tabnet: Fit 'TabNet' Models for Classification and Regression

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.

Version: 0.5.0
Depends: R (≥ 3.6)
Imports: torch (≥ 0.4.0), hardhat (≥ 1.3.0), magrittr, progress, rlang, methods, dplyr, tibble, tidyr, coro, vctrs, zeallot
Suggests: testthat (≥ 3.0.0), data.tree, Matrix, modeldata, recipes, rsample, parsnip, dials, withr, knitr, rmarkdown, vip, tidyverse, ggplot2, purrr, stringr, tune, workflows, yardstick
Published: 2023-12-05
DOI: 10.32614/CRAN.package.tabnet
Author: Daniel Falbel [aut], RStudio [cph], Christophe Regouby [cre, ctb], Egill Fridgeirsson [ctb], Philipp Haarmeyer [ctb], Sven Verweij ORCID iD [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: Hierarchical Classification
pretrain from dataset with missing-values
Interpretation tools
Self-supervised training and fine-tuning
Fitting tabnet with tidymodels


Package source: tabnet_0.5.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): tabnet_0.5.0.tgz, r-oldrel (arm64): tabnet_0.5.0.tgz, r-release (x86_64): tabnet_0.5.0.tgz, r-oldrel (x86_64): tabnet_0.5.0.tgz
Old sources: tabnet archive


Please use the canonical form to link to this page.