{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T07:32:02Z","timestamp":1784619122054,"version":"3.55.0"},"reference-count":263,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Natural Science Foundation of Jiangsu Province of China","award":["BK20250062"],"award-info":[{"award-number":["BK20250062"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376118"],"award-info":[{"award-number":["62376118"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62522605"],"award-info":[{"award-number":["62522605"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3657217","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:03:08Z","timestamp":1769806988000},"page":"6488-6508","source":"Crossref","is-referenced-by-count":13,"title":["Representation Learning for Tabular Data: A Comprehensive Survey"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5744-8126","authenticated-orcid":false,"given":"Jun-Peng","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University, and National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si-Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University, and National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Run","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University, and National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3492-9697","authenticated-orcid":false,"given":"Qi-Le","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University, and National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1173-1880","authenticated-orcid":false,"given":"Han-Jia","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University, and National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Data Mining in Finance: Advances in Relational and Hybrid Methods","author":"Kovalerchuk","year":"2005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0789-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2053532"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-85820-3_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.082099299"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/9780470116449.ch6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/07474938.2010.481556"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature01092a"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3229161"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-14142-8","volume-title":"Data Mining - the Textbook","author":"Aggarwal","year":"2015"},{"key":"ref11","article-title":"Differential privacy and machine learning: A survey and review","author":"Ji","year":"2014"},{"issue":"1","key":"ref12","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"Delgado","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7566-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref15","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7068349"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref20","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1097\/00003643-201406001-00333"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref23","first-page":"384","article-title":"Learning a parametric embedding by preserving local structure","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Van Der Maaten"},{"key":"ref24","first-page":"791","article-title":"Deep supervised t-distributed embedding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min"},{"key":"ref25","first-page":"45","article-title":"Deep learning over multi-field categorical data\u2014A case study on user response prediction","volume-title":"Proc. Eur. Conf. Inf. Retrieval","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_61713"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2015.06.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0209"},{"key":"ref29","first-page":"18932","article-title":"Revisiting deep learning models for tabular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gorishniy"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0837"},{"key":"ref31","article-title":"Revisiting nearest neighbor for tabular data: A deep tabular baseline two decades later","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ye"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0037"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1869"},{"key":"ref35","first-page":"76336","article-title":"When do neural nets outperform boosted trees on tabular data?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"McElfresh"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901675"},{"key":"ref37","first-page":"33563","article-title":"Turning the tables: Biased, imbalanced, dynamic tabular datasets for ML evaluation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jesus"},{"key":"ref38","article-title":"Towards quantifying the effect of datasets for benchmarking: A look at tabular machine learning","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Kohli"},{"key":"ref39","first-page":"40043","article-title":"TabPFN unleashed: A scalable and effective solution to tabular classification problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref40","first-page":"50817","article-title":"TabICL: A tabular foundation model for in-context learning on large data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qu"},{"key":"ref41","article-title":"TabDPT: Scaling tabular foundation models on real data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref42","article-title":"A closer look at deep learning on tabular data","author":"Ye","year":"2024"},{"key":"ref43","first-page":"24991","article-title":"On embeddings for numerical features in tabular deep learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gorishniy"},{"key":"ref44","first-page":"18853","article-title":"Subtab: Subsetting features of tabular data for self-supervised representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ucar"},{"key":"ref45","article-title":"SCARF: Self-supervised contrastive learning using random feature corruption","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bahri"},{"key":"ref46","first-page":"11033","article-title":"VIME: Extending the success of self- and