{"id":"https://openalex.org/W7166817281","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2053","title":"MaskTab: Scalable Masked Tabular Pretraining with Scaling Laws and Distillation for Industrial Classification","display_name":"MaskTab: Scalable Masked Tabular Pretraining with Scaling Laws and Distillation for Industrial Classification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166817281","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2053"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2053","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2053","pdf_url":"https://aclanthology.org/2026.findings-acl.2053.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.2053.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139732377","display_name":"Bo Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060774236","display_name":"Yudong Chen","orcid":"https://orcid.org/0000-0002-6416-5635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yudong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139820861","display_name":"Zihua Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihua Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139759218","display_name":"Shuai Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139847266","display_name":"Peidong He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peidong He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139780088","display_name":"Yang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139727007","display_name":"Sheng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Guo","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90153936,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41268","last_page":"41280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12141","display_name":"Fluid Dynamics and Thin Films","score":0.11320000141859055,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12141","display_name":"Fluid Dynamics and Thin Films","score":0.11320000141859055,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.035100001841783524,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11053","display_name":"Process Optimization and Integration","score":0.024399999529123306,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.51910001039505},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.499099999666214},{"id":"https://openalex.org/keywords/scaling-law","display_name":"Scaling law","score":0.4706000089645386},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.40450000762939453},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5871000289916992},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.4706000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39399999380111694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2053","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2053","pdf_url":"https://aclanthology.org/2026.findings-acl.2053.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2053","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2053","pdf_url":"https://aclanthology.org/2026.findings-acl.2053.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166817281.pdf","grobid_xml":"https://content.openalex.org/works/W7166817281.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tabular":[0],"data":[1,150],"forms":[2],"the":[3,70],"backbone":[4],"of":[5],"high-stakes":[6],"decision":[7],"systems":[8],"in":[9],"finance,":[10],"healthcare,":[11],"and":[12,25,35,44,112,131,137],"beyond.Yet":[13],"industrial":[14],"tabular":[15,37,60,149],"datasets":[16],"are":[17,158],"inherently":[18],"difficult:":[19],"high-dimensional,":[20],"riddled":[21],"with":[22,93],"missing":[23,63],"entries,":[24],"rarely":[26],"labeled":[27],"at":[28],"scale.While":[29],"foundation":[30],"models":[31],"have":[32],"revolutionized":[33],"vision":[34],"language,":[36],"learning":[38],"still":[39],"leans":[40],"on":[41],"handcrafted":[42],"features":[43,102],"lacks":[45],"a":[46,52,81,86,152],"general":[47],"self-supervised":[48],"framework.We":[49],"present":[50],"MaskTab,":[51],"unified":[53],"pre-training":[54,84],"framework":[55],"designed":[56],"specifically":[57],"for":[58],"industrialscale":[59],"data.MaskTab":[61],"encodes":[62],"values":[64],"via":[65],"dedicated":[66],"learnable":[67],"tokens,":[68],"enabling":[69],"model":[71],"to":[72,89,143],"distinguish":[73],"structural":[74,156],"absence":[75],"from":[76],"random":[77],"dropout.It":[78],"jointly":[79],"optimizes":[80],"hybrid":[82],"supervised":[83],"scheme-utilizing":[85],"twin-path":[87],"architecture":[88],"reconcile":[90],"masked":[91],"reconstruction":[92],"taskspecific":[94],"supervision-and":[95],"an":[96],"MoE-augmented":[97],"loss":[98],"that":[99,148],"adaptively":[100],"routes":[101],"through":[103],"specialized":[104],"subnetworks.On":[105],"industrial-scale":[106],"benchmarks,":[107],"it":[108],"achieves":[109],"+5.04%":[110],"AUC":[111,130],"+8.28%":[113],"KS":[114,133],"over":[115],"prior":[116],"art":[117],"under":[118,134],"rigorous":[119],"scaling.Moreover,":[120],"its":[121,155],"representations":[122],"distill":[123],"effectively":[124],"into":[125],"lightweight":[126],"models,":[127],"yielding":[128],"+2.55%":[129],"+4.85%":[132],"strict":[135],"latency":[136],"interpretability":[138],"constraints,":[139],"while":[140],"improving":[141],"robustness":[142],"distribution":[144],"shifts.Our":[145],"work":[146],"demonstrates":[147],"admits":[151],"foundation-model":[153],"treatment-when":[154],"idiosyncrasies":[157],"respected.":[159]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}