openalex.org/W3204937802","https://openalex.org/W4200027480","https://openalex.org/W4206912392","https://openalex.org/W4226210428","https://openalex.org/W4226348722","https://openalex.org/W4232475737","https://openalex.org/W4234296452","https://openalex.org/W4285149890","https://openalex.org/W4288296172","https://openalex.org/W4289520498","https://openalex.org/W4291302219","https://openalex.org/W4295521014","https://openalex.org/W4313342210","https://openalex.org/W4391602018","https://openalex.org/W6637568146","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6735913928","https://openalex.org/W6760105176","https://openalex.org/W6765451912","https://openalex.org/W6807002757"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W4318559728","https://openalex.org/W3183136280","https://openalex.org/W3005996785","https://openalex.org/W4386984417","https://openalex.org/W2476099471"],"abstract_inverted_index":{"Considering":[0],"the":[1,19,34,45,50,68,76,86,130,134,143,146,154,167,183,189],"growing":[2],"global":[3],"demand":[4],"for":[5,84,93,153],"machine":[6],"learning":[7,172],"training":[8],"data,":[9],"synthetic":[10],"data":[11,23,54,69,113,177,199],"generation":[12],"is":[13,41,121,142],"a":[14,61,81,122],"reasonable":[15],"way":[16],"to":[17,107,161,182],"address":[18],"versatile":[20],"challenges":[21],"in":[22,49,201],"acquisition.":[24],"Conditional":[25],"Tabular":[26],"Generative":[27,37],"Adversarial":[28,38],"Network":[29,39],"(CTGAN),":[30],"an":[31,150],"extension":[32],"of":[33,44,52,59,63,88,96,112,133,145,170,191,203],"widely":[35],"used":[36],"(GAN),":[40],"considered":[42],"one":[43],"most":[46],"promising":[47],"techniques":[48],"field":[51],"tabular":[53],"generation.":[55],"Despite":[56],"numerous":[57],"successes":[58],"CTGAN,":[60],"lack":[62],"preserving":[64,195],"categorical":[65,89,198],"dependencies":[66,90,196],"within":[67,115],"has":[70],"been":[71],"identified.":[72],"In":[73,99],"prior":[74],"work,":[75],"Cramer\u00e2\u0080\u0099s":[77],"V":[78],"(CV)":[79],"as":[80,149],"natural":[82],"metric":[83],"representing":[85],"correlation":[87],"was":[91],"proposed":[92,159],"hyperparameter":[94],"tuning":[95],"CTGAN":[97,116],"models.":[98],"this":[100],"paper,":[101],"we":[102,165],"explore":[103],"two":[104],"novel":[105],"strategies":[106],"directly":[108],"integrate":[109],"CV":[110,131,147,192],"statistics":[111,132,193],"batches":[114],"training.":[117],"The":[118,139],"first":[119],"approach":[120],"generator":[123],"loss":[124],"term":[125],"that":[126],"penalizes":[127],"differences":[128],"between":[129,197],"original":[135],"and":[136,205,211],"generated":[137],"data.":[138],"second":[140],"innovation":[141],"extraction":[144],"matrix":[148],"additional":[151],"feature":[152],"critic.":[155],"By":[156],"applying":[157],"our":[158],"methods":[160],"three":[162],"benchmark":[163],"datasets,":[164],"improve":[166],"averaged":[168],"accuracy":[169],"supervised":[171],"models":[173],"trained":[174],"on":[175,194],"synthesized":[176],"by":[178],"11":[179],"%":[180],"compared":[181],"legacy":[184],"CTGAN.":[185],"We":[186],"also":[187],"outline":[188],"impact":[190],"columns":[200],"terms":[202],"integrity":[204],"contingency":[206],"similarity,":[207],"discuss":[208],"existing":[209],"challenges,":[210],"identify":[212],"potential":[213],"improvements.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-01-21T23:30:37.877113","created_date":"2025-10-10T00:00:00"}