{"id":"https://openalex.org/W7009575229","doi":null,"title":"End-to-End Federated Diffusion Generative Models for Tabular Data","display_name":"End-to-End Federated Diffusion Generative Models for Tabular Data","publication_year":2023,"publication_date":"2023-06-22","ids":{"openalex":"https://openalex.org/W7009575229"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:cadbcbd1-04b3-463c-a96a-98e963a4bb94","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:cadbcbd1-04b3-463c-a96a-98e963a4bb94","pdf_url":"https://repository.tudelft.nl/file/File_9f28a5bd-dc4e-46eb-a1c2-20ca23aa209b","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,"listed_in":[],"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":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_9f28a5bd-dc4e-46eb-a1c2-20ca23aa209b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xu, Jiaming (author)","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Jiaming (author)","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T14509","display_name":"demographic modeling and climate adaptation","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"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/tabular-data-synthesis","display_name":"tabular data synthesis","score":0.9259999990463257},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8159999847412109},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/privacy-preserving-data-synthesis","display_name":"privacy-preserving data synthesis","score":0.843999981880188},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.8949999809265137},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.9509999752044678}],"concepts":[{"id":"https://openalex.org/C144251240","wikidata":"https://www.wikidata.org/wiki/Q7068229","display_name":"Nucleofection","level":4,"score":0.34929999709129333},{"id":"https://openalex.org/C2778283623","wikidata":"https://www.wikidata.org/wiki/Q18032200","display_name":"TSG101","level":5,"score":0.2460000067949295},{"id":"https://openalex.org/C2781032047","wikidata":"https://www.wikidata.org/wiki/Q938793","display_name":"Articular cartilage damage","level":5,"score":0.24379999935626984},{"id":"https://openalex.org/C2780904289","wikidata":"https://www.wikidata.org/wiki/Q426498","display_name":"Tantalum carbide","level":3,"score":0.23029999434947968},{"id":"https://openalex.org/C133074676","wikidata":"https://www.wikidata.org/wiki/Q428729","display_name":"Fusible alloy","level":2,"score":0.2287999987602234},{"id":"https://openalex.org/C2777054765","wikidata":"https://www.wikidata.org/wiki/Q6402731","display_name":"Dysgeusia","level":3,"score":0.22849999368190765},{"id":"https://openalex.org/C18743360","wikidata":"https://www.wikidata.org/wiki/Q1208096","display_name":"Diafiltration","level":4,"score":0.22269999980926514},{"id":"https://openalex.org/C145741570","wikidata":"https://www.wikidata.org/wiki/Q7251534","display_name":"Proteogenomics","level":5,"score":0.22190000116825104},{"id":"https://openalex.org/C2992336715","wikidata":"https://www.wikidata.org/wiki/Q63431143","display_name":"Gestational period","level":4,"score":0.2215999960899353},{"id":"https://openalex.org/C2777158700","wikidata":"https://www.wikidata.org/wiki/Q1419356","display_name":"Hyporeflexia","level":3,"score":0.21570000052452087}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:cadbcbd1-04b3-463c-a96a-98e963a4bb94","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:cadbcbd1-04b3-463c-a96a-98e963a4bb94","pdf_url":"https://repository.tudelft.nl/file/File_9f28a5bd-dc4e-46eb-a1c2-20ca23aa209b","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,"listed_in":[],"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":"master thesis"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:cadbcbd1-04b3-463c-a96a-98e963a4bb94","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:cadbcbd1-04b3-463c-a96a-98e963a4bb94","pdf_url":"https://repository.tudelft.nl/file/File_9f28a5bd-dc4e-46eb-a1c2-20ca23aa209b","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,"listed_in":[],"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":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7009575229.pdf","grobid_xml":"https://content.openalex.org/works/W7009575229.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2464785945","https://openalex.org/W2995289379","https://openalex.org/W3006853572","https://openalex.org/W3110257065","https://openalex.org/W3193989161","https://openalex.org/W4300980427","https://openalex.org/W4304700981","https://openalex.org/W4306178203","https://openalex.org/W4306893236","https://openalex.org/W4390665506"],"related_works":["https://openalex.org/W4390897376","https://openalex.org/W4313472309","https://openalex.org/W4416125782","https://openalex.org/W4387723908","https://openalex.org/W4386301915","https://openalex.org/W4405716301","https://openalex.org/W4413913950","https://openalex.org/W7126026159","https://openalex.org/W4387005651","https://openalex.org/W7162533418"],"abstract_inverted_index":{"Tabular":[0],"data":[1,15,34,41,94,198,209],"is":[2,27,75],"widely":[3],"used":[4],"in":[5,52,72,149,197,208,213],"various":[6],"fields":[7],"and":[8,130,141,153,173,179,195,200,204,206,211],"applications,":[9],"making":[10],"the":[11,28,48,53,92,103,138],"synthesis":[12],"of":[13,19,24,30,50,78,127],"such":[14,59],"an":[16,128],"active":[17],"area":[18],"research.":[20],"One":[21],"important":[22],"aspect":[23],"this":[25,107],"research":[26],"development":[29],"methods":[31,192],"for":[32,82,99],"privacy-preserving":[33,104],"synthesis,":[35,68],"which":[36,117],"aims":[37],"to":[38,95,133],"generate":[39],"synthetic":[40],"that":[42,168,186],"retains":[43],"statistical":[44],"properties":[45],"while":[46],"protecting":[47],"privacy":[49,157],"individuals":[51],"dataset.":[54],"Recently,":[55],"Diffusion":[56,62],"Generative":[57],"Models,":[58],"as":[60],"Gaussian":[61],"Model,":[63],"have":[64],"significantly":[65],"improved":[66],"image":[67],"but":[69],"their":[70],"effectiveness":[71],"synthesizing":[73,115],"tables":[74],"limited,":[76],"because":[77],"using":[79,175],"One-Hot":[80],"encoding":[81],"representing":[83],"categorical":[84],"attributes":[85],"with":[86],"many":[87],"categories.":[88],"Furthermore,":[89],"it":[90],"needs":[91],"private":[93],"be":[96],"centrally":[97],"collected":[98],"training,":[100],"thus":[101],"violating":[102],"criteria.":[105],"In":[106],"paper,":[108],"we":[109],"propose":[110],"a":[111,123,131,144,150],"new":[112],"decentralized":[113,124,151],"tabular":[114,145,177],"framework,":[116],"has":[118],"three":[119],"key":[120],"features:":[121],"(i)":[122],"Autoencoder":[125],"comprised":[126],"encoder":[129],"decoder":[132],"map":[134],"discrete":[135],"features":[136],"into":[137],"continuous":[139],"space":[140],"back,":[142],"(ii)":[143],"diffusion":[146],"model":[147],"trained":[148],"manner":[152],"(iii)":[154],"incorporating":[155],"differential":[156],"on":[158,170,202],"central":[159,191],"stochastic":[160],"gradient":[161],"training.":[162],"We":[163],"conduct":[164],"extensive":[165],"experimental":[166],"studies":[167],"focus":[169],"sampling":[171],"quality":[172,199,210],"diversity,":[174],"9":[176],"datasets":[178],"4":[180],"state-of-the-art":[181],"synthesizers.":[182],"The":[183],"results":[184],"show":[185],"our":[187],"method":[188],"outperforms":[189],"existing":[190],"by":[193],"10.7%":[194],"31.4%":[196],"diversity":[201,212],"average,":[203],"6.8%":[205],"21.1%":[207],"scenarios":[214],"facing":[215],"non-IID":[216],"data.":[217]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}