semi-supervised learning to tabular domain","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yoon"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29523"},{"key":"ref48","first-page":"23928","article-title":"Well-tuned simple nets excel on tabular datasets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kadra"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"ref50","first-page":"971","article-title":"Self-normalizing neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Klambauer"},{"key":"ref51","article-title":"TabNN: A universal neural network solution for tabular data","author":"Ke","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20309"},{"key":"ref54","article-title":"TabCaps: A capsule neural network for tabular data classification with bow routing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671964"},{"key":"ref56","first-page":"55048","article-title":"Bishop: Bi-directional cellular learning for tabular data with generalized sparse modern hopfield model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref57","article-title":"Gradient boosting neural networks: Grownet","author":"Badirli","year":"2020"},{"key":"ref58","article-title":"Neural oblivious decision ensembles for deep learning on tabular data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Popov"},{"key":"ref59","article-title":"NODE-GAM: Neural generalized additive model for interpretable deep learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"ref61","article-title":"TabTransformer: Tabular data modeling using contextual embeddings","author":"Huang","year":"2020"},{"key":"ref62","article-title":"Unlocking the transferability of tokens in deep models for tabular data","author":"Zhou","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671893"},{"key":"ref64","article-title":"Tangos: Regularizing tabular neural networks through gradient orthogonalization and specialization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jeffares"},{"key":"ref65","article-title":"Ptarl: Prototype-based tabular representation learning via space calibration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ye"},{"key":"ref66","first-page":"16296","article-title":"DNNR: Differential nearest neighbors regression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nader"},{"key":"ref67","article-title":"TabR: Tabular deep learning meets nearest neighbors in 2023","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gorishniy"},{"key":"ref68","article-title":"SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Somepalli"},{"key":"ref69","article-title":"Revisiting pretraining objectives for tabular deep learning","author":"Rubachev","year":"2022"},{"key":"ref70","article-title":"TabRet: Pre-training transformer-based tabular models for unseen columns","author":"Onishi","year":"2023"},{"key":"ref71","first-page":"31030","article-title":"Cross-modal fine-tuning: Align then refine","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shen"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90923-y"},{"key":"ref73","article-title":"TablEye: Seeing small tables through the lens of images","author":"Lee","year":"2023"},{"key":"ref74","first-page":"2902","article-title":"TransTab: Learning transferable tabular transformers across tables","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref75","article-title":"Making pre-trained language models great on tabular prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yan"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645707"},{"key":"ref77","first-page":"5549","article-title":"TabLLM: Few-shot classification of tabular data with large language models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hegselmann"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671975"},{"key":"ref79","first-page":"17454","article-title":"Large language models can automatically engineer features for few-shot tabular learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671451"},{"key":"ref82","article-title":"Rethinking pre-training in tabular data: A neighborhood embedding perspective","author":"Ye","year":"2025"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28988"},{"key":"ref84","article-title":"Mothernet: Fast training and inference via hyper-network transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"M\u00fcller"},{"key":"ref85","article-title":"TabPFN: A transformer that solves small tabular classification problems in a second","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hollmann"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3442"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08328-6"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1435"},{"key":"ref89","article-title":"Scalable in-context learning on tabular data via retrieval-augmented large language models","author":"Wen","year":"2025"},{"key":"ref90","article-title":"TabM: Advancing tabular deep learning with parameter-efficient ensembling","author":"Gorishniy","year":"2024"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2457911"},{"key":"ref92","volume-title":"Introduction to Statistics","author":"Lane","year":"2003"},{"key":"ref93","article-title":"Limix: Unleashing structured-data modeling capability for generalist intelligence","author":"Zhang","year":"2025"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.stamet.2005.08.005"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04013-2"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010718"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330679"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1002\/9781118646106"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467066"},{"key":"ref101","article-title":"Annotatedtables: A large tabular dataset with language model annotations","author":"Hu","year":"2024"},{"key":"ref102","article-title":"Tabular benchmarks for joint architecture and hyperparameter optimization","author":"Klein","year":"2019"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.36.133357"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"issue":"261","key":"ref105","first-page":"1","article-title":"Auto-sklearn 