yandex-research/tab-ddpm

[ICML 2023] The official implementation of the paper "TabDDPM: Modelling Tabular Data with Diffusion Models"

51
/ 100
Established

Applies diffusion models to tabular data generation by treating mixed data types (continuous and categorical features) through a unified continuous representation during the diffusion process. The implementation uses PyTorch and provides modular training/sampling pipelines with evaluation against multiple baselines (CTGAN, CTAB-GAN) using tuned downstream models like CatBoost and MLPs to assess synthetic data quality.

533 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

533

Forks

132

Language

Python

License

MIT

Last pushed

Jul 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yandex-research/tab-ddpm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.