{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:49:21Z","timestamp":1782161361068,"version":"3.54.5"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Research Foundation of Korea (NRF) grant"},{"name":"Korean Government [Ministry of Science and ICT (MSIT)]","award":["RS-2025-24534467"],"award-info":[{"award-number":["RS-2025-24534467"]}]},{"name":"Brain Korea 21 (BK21) FOUR funded by the Ministry of Education of Korea and the National Research Foundation of Korea"},{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","award":["IO251218-14783-01"],"award-info":[{"award-number":["IO251218-14783-01"]}],"id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3702060","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T20:03:37Z","timestamp":1781121817000},"page":"90319-90333","source":"Crossref","is-referenced-by-count":0,"title":["A Gated Attention-Based Semi-Supervised Learning Framework for Label-Scarce Tabular Data"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1875-017X","authenticated-orcid":false,"given":"Yongeun","family":"Jang","sequence":"first","affiliation":[{"name":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0416-2356","authenticated-orcid":false,"given":"Yonggon","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4063-3369","authenticated-orcid":false,"given":"Ghil-Geun","family":"Oh","sequence":"additional","affiliation":[{"name":"Samsung Electronics Co. Ltd., Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-1478","authenticated-orcid":false,"given":"Jun-Geol","family":"Baek","sequence":"additional","affiliation":[{"name":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Position: Why tabular foundation models should be a research priority","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"van Breugel"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0037"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3201576"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3229161"},{"key":"ref10","article-title":"Neural oblivious decision ensembles for deep learning on tabular data","author":"Popov","year":"2019","journal-title":"arXiv:1909.06312"},{"key":"ref11","article-title":"GANDALF: Gated adaptive network for deep automated learning of features","author":"Joseph","year":"2022","journal-title":"arXiv:2207.08548"},{"key":"ref12","article-title":"TabTransformer: Tabular data modeling using contextual embeddings","author":"Huang","year":"2020","journal-title":"arXiv:2012.06678"},{"key":"ref13","first-page":"18932","article-title":"Revisiting deep learning models for tabular data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gorishniy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref15","article-title":"SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training","volume-title":"Proc. NeurIPS 1st Table Represent. Workshop","author":"Somepalli"},{"key":"ref16","first-page":"11033","article-title":"VIME: Extending the success of self- and semi-supervised learning to tabular domain","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yoon"},{"key":"ref17","article-title":"SCARF: Self-supervised contrastive learning using random feature corruption","author":"Bahri","year":"2021","journal-title":"arXiv:2106.15147"},{"key":"ref18","article-title":"ReConTab: Regularized contrastive representation learning for tabular data","author":"Chen","year":"2023","journal-title":"arXiv:2310.18541"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29523"},{"key":"ref20","article-title":"AGATa: Attention-guided augmentation for tabular data in contrastive learning","volume-title":"Proc. NeurIPS 3rd Table Represent. Learn. Workshop","author":"Eo"},{"key":"ref21","article-title":"Deep learning within tabular data: Foundations, challenges, advances and future directions","author":"Ren","year":"2025","journal-title":"arXiv:2501.03540"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref24","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sohn"},{"key":"ref25","first-page":"2012","article-title":"Analyzing and improving representations with the soft nearest neighbor loss","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Frosst"},{"key":"ref26","article-title":"Revisiting nearest neighbor for tabular data: A deep tabular baseline two decades later","author":"Ye","year":"2024","journal-title":"arXiv:2407.03257"},{"key":"ref27","article-title":"PTaRL: Prototype-based tabular representation learning via space calibration","volume-title":"Proc. 12th Int. Conf. Learn. Represent. (ICLR)","author":"Ye"},{"key":"ref28","first-page":"1608","article-title":"Learning generative models with sinkhorn divergences","volume-title":"Proc. Int. Conf. Artif. Intell. Stat. (PMLR)","author":"Genevay"},{"key":"ref29","volume-title":"Churn Modelling","year":"2026"},{"key":"ref30","volume-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","author":"Garofolo","year":"1993"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.snb.2012.01.074"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104344"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11557107.pdf?arnumber=11557107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T19:57:34Z","timestamp":1782158254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3702060","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}