lucidrains/tab-transformer-pytorch

Health v2 · maintenance only

Adoption not part of the score

1091 stars · 131 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 TabTransformer architecture, an attention-based neural network for tabular data, also including the FT Transformer variant for comparison. It is distributed as a pip-installable library for researchers and practitioners applying deep learning to structured data.

Use cases

• train a transformer model on tabular data with categorical and continuous features
• compare attention-based models against gradient boosted decision trees on structured datasets
• implement TabTransformer from the paper in PyTorch
• use FT Transformer for embedding continuous numerical features
• predict outcomes like shipping cost from mixed tabular inputs

When to choose

• you want a ready-made PyTorch implementation of TabTransformer or FT Transformer
• your dataset has many categorical features and you want attention-based modeling
• you are benchmarking deep learning against GBDT on tabular data

When to avoid

• you need a battle-tested production AutoML solution rather than a research implementation
• your tabular data is small and gradient boosted trees would suffice
• you do not use PyTorch

Facets

library · maturity stable

machine-learning deep-learning machine-learning deep-learning artificial-intelligence python transformer tabular-data attention-mechanism pytorch ft-transformer

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lucidrains/tab-transformer-pytorch")