Metraipolis › archive › dc_c5dd2aee45c2
CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data — arXiv:2609.39124
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39124
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:45:50.867Z
- SHA-256 of the archived text
d546cd1c1d8dfabb6db43eb5674e7505c869ae84c3d50c825f6176c17a4a00ce- Stable URL of this page
https://metraipolis.com/documento/dc_c5dd2aee45c2
How to cite
CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data — arXiv:2609.39124 — arXiv (en), https://arxiv.org/abs/2609.39124 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5dd2aee45c2 (Metraipolis archive dc_c5dd2aee45c2, sha256 d546cd1c1d8dfabb6db43eb5674e7505c869ae84c3d50c825f6176c17a4a00ce)
BibTeX
@misc{dcc5dd2aee45c2,
title = {CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data — arXiv:2609.39124},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39124},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5dd2aee45c2; sha256 d546cd1c1d8dfabb6db43eb5674e7505c869ae84c3d50c825f6176c17a4a00ce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39124. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative models for tabular data are typically trained separately for each dataset, limiting knowledge transfer and requiring the storage of many specialized models. In this paper, we introduce CDMD, a tabular diffusion model trained jointly across heterogeneous datasets with different schemas and variable numbers of numerical and categorical features. Unlike existing cross-dataset tabular diffusion models that operate in continuous representation spaces, CDMD defines diffusion directly over the mixed-type feature space and is trained end-to-end. To accommodate heterogeneous categorical domains, we introduce a schema-restricted reverse-process parameterization for masked diffusion models, in which the output space dynamically adapts to each feature's vocabulary. We then compose numerical and categorical feature-level diffusion processes into a schema-dependent row-level process. A shared schema-aware Transformer denoiser captures dependencies between features and parameterizes the reverse process across varying schemas. On seven real-world datasets, a single jointly trained CDMD achieves the highest average generation quality among strong single-dataset and cross-dataset baselines, while using substantially fewer total parameters than the collection of separately trained models. Furthermore, pre-training on a corpus of 337 datasets improves generation on previously unseen datasets under both limited target data and limited adaptation epochs. These results demonstrate the potential of direct mixed-type diffusion for shared and transferable tabular data generation. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.39124 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T13:18:10.323Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).