Metraipolis › archive › dc_cf4b3f48d47e

Generating Benchmark Health Data Using a Tabular Diffusion Transformer — arXiv:2608.14496

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14496
License (as archived)
CC0-1.0
Archived
2026-10-19T02:21:36.284Z
SHA-256 of the archived text
484dd78e46a5556b2ee831bef9cf42952798955744d90c5e36bd8dd9714fa573
Stable URL of this page
https://metraipolis.com/documento/dc_cf4b3f48d47e

How to cite

Generating Benchmark Health Data Using a Tabular Diffusion Transformer — arXiv:2608.14496 — arXiv (en), https://arxiv.org/abs/2608.14496 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf4b3f48d47e (Metraipolis archive dc_cf4b3f48d47e, sha256 484dd78e46a5556b2ee831bef9cf42952798955744d90c5e36bd8dd9714fa573)
BibTeX
@misc{dccf4b3f48d47e,
  title = {Generating Benchmark Health Data Using a Tabular Diffusion Transformer — arXiv:2608.14496},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14496},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf4b3f48d47e; sha256 484dd78e46a5556b2ee831bef9cf42952798955744d90c5e36bd8dd9714fa573},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14496. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cross-Tabular Data Generation (CTDG) seeks to learn a generative model from multiple heterogeneous tables and produce new synthetic tabular datasets. However, existing synthetic tabular data generation methods are largely restricted to single-input-table scenarios and struggle to effectively handle multiple heterogeneous tables with diverse feature sets. To address this limitation, we propose a two-stage framework for cross-tabular data generation. In the first stage, each heterogeneous raw table is transformed into a standardized statistical table with the same set of columns across all tables. Each statistical table captures the marginal distributions of the original columns and the pairwise correlations among them. In the second stage, a diffusion transformer model is trained to capture structural patterns across these homogeneous statistical tables and to generate synthetic statistical tables. Synthetic raw tables are subsequently reconstructed from the generated statistical tables via multivariate Gaussian sampling followed by an inverse probability integral transform. This two-stage CTDG framework enables the learning of a unified generative model from multiple heterogeneous tables and supports the generation of an unlimited number of realistic synthetic heterogeneous tables. Experimental results demonstrate high fidelity in the learned statistical representations and a favorable fidelity-diversity trade-off in the generated synthetic data, validating the effectiveness of the proposed approach.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14496 — 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 2026-10-19T02:02:02.954Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).