{"id":"https://openalex.org/W4404088722","doi":"https://doi.org/10.48550/arxiv.2410.15516","title":"Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching","display_name":"Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4404088722","doi":"https://doi.org/10.48550/arxiv.2410.15516"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.15516","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15516","pdf_url":"https://arxiv.org/pdf/2410.15516","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.15516","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114534402","display_name":"Ange-Cl\u00e9ment Akazan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Akazan, Ange-Cl\u00e9ment","raw_affiliation_strings":["Mila Qu\u00e9bec AI Institute , Universit\u00e9 de Montr\u00e9al , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila Qu\u00e9bec AI Institute , Universit\u00e9 de Montr\u00e9al , Canada","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011012516","display_name":"Alexia Jolicoeur\u2010Martineau","orcid":"https://orcid.org/0000-0003-2169-4008","observed_orcids":["https://orcid.org/0000-0003-2169-4008"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jolicoeur-Martineau, Alexia","raw_affiliation_strings":["SAIT Montreal AI Lab , Montr\u00e9al , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT Montreal AI Lab , Montr\u00e9al , Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088076429","display_name":"Ioannis Mitliagkas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112059","display_name":"African Institute for Mathematical Sciences","ror":"https://ror.org/02w32z542","country_code":"RW","type":"education","lineage":["https://openalex.org/I4210112059"]},{"id":"https://openalex.org/I4405261291","display_name":"AIMS Research and Innovation Centre","ror":"https://ror.org/052gr0y82","country_code":"RW","type":"education","lineage":["https://openalex.org/I4405261291"]}],"countries":["RW"],"is_corresponding":false,"raw_author_name":"Mitliagkas, Ioannis","raw_affiliation_strings":["AIMS Research and Innovation Center , Kigali , Rwanda"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIMS Research and Innovation Center , Kigali , Rwanda","institution_ids":["https://openalex.org/I4210112059","https://openalex.org/I4405261291"]}]}],"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":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":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5371000170707703,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5371000170707703,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.10249999910593033,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.09300000220537186,"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/tabular-data-generation","display_name":"tabular data generation","score":0.9739999771118164},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.8529999852180481},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.9850000143051147},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.8920000195503235},{"id":"https://openalex.org/keywords/multinomial-sampling","display_name":"multinomial sampling","score":0.9810000061988831},{"id":"https://openalex.org/keywords/ordinary-differential-equations","display_name":"ordinary differential equations","score":0.8019999861717224},{"id":"https://openalex.org/keywords/sensitivity-to-initial-conditions","display_name":"sensitivity to initial conditions","score":0.7419999837875366},{"id":"https://openalex.org/keywords/affine-transformation-robustness","display_name":"affine transformation robustness","score":0.7360000014305115},{"id":"https://openalex.org/keywords/privacy-preserving-machine-learning","display_name":"privacy-preserving machine learning","score":0.6690000295639038}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6771336197853088},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6237672567367554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5571091175079346},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.480493426322937},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4703769087791443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41348063945770264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3572685420513153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21998435258865356},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.1785644292831421},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1607511043548584},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.15516","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15516","pdf_url":"https://arxiv.org/pdf/2410.15516","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.15516","doi":"https://doi.org/10.48550/arxiv.2410.15516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.15516","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.15516","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15516","pdf_url":"https://arxiv.org/pdf/2410.15516","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330273","display_name":"Institut de Valorisation des Donn\u00e9es","ror":"https://ror.org/05a3srq89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404088722.pdf","grobid_xml":"https://content.openalex.org/works/W4404088722.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2806276686","https://openalex.org/W3110257065","https://openalex.org/W3202428668","https://openalex.org/W3215969524","https://openalex.org/W4392302553"],"related_works":["https://openalex.org/W7140030102","https://openalex.org/W7221806207","https://openalex.org/W7214345046","https://openalex.org/W7158574338","https://openalex.org/W4406745586","https://openalex.org/W4408423705","https://openalex.org/W7126026159","https://openalex.org/W4416953475","https://openalex.org/W4413913950","https://openalex.org/W7127157634"],"abstract_inverted_index":{"Privacy":[0],"and":[1,43,155],"regulatory":[2],"constraints":[3],"make":[4],"data":[5,22,87,159,169],"generation":[6,23,122],"vital":[7],"to":[8,59,184,193,208],"advancing":[9],"machine":[10],"learning":[11],"without":[12],"relying":[13],"on":[14,93],"real-world":[15],"datasets.":[16],"A":[17],"leading":[18],"approach":[19],"for":[20,134,163,173],"tabular":[21],"is":[24,41,55],"the":[25,63,67,91,98,138,200],"Forest":[26,81],"Flow":[27,32,82],"(FF)":[28],"method,":[29],"which":[30],"combines":[31],"Matching":[33],"with":[34,146,175],"XGBoost.":[35],"Despite":[36],"its":[37],"good":[38],"performance,":[39],"FF":[40],"slow":[42],"makes":[44],"errors":[45],"when":[46],"treating":[47],"categorical":[48,108,164,177],"variables":[49,109],"as":[50],"one-hot":[51],"continuous":[52],"features.":[53,104],"It":[54,166],"also":[56,125,167,203],"highly":[57],"sensitive":[58],"small":[60],"changes":[61],"in":[62,142,187],"initial":[64,95,190],"conditions":[65,96,191],"of":[66,118],"ordinary":[68],"differential":[69],"equation":[70],"(ODE).":[71],"To":[72],"overcome":[73],"these":[74],"limitations,":[75],"we":[76],"develop":[77],"Heterogeneous":[78],"Sequential":[79],"Feature":[80],"(HS3F).":[83],"Our":[84,144],"method":[85],"generates":[86,107,168],"sequentially":[88],"(feature-by-feature),":[89],"reducing":[90],"dependency":[92],"noisy":[94],"through":[97],"additional":[99],"information":[100],"from":[101],"previously":[102],"generated":[103],"Furthermore,":[105],"it":[106],"using":[110],"multinomial":[111],"sampling":[112],"(from":[113],"an":[114],"XGBoost":[115],"classifier)":[116],"instead":[117],"flow":[119,188],"matching,":[120],"improving":[121],"speed.":[123],"We":[124],"use":[126],"a":[127],"Runge-Kutta":[128],"4th":[129],"order":[130],"(Rg4)":[131],"ODE":[132,189],"solver":[133,140],"improved":[135],"performance":[136],"over":[137],"Euler":[139],"used":[141],"FF.":[143,194],"experiments":[145],"25":[147],"datasets":[148,174],"reveal":[149],"that":[150],"HS3F":[151,179,201],"produces":[152],"higher":[153],"quality":[154],"more":[156],"diverse":[157],"synthetic":[158],"than":[160],"FF,":[161],"especially":[162],"variables.":[165,178],"21-27":[170],"times":[171],"faster":[172],"$\\geq20%$":[176],"further":[180],"demonstrates":[181],"enhanced":[182],"robustness":[183],"affine":[185],"transformation":[186],"compared":[192],"This":[195],"study":[196],"not":[197],"only":[198],"validates":[199],"but":[202],"unveils":[204],"promising":[205],"new":[206],"strategies":[207],"advance":[209],"generative":[210],"models.":[211]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-11-06T00:00:00"}