2.0: Hands-free automl via meta-learning","volume":"23","author":"Feurer","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e26297"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.2967\/jnmt.119.227819"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.970246"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3134"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"ref111","article-title":"Tabm: Advancing tabular deep learning with parameter-efficient ensembling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gorishniy"},{"key":"ref112","article-title":"Unreflected use of tabular data repositories can undermine research quality","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Tschalzev"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-024-00681-z"},{"key":"ref114","article-title":"TabArena: A living benchmark for machine learning on tabular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Erickson"},{"key":"ref115","article-title":"Unitabe: A universal pretraining protocol for tabular foundation model in data science","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref116","article-title":"Tablib: A dataset of 627M tables with context","author":"Eggert","year":"2023"},{"key":"ref117","article-title":"DeepTables: A deep learning python package for tabular data","author":"Yang","year":"2022"},{"key":"ref118","article-title":"Autogluon-tabular: Robust and accurate autoML for structured data","author":"Erickson","year":"2020"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.21105\/joss.05027"},{"key":"ref120","first-page":"226:1","article-title":"TALENT: A tabular analytics and learning toolbox","volume":"26","author":"Liu","year":"2025","journal-title":"J. Mach. Learn. Res."},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref122","first-page":"630","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Morgan"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1214\/09-ss054"},{"key":"ref124","first-page":"4392","article-title":"Trompt: Towards a better deep neural network for tabular data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref125","article-title":"GRANDE: Gradient-based decision tree ensembles for tabular data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Marton"},{"key":"ref126","first-page":"21844","article-title":"Protogate: Prototype-based neural networks with global-to-local feature selection for tabular biomedical data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref127","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref128","article-title":"Constructing confidence intervals for \u2019the\u2019 generalization error\u2013A comprehensive benchmark study","author":"Schulz-K\u00fcmpel","year":"2024"},{"key":"ref129","article-title":"Reshuffling resampling splits can improve generalization of hyperparameter optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nagler"},{"key":"ref130","first-page":"21988","article-title":"Tabular insights, visual impacts: Transferring expertise from tables to images","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref131","first-page":"3555","article-title":"Multi-layered gradient boosting decision trees","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02291"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414142"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10304-3"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00568-3"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429383"},{"key":"ref137","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28148"},{"key":"ref139","first-page":"685","article-title":"Frequency bias in neural networks for input of non-uniform density","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Basri"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3038799"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref143","first-page":"6639","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Prokhorenkova"},{"key":"ref144","first-page":"3146","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref146","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref147","article-title":"A data-centric perspective on evaluating machine learning models for tabular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Tschalzev"},{"key":"ref148","article-title":"TabReD: A benchmark of tabular machine learning in-the-wild","author":"Rubachev","year":"2024"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1214\/09-aoas285"},{"key":"ref150","first-page":"2690","article-title":"NGBoost: Natural gradient boosting for probabilistic prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi5639"},{"key":"ref152","article-title":"xRFM: Accurate, scalable, and interpretable feature learning models for tabular data","author":"Beaglehole","year":"2025"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29033"},{"key":"ref154","first-page":"28742","article-title":"Self-attention between datapoints: Going beyond individual input-output pairs in deep learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kossen"},{"key":"ref155","article-title":"Hopular: Modern hopfield networks for tabular data","author":"Sch\u00e4fl","year":"2022"},{"key":"ref156","article-title":"Attentive neural processes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref157","first-page":"1386","article-title":"Regularization learning networks: Deep learning for tabular datasets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shavitt"},{"key":"ref158","first-page":"10530","article-title":"Towards domain-agnostic contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref159","article-title":"Self-supervision enhanced feature selection with correlated gates","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref160","article-title":"Transfer learning with deep tabular models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Levin"},{"key":"ref161","article-title":"MET: Masked encoding for tabular data","author":"Majmundar","year":"2022"},{"key":"ref162","article-title":"STab: Self-supervised learning for