用图条件扩散模型联合生成多表数据库，突破顺序生成局限。
Joint Relational Database Generation via Graph-Conditional Diffusion Models
- 用图神经网络建模表间关系，联合生成所有表无顺序依赖。
- 在6个真实数据集上显著提升多跳表关联建模能力。
- 适合需要高保真多表结构的隐私数据生成场景。
构建关系型数据库的生成模型对隐私保护数据发布和真实数据增强等应用至关重要。然而，现有方法多聚焦单表生成，或通过自回归因子分解和序列生成扩展至多表，受限于生成顺序，难以并行，且因条件独立假设导致误差累积。本文提出一种新范式：不依赖表序，联合建模整个数据库。基于关系型数据库的自然图结构，提出图条件关系扩散模型（GRDM），利用图神经网络同时去噪行属性并捕捉复杂表间依赖。在六个真实数据集上的实验表明，该方法显著优于自回归基线，在多跳表关联建模上表现突出，并在单表保真度指标上达到当前最优。代码已开源。
原文摘要 · Abstract (English)
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 https://github.com/ketatam/rdb-diffusion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。