dreamquark-ai/tabnet

Health v2 · maintenance only

Adoption not part of the score

2955 stars · 516 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity stable

machine-learning deep-learning machine-learning data-science python cross-platform tabular-data tabnet pytorch interpretable-ml attention gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dreamquark-ai/tabnet")