tabular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Hajiramezanali"},{"key":"ref163","article-title":"ReConTab: Regularized contrastive representation learning for tabular data","author":"Chen","year":"2023"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615470"},{"key":"ref165","article-title":"Self-supervised representation learning from random data projectors","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sui"},{"key":"ref166","first-page":"6053","article-title":"Meta-learning from tasks with heterogeneous attribute spaces","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Iwata"},{"key":"ref167","article-title":"Distribution embedding networks for generalization from a diverse set of classification tasks","author":"Liu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref168","first-page":"43181","article-title":"Xtab: Cross-table pretraining for tabular transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref169","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023"},{"key":"ref170","article-title":"PTab: Using the pre-trained language model for modeling tabular data","author":"Liu","year":"2022"},{"key":"ref171","first-page":"23843","article-title":"CARTE: Pretraining and transfer for tabular learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref172","article-title":"Binding language models in symbolic languages","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheng"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1938"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.917"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0855"},{"key":"ref176","article-title":"UniPredict: Large language models are universal tabular predictors","author":"Wang","year":"2023"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-47765-6"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18197-y"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1101\/2020.05.02.074203"},{"key":"ref180","article-title":"LM-IGTD: A 2D image generator for low-dimensional and mixed-type tabular data to leverage the potential of convolutional neural networks","author":"G\u00f3mez-Mart\u0131\u0144ez","year":"2024"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00360"},{"key":"ref182","article-title":"Tab2Visual: Overcoming limited data in tabular data classification using deep learning with visual representations","author":"Mamdouh","year":"2025"},{"key":"ref183","article-title":"iLTM: Integrated large tabular model","author":"Bonet","year":"2025"},{"key":"ref184","article-title":"TabPFN-2.5: Advancing the state of the art in tabular foundation models","author":"Grinsztajn","year":"2025"},{"key":"ref185","article-title":"Mitra: Mixed synthetic priors for enhancing tabular foundation models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref186","first-page":"83430","article-title":"Tunetables: Context optimization for scalable prior-data fitted networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Feuer"},{"key":"ref187","article-title":"Scaling tabPFN: Sketching and feature selection for tabular prior-data fitted networks","author":"Feuer","year":"2023"},{"key":"ref188","article-title":"Fine-tuned in-context learning transformers are excellent tabular data classifiers","author":"Breejen"},{"key":"ref189","article-title":"A closer look at tabPFN V2: Strength, limitation, and extension","author":"Ye","year":"2025"},{"key":"ref190","article-title":"EquitabPFN: A target-permutation equivariant prior fitted network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Arbel"},{"key":"ref191","article-title":"On finetuning tabular foundation models","author":"Rubachev","year":"2024"},{"key":"ref192","first-page":"6062","article-title":"Meditab: Scaling medical tabular data predictors via data consolidation, enrichment, and refinement","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Wang"},{"key":"ref193","article-title":"TabSTAR: A foundation tabular model with semantically target-aware representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Arazi"},{"key":"ref194","article-title":"Contexttab: A semantics-aware tabular in-context learner","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Spinaci"},{"key":"ref195","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref196","article-title":"Neighbourhood components analysis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Goldberger"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00305-w"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2004.11"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177013609"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.32614\/cran.package.rstg"},{"key":"ref202","first-page":"25123","article-title":"Locally sparse neural networks for tabular biomedical data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref203","first-page":"4699","article-title":"Neural additive models: Interpretable machine learning with neural nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Agarwal"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06674-0"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref206","first-page":"5630","article-title":"Rectify heterogeneous models with semantic mapping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ye"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179368"},{"key":"ref208","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu"},{"key":"ref209","first-page":"177","article-title":"YAGO3: A knowledge base from multilingual Wikipedias","volume-title":"Proc. Conf. Innov. Data Syst. Res.","author":"Mahdisoltani"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"ref211","article-title":"Make still further progress: Chain of thoughts for tabular data leaderboard","author":"Liu","year":"2025"},{"key":"ref212","article-title":"Visionts: Visual masked autoencoders are free-lunch zero-shot time series forecasters","author":"Chen","year":"2024"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2139"},{"key":"ref214","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha"},{"key":"ref215","article-title":"Revisiting meta-learning as supervised