{"id":"https://openalex.org/W4320024133","doi":"https://doi.org/10.1109/bigdata55660.2022.10020639","title":"Permutation-Invariant Tabular Data Synthesis","display_name":"Permutation-Invariant Tabular Data Synthesis","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024133","doi":"https://doi.org/10.1109/bigdata55660.2022.10020639"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020639","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_8382174c-c0d7-4499-a740-1e8d78473eb4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075476739","display_name":"Yujin Zhu","orcid":"https://orcid.org/0000-0002-6666-2870"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yujin Zhu","raw_affiliation_strings":["TU Delft,Computer Engineering,Delft,the Netherlands","Computer Engineering, TU Delft, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Delft,Computer Engineering,Delft,the Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Computer Engineering, TU Delft, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016185099","display_name":"Zilong Zhao","orcid":"https://orcid.org/0000-0001-6549-3414"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zilong Zhao","raw_affiliation_strings":["TU Delft,Computer Science,Delft,the Netherlands","Computer Science, TU Delft, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Delft,Computer Science,Delft,the Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Computer Science, TU Delft, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000838509","display_name":"Robert Birke","orcid":"https://orcid.org/0000-0003-1144-3707"},"institutions":[{"id":"https://openalex.org/I4210095558","display_name":"5T Torino (Italy)","ror":"https://ror.org/00k7znw93","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210095558"]},{"id":"https://openalex.org/I4210128445","display_name":"Torino e-district","ror":"https://ror.org/03cxxc369","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210128445"]},{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Robert Birke","raw_affiliation_strings":["University of Torino,Computer Science,Torino,Italy","Computer Science, University of Torino, Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Torino,Computer Science,Torino,Italy","institution_ids":["https://openalex.org/I4210095558","https://openalex.org/I4210128445","https://openalex.org/I55143463"]},{"raw_affiliation_string":"Computer Science, University of Torino, Torino, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013859152","display_name":"Lydia Y. Chen","orcid":"https://orcid.org/0000-0002-4228-6735"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lydia Y. Chen","raw_affiliation_strings":["TU Delft,Computer Science,Delft,the Netherlands","Computer Science, TU Delft, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Delft,Computer Science,Delft,the Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Computer Science, TU Delft, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5855","last_page":"5864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9997000098228455,"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":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9911999702453613,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9833999872207642,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.713512659072876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6758343577384949},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6212222576141357},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5018935203552246},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4781423807144165},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4539775848388672},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4424520432949066},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.42311742901802063},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.41644757986068726},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.41503453254699707},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4052388668060303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28777486085891724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2632770538330078},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1500718593597412}],"concepts":[{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.713512659072876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758343577384949},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6212222576141357},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5018935203552246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4781423807144165},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4539775848388672},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4424520432949066},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.42311742901802063},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.41644757986068726},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.41503453254699707},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4052388668060303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28777486085891724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