RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models
This addresses the challenge of generating realistic synthetic data for relational databases, which is important for data privacy and augmentation, though it is an incremental improvement over existing generative methods.
The paper tackled the problem of generating synthetic relational databases by introducing RelDiff, a diffusion model that explicitly models foreign key graph structure, and it outperformed prior methods on 11 benchmark datasets.
Real-world databases are predominantly relational, comprising multiple interlinked tables that contain complex structural and statistical dependencies. Learning generative models on relational data has shown great promise in generating synthetic data and imputing missing values. However, existing methods often struggle to capture this complexity, typically reducing relational data to conditionally generated flat tables and imposing limiting structural assumptions. To address these limitations, we introduce RelDiff, a novel diffusion generative model that synthesizes complete relational databases by explicitly modeling their foreign key graph structure. RelDiff combines a joint graph-conditioned diffusion process across all tables for attribute synthesis, and a $2K+$SBM graph generator based on the Stochastic Block Model for structure generation. The decomposition of graph structure and relational attributes ensures both high fidelity and referential integrity, both of which are crucial aspects of synthetic relational database generation. Experiments on 11 benchmark datasets demonstrate that RelDiff consistently outperforms prior methods in producing realistic and coherent synthetic relational databases. Code is available at https://github.com/ValterH/RelDiff.