learning","author":"Chao","year":"2020"},{"key":"ref216","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters","year":"2017"},{"key":"ref217","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0745-0","volume-title":"Bayesian Learning for Neural Networks","author":"Neal","year":"1996"},{"key":"ref218","article-title":"Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces","author":"Iwata","year":"2023"},{"key":"ref219","article-title":"TabPFGen - tabular data generation with tabPFN","author":"Ma","year":"2024"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06166-x"},{"key":"ref221","article-title":"TabMDA: Tabular manifold data augmentation for any classifier using transformers with in-context subsetting","author":"Margeloiu","year":"2024"},{"key":"ref222","article-title":"The tabular foundation model tabPFN outperforms specialized time series forecasting models based on simple features","author":"Hoo","year":"2025"},{"key":"ref223","article-title":"Zero-shot meta-learning for tabular prediction tasks with adversarially pre-trained transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref224","article-title":"In-context data distillation with tabPFN","author":"Ma","year":"2024"},{"key":"ref225","article-title":"Mixture of in-context prompters for tabular PFNs","author":"Xu","year":"2024"},{"key":"ref226","article-title":"Towards localization via data embedding for tabPFN","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Koshil"},{"key":"ref227","article-title":"Tabflex: Scaling tabular learning to millions with linear attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Zeng"},{"key":"ref228","article-title":"Exploration of autoregressive models for in-context learning on tabular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Baur"},{"key":"ref229","article-title":"Scaling generative tabular learning for large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Sun"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref231","article-title":"Transformers boost the performance of decision trees on tabular data across sample sizes","author":"Jayawardhana","year":"2025"},{"key":"ref232","article-title":"Prior-fitted networks scale to larger datasets when treated as weak learners","author":"Wang","year":"2025"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"ref235","first-page":"2271","article-title":"Transductive and inductive outlier detection with robust autoencoders","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Lindenbaum"},{"key":"ref236","first-page":"3121","article-title":"Anomaly detection with variance stabilized density estimation","volume-title":"UAI","author":"Rozner"},{"key":"ref237","article-title":"Anomaly detection for tabular data with internal contrastive learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shenkar"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2329"},{"key":"ref239","article-title":"Anomaly detection of tabular data using LLMs","author":"Li","year":"2024"},{"key":"ref240","first-page":"18940","article-title":"CoDi: Co-evolving contrastive diffusion models for mixed-type tabular synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref241","article-title":"Causality for tabular data synthesis: A high-order structure causal benchmark framework","author":"Tu","year":"2024"},{"key":"ref242","article-title":"Generating new concepts with hybrid neuro-symbolic models","author":"Feinman","year":"2020"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.32614\/RJ-2017-016"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1418"},{"key":"ref245","first-page":"53385","article-title":"Benchmarking distribution shift in tabular data with tableshift","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gardner"},{"key":"ref246","article-title":"Adaptable: Test-time adaptation for tabular data via shift-aware uncertainty calibrator and label distribution handler","author":"Kim","year":"2024"},{"key":"ref247","article-title":"Distributionally robust neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sagawa"},{"key":"ref248","first-page":"6366","article-title":"Understanding the limits of deep tabular methods with temporal shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cai","year":"2025"},{"key":"ref249","article-title":"Feature-aware modulation for learning from temporal tabular data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cai"},{"key":"ref250","article-title":"TabGNN: Multiplex graph neural network for tabular data prediction","author":"Guo","year":"2021"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00261"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_27"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.131"},{"key":"ref254","first-page":"1918","article-title":"Tablebank: Table benchmark for image-based table detection and recognition","volume-title":"Proc. Lang. Resour. Eval. Conf.","author":"Li"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.192"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1145\/3657281"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7596-7_14"},{"key":"ref258","first-page":"27831","article-title":"Compositional condition question answering in tabular understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref259","article-title":"Multimodal tabular reasoning with privileged structured information","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01481"},{"key":"ref262","article-title":"Tables as images? Exploring the strengths and limitations of LLMs on multimodal representations of tabular data","author":"Deng","year":"2024"},{"key":"ref263","article-title":"Large language models (LLMs) on tabular data: Prediction, generation, and understanding\u2013A survey","author":"Fang","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11369258.pdf?arnumber=11369258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:46:32Z","timestamp":1778528792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11369258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":263,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3657217","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}