tabnet: Fit 'TabNet' Models for Classification and Regression

Implements the 'TabNet' model by Sercan O. Arik et al. (2019) <arXiv:1908.07442> and provides a consistent interface for fitting and creating predictions. It's also fully compatible with the 'tidymodels' ecosystem.

Version: 0.4.0
Imports: torch (≥ 0.4.0), hardhat (≥ 1.3.0), magrittr, glue, progress, rlang, methods, tibble, coro, vctrs
Suggests: testthat (≥ 3.0.0), modeldata, recipes, rsample, parsnip, dials, withr, knitr, rmarkdown, vip, tidyverse, ggplot2, dplyr, tidyr, purrr, stringr, tune, workflows, yardstick
Published: 2023-05-11
Author: Daniel Falbel [aut], RStudio [cph], Christophe Regouby [cre, ctb], Egill Fridgeirsson [ctb], Philipp Haarmeyer [ctb]
Maintainer: Christophe Regouby <christophe.regouby at>
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README NEWS
CRAN checks: tabnet results


Reference manual: tabnet.pdf
Vignettes: pretrain from dataset with missing-values
Interpretation tools
Fitting tabnet with tidymodels
Unsupervised training and fine-tuning


Package source: tabnet_0.4.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): tabnet_0.4.0.tgz, r-oldrel (arm64): tabnet_0.4.0.tgz, r-release (x86_64): tabnet_0.4.0.tgz, r-oldrel (x86_64): tabnet_0.4.0.tgz
Old sources: tabnet archive


Please use the canonical form to link to this page.