{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:59:59Z","timestamp":1772521199854,"version":"3.50.1"},"reference-count":49,"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\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100017638","name":"Ministry of Health of the Russian Federation","doi-asserted-by":"publisher","award":["139-15-2025-008"],"award-info":[{"award-number":["139-15-2025-008"]}],"id":[{"id":"10.13039\/501100017638","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.2026.3663928","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:56:35Z","timestamp":1770843395000},"page":"30073-30086","source":"Crossref","is-referenced-by-count":0,"title":["Bridging KANs and Tabular Deep Learning: Feature Embeddings and Efficient Ensembling"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4703-9642","authenticated-orcid":false,"given":"Georgii","family":"Bulgakov","sequence":"first","affiliation":[{"name":"N. N. Blokhin National Medical Research Center of Oncology of the Ministry of Health of the Russian Federation (N. N. Blokhin NMRCO), Moscow, Russia"}]},{"given":"Danil","family":"Rudenko","sequence":"additional","affiliation":[{"name":"Moscow Independent Research Institute of Artificial Intelligence, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3516-1848","authenticated-orcid":false,"given":"Gleb","family":"Molodtsov","sequence":"additional","affiliation":[{"name":"Moscow Independent Research Institute of Artificial Intelligence, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3217-3614","authenticated-orcid":false,"given":"Aleksandr","family":"Beznosikov","sequence":"additional","affiliation":[{"name":"Moscow Independent Research Institute of Artificial Intelligence, Moscow, Russia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref2","first-page":"3149","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref3","first-page":"6639","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Prokhorenkova"},{"key":"ref4","article-title":"TabM: Advancing tabular deep learning with parameter-efficient ensembling","author":"Gorishniy","year":"2024","journal-title":"arXiv:2410.24210"},{"key":"ref5","article-title":"Diabetes","author":"Kahn","year":"1990"},{"key":"ref6","first-page":"24991","article-title":"On embeddings for numerical features in tabular deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gorishniy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3743128"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159727"},{"key":"ref9","article-title":"Are neural rankers still outperformed by gradient boosted decision trees","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Qin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"ref11","article-title":"KAN: Kolmogorov\u2013Arnold networks","author":"Liu","year":"2024","journal-title":"arXiv:2404.19756"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1090\/trans2\/017\/12"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-01742-1_2","article-title":"On functions of three variables","volume-title":"Proc. USSR Acad. Sci.","author":"Arnold"},{"key":"ref14","article-title":"Chebyshev polynomial-based Kolmogorov\u2013Arnold networks: An efficient architecture for nonlinear function approximation","author":"Sidharth","year":"2024","journal-title":"arXiv:2405.07200"},{"key":"ref15","article-title":"Kolmogorov\u2013Arnold networks are radial basis function networks","author":"Li","year":"2024","journal-title":"arXiv:2405.06721"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshp64532.2024.11100692"},{"key":"ref17","article-title":"Demonstrating the efficacy of Kolmogorov\u2013Arnold networks in vision tasks","author":"Cheon","year":"2024","journal-title":"arXiv:2406.14916"},{"key":"ref18","article-title":"Kolmogorov\u2013Arnold transformer","author":"Yang","year":"2024","journal-title":"arXiv:2409.10594"},{"key":"ref19","article-title":"GKAN: Graph Kolmogorov\u2013Arnold networks","author":"Kiamari","year":"2024","journal-title":"arXiv:2406.06470"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/AICT61888.2024.10740444"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s44379-025-00042-y"},{"key":"ref22","article-title":"TabKANet: Tabular data modeling with Kolmogorov\u2013Arnold network and transformer","author":"Gao","year":"2024","journal-title":"arXiv:2409.08806"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08328-6"},{"key":"ref24","first-page":"23928","article-title":"Well-tuned simple nets excel on tabular datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kadra"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0837"},{"key":"ref26","first-page":"6405","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lakshminarayanan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref28","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019","journal-title":"arXiv:1912.02757"},{"key":"ref29","first-page":"4697","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wilson"},{"key":"ref30","article-title":"BatchEnsemble: An alternative approach to efficient ensemble and lifelong learning","author":"Wen","year":"2020","journal-title":"arXiv:2002.06715"},{"key":"ref31","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref32","article-title":"Understanding optimization in deep learning with central flows","author":"Cohen","year":"2024","journal-title":"arXiv:2410.24206"},{"key":"ref33","article-title":"Muon is scalable for LLM training","author":"Liu","year":"2025","journal-title":"arXiv:2502.16982"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00933"},{"key":"ref35","article-title":"A note on task-aware loss via reweighing prediction loss by decision-regret","author":"Lawless","year":"2022","journal-title":"arXiv:2211.05116"},{"key":"ref36","article-title":"Clipping improves adam-norm and AdaGrad-norm when the noise is heavy-tailed","author":"Chezhegov","year":"2024","journal-title":"arXiv:2406.04443"},{"key":"ref37","volume-title":"Muon: An Optimizer for Hidden Layers in Neural Networks","author":"Keller","year":"2024"},{"key":"ref38","article-title":"The AdEMAMix optimizer: Better, faster, older","author":"Pagliardini","year":"2024","journal-title":"arXiv:2409.03137"},{"key":"ref39","article-title":"MARS: Unleashing the power of variance reduction for training large models","author":"Yuan","year":"2024","journal-title":"arXiv:2411.10438"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0037"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-7152(96)00140-X"},{"key":"ref42","first-page":"202","article-title":"Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid","author":"Kohavi","year":"1996","journal-title":"Kdd"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5308"},{"key":"ref44","first-page":"15","article-title":"Comment volume prediction using neural networks and decision trees","volume-title":"Proc. IEEE UKSim-AMSS 17th Int. Conf. Comput. Model. Simul.","author":"Singh"},{"key":"ref45","article-title":"Introducing LETOR 4.0 datasets","author":"Qin","year":"2013","journal-title":"arXiv:1306.2597"},{"key":"ref46","volume-title":"Efficient-Kan: An Efficient Pure-Pytorch Implementation of Kolmogorov\u2013Arnold Network (kan)","year":"2024"},{"key":"ref47","volume-title":"Chebykan: Kolmogorov\u2013Arnold Networks Using Chebyshev Polynomials Instead of B-Splines","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11393617.pdf?arnumber=11393617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:21:38Z","timestamp":1772518898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11393617\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3663928","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}