Skip to content

tabnet

0.9.1Package record

Fit 'TabNet' Models for Classification and Regression

0packages dependsuggested by 2
32.4Kdownloads / year
0.0%test coverage
13/13flavors OK

Overview

About

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.

Changes in 0.9.1
  • {vip} is now distributed from r-universe.

From NEWS.md in the release

Install

Health

CRAN checks
13OK
Slowest check: 5.9 min · r-oldrel-macos-x86_64
Status changes
  • OK13 OK2026-08-04
  • NOTE12 OK, 1 NOTE2026-08-01
  • OK13 OK2026-06-09
  • ERROR12 OK, 1 ERROR2026-06-08
  • OK13 OK2026-05-10
Show 2 earlier changesHide 2 earlier changes
  • WARNING12 OK, 1 WARNING2026-05-09
  • OK14 OK2026-03-10
Advisories

none known

Documentation

In release 0.9.1
READMEYes · 628 wordsVignettesYes · 6 · dynamicNEWSYes · 100% structured · mentions 0.9.1Citation fileNoWebsiteYes · pkgdown
Help pages
26 (3 internal)
Examples that run
65%11 run in a plain check (10 of them under a condition) · 6 never run
Exported functions with examples
63%
Documented parameters
100%
Return-value docs
72%
Help pages citing references
0%

Downloads

32.4K
CRAN downloads in the past year
Rank #2,452 · ~89/day · ~2.7K/mo
Daily download trend is not available in this view yet.
2.2K30 days
6.5K90 days
32.4K1 year
Compare downloads with other packages →
Also on123 r2u6 autocran

Repository

119Stars
16Forks
17Open issues
0Open PRs
11Releases
510Commits
11Commit identities
tabnet
510 commits · Last activity 2026-07-23 · 0% stars, 30d · Default branch at 0.9.1.9000, ahead of CRAN 0.9.1 (checked 2026-10-18)
Responsiveness
How these are sampled
PRs merged (all time)
89%
Median days to close, 50 most recently updated closed issues
24
Median days to close, 50 most recently updated closed PRs
2

Stars over time

2025-09-06 · 1132026-09-11 · 119
PracticesBeta

8 development-tooling and community-health practices detected across 4 families in the upstream repository

Checks run against github.com/mlverse/tabnet on 2026-10-18.

Continuous integration (2)
GitHub ActionsR CMD check workflow

The R CMD check workflow runs on Linux and Windows, and on R-devel

Docs source (4)
README.Rmdpkgdown

GitHub Pages site last deployed 2026-07-23 · The repository has a site deploy workflow

Coverage (1)
Coverage reporting
CRAN release process (1)
cran-comments.md
How this is detected·Detection ruleset v3 (2026-09-26)

Dependencies

Declared dependencies
37 external dependencies (excludes base and recommended)

Installing tabnet adds 108 packages (50 with compiled code, 77 MB of source tarballs). Heaviest: stringi 11 MB, ggplot2 6.0 MB, data.table 5.7 MB.

Depends (1)
R >= 3.6
LinkingTo (0)
none
Enhances (0)
none
Reverse dependencies
0direct
0indirect
Suggested by 2
Suggests, most downloaded first

People & History

People (6)
Maintainer since 0.4.0 (2023), Contributor · added in 0.2.0
Contributor · added in 0.4.0
Contributor · added in 0.4.0
Contributor · added in 0.5.0
Copyright holder

Previously maintained by Daniel Falbel (0.1.0 to 0.3.0).

Releases (10)

Pick two releases to compare their code metrics.

  • 0.9.1Latest
    record
    2026-07-22 · current release · diff ↗
  • 0.9.0
    record
    2026-06-12 · diff ↗ ·
    added 5 exports
    augment, build_ancestor_matrix_from_outcomes, nn_mc_loss, nnf_mc_loss, nnf_multilabel_one_hot
  • R
    R 4.6.0 released · 2026-04-24
  • 0.8.0
    record
    2026-01-31 · diff ↗ ·
    added 5 exports
    entmax, entmax15, nn_aum_loss, sparsemax, sparsemax15
  • unarchivedReturned to CRAN
    2025-04-17
  • 0.7.0
    record
    2025-04-17 · diff ↗ ·
    removed 2 exports
    nn_prune_head.tabnet_fit, nn_prune_head.tabnet_pretrain
    added 13 exports
    cat_emb_dim, checkpoint_epochs, drop_last, encoder_activation, lr_scheduler, mlp_activation, mlp_hidden_multiplier, num_independent_decoder, num_shared_decoder, optimizer, penalty, verbose, virtual_batch_size
  • R
    R 4.5.0 released · 2025-04-11
  • archivedRemoved from CRAN
    2025-04-01
    issues were not corrected in time
  • 0.6.0
    record
    2024-06-15 · diff ↗
  • R
    R 4.4.0 released · 2024-04-24
  • 0.5.0
    record
    2023-12-05 · diff ↗ ·
    added 2 exports
    check_compliant_node, node_to_df
  • 0.4.0
    record
    2023-05-11 · diff ↗ ·
    added 3 exports
    nn_prune_head.tabnet_fit, nn_prune_head.tabnet_pretrain, tabnet_nn
  • R
    R 4.3.0 released · 2023-04-21
  • R
    R 4.2.0 released · 2022-04-22
  • 0.3.0
    record
    2021-10-11 · diff ↗
  • 0.2.0
    record
    2021-06-23 · diff ↗ ·
    added 3 exports
    mask_type, momentum, tabnet_pretrain
Show 3 earlier eventsHide 3 earlier events
  • R
    R 4.1.0 released · 2021-05-18
  • 0.1.0
    record
    2021-01-14
  • R
    R 4.0.0 released · 2020-04-24

Package metadata

First published
2021-01-14
Total releases
10 / 5 yrs
License
MIT + file LICENSE OSI
Additional repositories
bgreenwell.r-universe.dev
Minimum R
≥ 3.6
Download size
6.2 MB

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("tabnet")
Regouby, C., Falbel, D., Fridgeirsson, E., Haarmeyer, P., RStudio, , & Verweij, S. (2026). tabnet: Fit 'TabNet' Models for Classification and Regression (Version 0.9.1) [Computer software]. https://doi.org/10.32614/CRAN.package.tabnet

This package has no citation file, so citation() returns this entry built from DESCRIPTION.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

APA

Balamuta, J. J. (2026). R Observatory: Metrics for tabnet version 0.9.1 [Data set]. HJJB, LLC. Data release v2026-10-20. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-20, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →

Privacy choices

These apply to this browser and are stored on this device only. Nothing about your choice is sent to us.

Read the privacy policy