2632770538330078},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1500718593597412},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020639","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:ed834654-3be7-4691-af38-e8eb6815815e","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:ed834654-3be7-4691-af38-e8eb6815815e","pdf_url":"https://repository.tudelft.nl/file/File_8382174c-c0d7-4499-a740-1e8d78473eb4","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:ed834654-3be7-4691-af38-e8eb6815815e","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:ed834654-3be7-4691-af38-e8eb6815815e","pdf_url":"https://repository.tudelft.nl/file/File_8382174c-c0d7-4499-a740-1e8d78473eb4","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4320024133.pdf","grobid_xml":"https://content.openalex.org/works/W4320024133.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2144321583","https://openalex.org/W2565167788","https://openalex.org/W2741951152","https://openalex.org/W2769152880","https://openalex.org/W2782291996","https://openalex.org/W2788592841","https://openalex.org/W2806276686","https://openalex.org/W2887146012","https://openalex.org/W2904849495","https://openalex.org/W2904931021","https://openalex.org/W2952813363","https://openalex.org/W2963274778","https://openalex.org/W2966090837","https://openalex.org/W2970360512","https://openalex.org/W2984789661","https://openalex.org/W3020873385","https://openalex.org/W3035661013","https://openalex.org/W3083145960","https://openalex.org/W3094101084","https://openalex.org/W3105026501","https://openalex.org/W3120644841","https://openalex.org/W3123788974","https://openalex.org/W3126865201","https://openalex.org/W3129829742","https://openalex.org/W3165390445","https://openalex.org/W3202428668","https://openalex.org/W3202996353","https://openalex.org/W4205944311","https://openalex.org/W4234726042","https://openalex.org/W4240161932","https://openalex.org/W4288296172","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W4388392666","https://openalex.org/W4390665506","https://openalex.org/W6735913928","https://openalex.org/W6735926176","https://openalex.org/W6743857607","https://openalex.org/W6747357560","https://openalex.org/W6755308174","https://openalex.org/W6755477022","https://openalex.org/W6757140150","https://openalex.org/W6767782324","https://openalex.org/W6780725165","https://openalex.org/W6784920712","https://openalex.org/W6790857497","https://openalex.org/W6801744293"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2752972570","https://openalex.org/W4297051394","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W2982314978"],"abstract_inverted_index":{"Tabular":[0],"data":[1,12,24,96,107,139],"synthesis":[2],"is":[3,41],"an":[4,73,132],"emerging":[5],"approach":[6],"to":[7,43,64,99,102,135,143,154,187,226,229],"circumvent":[8],"strict":[9],"regulations":[10],"on":[11,179],"privacy":[13],"while":[14],"discovering":[15],"knowledge":[16],"through":[17],"big":[18,118],"data.":[19,48],"Although":[20],"state-of-the-art":[21],"AI-based":[22],"tabular":[23,37,106,120,138],"synthesizers,":[25],"e.g.,":[26],"table-GAN,":[27],"CTGAN,":[28],"TVAE,":[29],"and":[30,72,94,108,140,148,196,215,220],"CTAB-GAN,":[31],"are":[32],"effective":[33],"at":[34],"generating":[35],"synthetic":[36,95,119,194,223],"data,":[38,121,195,224],"their":[39],"training":[40,213],"sensitive":[42],"column":[44,86,189],"permutations":[45],"of":[46,69,76,105,117,184,193,210,222],"input":[47,85],"In":[49],"this":[50],"paper,":[51],"we":[52,122,206],"first":[53],"c":[54,160],"onduct":[55],"a":[56,67,128,150],"n":[57],"e":[58,60],"xtensive":[59],"mpirical":[61],"s":[62,158],"tudy":[63],"disclose":[65],"such":[66],"property":[68,209],"permutation":[70],"invariance":[71],"in-depth":[74],"analysis":[75],"the":[77,84,89,103,109,115,137,145,176,185,188,191,197,208,218,230],"existing":[78,231],"synthesizers.":[79,173,232],"We":[80,174],"show":[81,204],"that":[82,130,205],"changing":[83],"order":[87],"worsens":[88],"statistical":[90],"difference":[91],"between":[92],"real":[93],"by":[97],"up":[98,225],"38.67%":[100],"due":[101],"encoding":[104],"network":[110,134],"architectures.":[111],"To":[112],"fully":[113],"unleash":[114],"potential":[116],"propose":[123],"two":[124],"solutions:":[125],"(i)":[126],"AE-GAN,":[127],"synthesizer":[129],"uses":[131],"autoencoder":[133],"represent":[136],"GAN":[141],"networks":[142],"synthesize":[144],"latent":[146],"representation,":[147],"(ii)":[149],"feature":[151],"sorting":[152],"algorithm":[153],"find":[155],"t":[156],"he":[157],"uitable":[159],"olumn":[161],"o":[162,164],"rder":[163],"f":[165,170],"i":[166],"nput":[167],"d":[168],"ata":[169],"or":[171],"CNN-based":[172],"evaluate":[175],"proposed":[177],"solutions":[178],"five":[180],"datasets":[181],"in":[182,199],"terms":[183],"sensitivity":[186],"permutation,":[190],"quality":[192,219],"utility":[198,221],"downstream":[200],"analyses.":[201],"Our":[202],"results":[203],"enhance":[207],"permutation-invariance":[211],"when":[212],"synthesizers":[214],"further":[216],"improve":[217],"22%,":[227],"compared":[228]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}