






















Abstract:Building generative models for relational databases (RDBs) is important for many applications, such as privacy-preserving data release and augmenting real datasets. However, most prior works either focus on single-table generation or adapt single-table models to the multi-table setting by relying on autoregressive factorizations and sequential generation. These approaches limit parallelism, restrict flexibility in downstream applications, and compound errors due to commonly made conditional independence assumptions. In this paper, we propose a fundamentally different approach: jointly modeling all tables in an RDB without imposing any table order. By using a natural graph representation of RDBs, we propose the Graph-Conditional Relational Diffusion Model (GRDM), which leverages a graph neural network to jointly denoise row attributes and capture complex inter-table dependencies. Extensive experiments on six real-world RDBs demonstrate that our approach substantially outperforms autoregressive baselines in modeling multi-hop inter-table correlations and achieves state-of-the-art performance on single-table fidelity metrics. Our code is available at $\texttt{this https URL}$.
| Comments: | Published at NeurIPS 2025 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2505.16527 [cs.LG] |
| (or arXiv:2505.16527v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2505.16527 arXiv-issued DOI via DataCite |
From: Mohamed Amine Ketata [view email]
[v1]
Thu, 22 May 2025 11:12:56 UTC (121 KB)
[v2]
Tue, 5 May 2026 09:25:22 UTC (146 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。