{"id":"https://openalex.org/W4390647705","doi":"https://doi.org/10.48550/arxiv.2401.02013","title":"SwitchTab: Switched Autoencoders Are Effective Tabular Learners","display_name":"SwitchTab: Switched Autoencoders Are Effective Tabular Learners","publication_year":2024,"publication_date":"2024-01-04","ids":{"openalex":"https://openalex.org/W4390647705","doi":"https://doi.org/10.48550/arxiv.2401.02013"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.02013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02013","pdf_url":"https://arxiv.org/pdf/2401.02013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.02013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101314844","display_name":"Wu Jing","orcid":"https://orcid.org/0000-0002-0181-4095"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Jing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101334167","display_name":"Suiyao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Suiyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365842","display_name":"Qi Zhao","orcid":"https://orcid.org/0000-0002-1472-702X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573357","display_name":"Renat Sergazinov","orcid":"https://orcid.org/0000-0001-5905-3674"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergazinov, Renat","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379250","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-4761-5913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654483","display_name":"Shengjie Liu","orcid":"https://orcid.org/0009-0007-6544-017X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shengjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111200418","display_name":"Chongchao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Chongchao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024180597","display_name":"Tianpei Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tianpei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035545617","display_name":"Hanqing Guo","orcid":"https://orcid.org/0000-0003-3779-4679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Hanqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100946319","display_name":"Ji Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034220067","display_name":"Daniel Cociorva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cociorva, Daniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5093666750","display_name":"Hakan Brunzel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brunzel, Hakan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5101314844"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9970999956130981,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9970999956130981,"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":0.9896000027656555,"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":0.9886000156402588,"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/salient","display_name":"Salient","score":0.8149691820144653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8080352544784546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5966247916221619},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5614324808120728},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5388211011886597},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.46679526567459106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4496975541114807},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4120129942893982},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37839561700820923},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34025439620018005},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2881626486778259}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.8149691820144653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080352544784546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5966247916221619},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5614324808120728},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5388211011886597},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.46679526567459106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4496975541114807},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4120129942893982},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37839561700820923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34025439620018005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2881626486778259},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.02013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02013","pdf_url":"https://arxiv.org/pdf/2401.02013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2401.02013","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.02013","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.02013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02013","pdf_url":"https://arxiv.org/pdf/2401.02013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390647705.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Self-supervised":[0],"representation":[1],"learning":[2],"methods":[3,27,150],"have":[4],"achieved":[5],"significant":[6],"success":[7],"in":[8,62,81,87,99,123,175],"computer":[9],"vision":[10],"and":[11,74,94,172],"natural":[12],"language":[13],"processing,":[14],"where":[15],"data":[16,30,40,78],"samples":[17],"exhibit":[18],"explicit":[19],"spatial":[20],"or":[21],"semantic":[22],"dependencies.":[23],"However,":[24],"applying":[25],"these":[26],"to":[28,34,58,71,90,96,142,163],"tabular":[29,63,116],"is":[31],"challenging":[32],"due":[33],"the":[35,104,144,159,176],"less":[36],"pronounced":[37],"dependencies":[38,61],"among":[39,77],"samples.":[41],"In":[42],"this":[43,47],"paper,":[44],"we":[45,108,130,157],"address":[46],"limitation":[48],"by":[49],"introducing":[50],"SwitchTab,":[51,107],"a":[52],"novel":[53],"self-supervised":[54],"method":[55],"specifically":[56],"designed":[57],"capture":[59],"latent":[60,177],"data.":[64,117],"SwitchTab":[65,162],"leverages":[66],"an":[67],"asymmetric":[68],"encoder-decoder":[69],"framework":[70],"decouple":[72],"mutual":[73,171],"salient":[75,134,173],"features":[76,141,174],"pairs,":[79],"resulting":[80],"more":[82],"representative":[83],"embeddings.":[84],"These":[85],"embeddings,":[86],"turn,":[88],"contribute":[89],"better":[91],"decision":[92],"boundaries":[93],"lead":[95],"improved":[97],"results":[98,119],"downstream":[100],"tasks.":[101],"To":[102],"validate":[103],"effectiveness":[105],"of":[106,146,161,169],"conduct":[109],"extensive":[110],"experiments":[111],"across":[112],"various":[113,147],"domains":[114],"involving":[115],"The":[118],"showcase":[120],"superior":[121],"performance":[122,145],"end-to-end":[124],"prediction":[125],"tasks":[126],"with":[127],"fine-tuning.":[128],"Moreover,":[129],"demonstrate":[131],"that":[132],"pre-trained":[133],"embeddings":[135],"can":[136],"be":[137],"utilized":[138],"as":[139],"plug-and-play":[140],"enhance":[143],"traditional":[148],"classification":[149],"(e.g.,":[151],"Logistic":[152],"Regression,":[153],"XGBoost,":[154],"etc.).":[155],"Lastly,":[156],"highlight":[158],"capability":[160],"create":[164],"explainable":[165],"representations":[166],"through":[167],"visualization":[168],"decoupled":[170],"space.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}