{"id":"https://openalex.org/W4401306679","doi":"https://doi.org/10.1145/3808692","title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","display_name":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W4401306679","doi":"https://doi.org/10.1145/3808692"},"language":"en","primary_location":{"id":"doi:10.1145/3808692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808692","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3808692","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108965069","display_name":"Lingxi Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxi Cui","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","The State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"raw_orcid":"https://orcid.org/0009-0002-6314-9104","affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","institution_ids":[]},{"raw_affiliation_string":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huan Li","orcid":"https://orcid.org/0000-0003-0084-1662"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Li","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","The State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0003-0084-1662","affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","institution_ids":[]},{"raw_affiliation_string":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ke Chen","orcid":"https://orcid.org/0000-0002-3062-0900"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","The State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-3062-0900","affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","institution_ids":[]},{"raw_affiliation_string":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063921338","display_name":"Lidan Shou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lidan Shou","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","The State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0001-8062-8356","affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","institution_ids":[]},{"raw_affiliation_string":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-7483-0045"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-7483-0045","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.00365631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"58","issue":"12","first_page":"1","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.7016000151634216,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.7016000151634216,"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/generative-grammar","display_name":"Generative grammar","score":0.7117071151733398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4968922436237335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48521164059638977},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4120492935180664}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7117071151733398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4968922436237335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48521164059638977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4120492935180664}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3808692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808692","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2407.21523","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.21523","pdf_url":"https://arxiv.org/pdf/2407.21523","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.21523","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.21523","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3808692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808692","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"on":[3,25,82,145,159],"tabular":[4,12,26],"data":[5,13,27],"is":[6,63],"ubiquitous,":[7],"yet":[8],"obtaining":[9],"abundant":[10],"high-quality":[11],"for":[14,57,176],"model":[15],"training":[16],"remains":[17],"a":[18,47,67,79],"significant":[19],"obstacle.":[20],"Numerous":[21],"works":[22],"have":[23],"focused":[24],"augmentation":[28,147],"(TDA)":[29],"to":[30,65],"enhance":[31],"the":[32,52,71,83,94,146,150,160,182],"original":[33],"table":[34,155],"with":[35,78],"additional":[36],"data,":[37,131],"thereby":[38],"improving":[39],"downstream":[40],"ML":[41],"tasks.":[42],"Recently,":[43],"there":[44],"has":[45],"been":[46],"growing":[48],"interest":[49],"in":[50,181,196],"leveraging":[51],"capabilities":[53],"of":[54,70,76,93,166,184],"generative":[55,85,185],"AI":[56],"TDA.":[58,167],"Therefore,":[59],"we":[60,88],"believe":[61],"it":[62],"time":[64],"provide":[66],"comprehensive":[68],"review":[69],"progress":[72],"and":[73,103,132,154,163,173,190],"future":[74,174],"prospects":[75],"TDA,":[77,177],"particular":[80],"emphasis":[81],"trending":[84],"AI.":[86,186],"Specifically,":[87],"present":[89],"an":[90],"architectural":[91],"view":[92],"TDA":[95,114,122],"pipeline,":[96],"comprising":[97],"three":[98],"main":[99],"procedures:":[100],"pre-augmentation,":[101],"augmentation,":[102],"post-augmentation.":[104],"Pre-augmentation":[105],"summarizes":[106],"eight":[107],"commonly-used":[108],"preparation":[109],"tasks":[110],"that":[111],"facilitate":[112],"subsequent":[113],"from":[115],"different":[116],"perspectives.":[117],"Augmentation":[118],"systematically":[119],"analyzes":[120],"current":[121,171],"methods,":[123,127,134],"categorized":[124],"into":[125],"retrieval-based":[126],"which":[128,135],"retrieve":[129],"external":[130],"generation-based":[133],"generate":[136],"synthetic":[137],"data.":[138],"We":[139,168],"further":[140],"subdivide":[141],"these":[142],"methods":[143],"based":[144],"process":[148],"at":[149],"row,":[151],"column,":[152],"cell,":[153],"levels.":[156],"Post-augmentation":[157],"focuses":[158],"datasets,":[161],"evaluation":[162],"optimization":[164],"aspects":[165],"also":[169],"summarize":[170],"trends":[172],"directions":[175],"highlighting":[178],"promising":[179],"opportunities":[180],"era":[183],"The":[187],"accompanying":[188],"articles":[189],"related":[191],"resources":[192],"are":[193],"continuously":[194],"updated":[195],"GitHub.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2024-08-04T00:00:00"}