# dreamquark-ai/tabnet

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

Repository: https://github.com/dreamquark-ai/tabnet
Canonical: https://ross.abutalabs.com/products/tabnet
Homepage: https://dreamquark-ai.github.io/tabnet/
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, deep-neural-networks, machine-learning-library, tabular-data, research-paper, pytorch-tabnet, tabnet
Last push: 2024-10-23T15:36:38+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2512, "days_push": 679, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2955, forks 516 (observed 2026-08-28T04:07:32.145673+00:00)

## What it is
A PyTorch implementation of the TabNet deep learning architecture for tabular data, providing attentive, interpretable models for classification, regression, and self-supervised pretraining. It is distributed as the pytorch-tabnet package on PyPI and conda-forge.

## Use cases
- train a deep learning model on tabular data
- classify tabular data with an interpretable neural network
- fit a TabNet regressor on structured data
- pretrain a tabular model with self-supervised learning
- apply feature attention to mixed categorical and numerical columns
- use grouped attention for TF-IDF or embedded features

## When to choose
- you want a deep learning model for tabular data with built-in interpretability via attention
- you want a scikit-learn-like fit/predict API on top of PyTorch
- you need self-supervised pretraining or on-the-fly data augmentation for tabular data

## When to avoid
- you need gradient-boosted tree performance on small tabular datasets with minimal tuning
- you work outside the PyTorch ecosystem
- you need a maintained library with frequent updates

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: tabular-data, tabnet, pytorch, interpretable-ml, attention, gpu

## Member repositories
- dreamquark-ai/tabnet (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.145673+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:32:27.507301+00:00, confidence not recorded.
  - readme: https://github.com/dreamquark-ai/tabnet (fetched 2026-08-28T04:07:32.145673+00:00, sha 012c1ac251de)
  - homepage: https://dreamquark-ai.github.io/tabnet/ (fetched 2026-08-29T09:47:37.822519+00:00, sha 93f19bd43908)
- Data as of 2026-08-30T08:39:29.467469+00:00.