{"id":"https://openalex.org/W4406458747","doi":"https://doi.org/10.1109/bigdata62323.2024.10826064","title":"TabularFM: An Open Framework For Tabular Foundational Models","display_name":"TabularFM: An Open Framework For Tabular Foundational Models","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458747","doi":"https://doi.org/10.1109/bigdata62323.2024.10826064"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10826064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088937688","display_name":"Quan M. Tran","orcid":"https://orcid.org/0000-0002-7931-4525"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Quan M. Tran","raw_affiliation_strings":["Vietnam National University,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"Vietnam National University,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068110591","display_name":"Suong N. Hoang","orcid":"https://orcid.org/0000-0002-3354-013X"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Suong N. Hoang","raw_affiliation_strings":["Vietnam National University,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"Vietnam National University,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099172409","display_name":"Lam M. Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lam M. Nguyen","raw_affiliation_strings":["IBM Research,Yorktown Heights,US"],"affiliations":[{"raw_affiliation_string":"IBM Research,Yorktown Heights,US","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036688203","display_name":"Dzung T. Phan","orcid":"https://orcid.org/0000-0003-1579-7035"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dzung Phan","raw_affiliation_strings":["IBM Research,Yorktown Heights,US"],"affiliations":[{"raw_affiliation_string":"IBM Research,Yorktown Heights,US","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027999872","display_name":"Hoang Thanh Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145784","display_name":"IBM Research - Ireland","ror":"https://ror.org/04jnxr720","country_code":"IE","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145784"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Hoang Thanh Lam","raw_affiliation_strings":["IBM Research,Dublin,Ireland"],"affiliations":[{"raw_affiliation_string":"IBM Research,Dublin,Ireland","institution_ids":["https://openalex.org/I4210145784"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088937688"],"corresponding_institution_ids":["https://openalex.org/I123565023"],"apc_list":null,"apc_paid":null,"fwci":0.5198,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69424231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1694","last_page":"1699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9807000160217285,"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/T10028","display_name":"Topic Modeling","score":0.9793999791145325,"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/computer-science","display_name":"Computer science","score":0.6544240713119507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6544240713119507}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10826064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1597533204","https://openalex.org/W2194775991","https://openalex.org/W2492794003","https://openalex.org/W2612690371","https://openalex.org/W2902901670","https://openalex.org/W2919115771","https://openalex.org/W2991044292","https://openalex.org/W3158303960","https://openalex.org/W3160590016","https://openalex.org/W3174086521","https://openalex.org/W4205922070","https://openalex.org/W4210490374","https://openalex.org/W4281260498","https://openalex.org/W4288296172","https://openalex.org/W4292779060","https://openalex.org/W4313485929","https://openalex.org/W4327550249","https://openalex.org/W4365456672","https://openalex.org/W4385245566","https://openalex.org/W4387596222","https://openalex.org/W4396641616","https://openalex.org/W6635726886","https://openalex.org/W6680532216","https://openalex.org/W6735913928","https://openalex.org/W6756556786","https://openalex.org/W6765451912","https://openalex.org/W6778883912","https://openalex.org/W6807402356","https://openalex.org/W6838540236","https://openalex.org/W6838847448","https://openalex.org/W6845642338","https://openalex.org/W6845816046","https://openalex.org/W6846967249","https://openalex.org/W6850545974","https://openalex.org/W6857700311"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Foundational":[0],"models":[1,178],"(FMs),":[2],"pretrained":[3,161,177],"on":[4,49,54,96,163,171],"extensive":[5,26],"datasets":[6,28,92,148],"using":[7],"self-supervised":[8],"techniques,":[9],"are":[10],"capable":[11],"of":[12,19,90,99,133,157,194,197],"learning":[13,169],"generalized":[14],"patterns":[15],"from":[16],"large":[17],"amounts":[18],"data.":[20,129],"This":[21,130],"reduces":[22],"the":[23,40,97,155,176,195],"need":[24],"for":[25,29,101,123,127,182],"labeled":[27],"each":[30],"new":[31],"task,":[32],"saving":[33],"both":[34],"time":[35],"and":[36,60,93,140,149,174],"resources":[37],"by":[38],"leveraging":[39],"broad":[41],"knowledge":[42],"base":[43],"established":[44],"during":[45],"pretraining.":[46],"Most":[47],"research":[48,95],"FMs":[50,100,125,162],"has":[51,69],"primarily":[52],"focused":[53],"unstructured":[55],"data,":[56,64,75,79,166],"such":[57,76,136],"as":[58,77,137],"text":[59],"images,":[61],"or":[62],"semi-structured":[63],"like":[65],"time-series.":[66],"However,":[67],"there":[68],"been":[70],"limited":[71],"attention":[72],"to":[73,87,108,153],"structured":[74],"tabular":[78,103,128,147,158,198],"which,":[80],"despite":[81],"its":[82],"prevalence,":[83],"remains":[84],"under-studied":[85],"due":[86],"a":[88,113,145,191],"lack":[89],"clean":[91],"insufficient":[94],"transferability":[98,196],"various":[102,168],"data":[104],"tasks.":[105],"In":[106],"response":[107],"this":[109,164],"gap,":[110],"we":[111],"introduce":[112],"framework":[114],"called":[115],"TabularFM<sup":[116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[118],"which":[119],"incorporates":[120],"state-of-the-art":[121],"methods":[122,170],"developing":[124],"specifically":[126],"includes":[131],"variations":[132],"neural":[134],"architectures":[135],"GANs,":[138],"VAEs,":[139],"Transformers.":[141],"We":[142,160],"have":[143],"curated":[144,165],"thousand":[146],"released":[150,175],"cleaned":[151],"versions":[152],"facilitate":[154],"development":[156],"FMs.":[159,199],"benchmarked":[167],"these":[172],"datasets,":[173],"along":[179],"with":[180],"leaderboards":[181],"future":[183],"comparative":[184],"studies.":[185],"Our":[186],"fully":[187],"open-sourced":[188],"system":[189],"provides":[190],"comprehensive":[192],"analysis":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}