Fit 'TabNet' Models for Classification and Regression R package tabnet version 0.9.1 Implements the 'TabNet' model by Sercan O. Arik et al. (2019) <doi:10.48550/arXiv.1908.07442> with 'Coherent Hierarchical Multi-label Classification Networks' by Giunchiglia et al. <doi:10.48550/arXiv.2010.10151> and provides a consistent interface for fitting and creating predictions. It's also fully compatible with the 'tidymodels' ecosystem. Software Depends: R (>= 3.6) Imports: coro, data.tree, dials, dplyr, generics, ggplot2, hardhat (>= 1.3.0), magrittr, methods, parsnip, progress, purrr, rlang, stats, stringr, tibble, tidyr, torch (>= 0.4.0), tune, utils, vctrs, withr, zeallot Suggests: cli, knitr, modeldata, patchwork, quarto, recipes, rmarkdown, rsample, spelling, testthat (>= 3.0.0), tidymodels, tidyverse, vip, visdat, workflows, xgboost, yardstick Christophe Regouby <christophe.regouby@free.fr> Comprehensive R Archive Network (CRAN) Daniel Falbel [aut], RStudio [cph], Christophe Regouby [cre, ctb], Egill Fridgeirsson [ctb], Philipp Haarmeyer [ctb], Sven Verweij [ctb] (ORCID: <https://orcid.org/0000-0002-5573-3952>) MIT + file LICENSE (https://CRAN.R-project.org/package=tabnet/LICENSE) 2026-07-22 application/tgz https://CRAN.R-project.org/package=tabnet doi:10.32614/CRAN.package.tabnet en-US