RelDiff synthesizes relational databases by generating their foreign-key graph with a stochastic block model and denoising all attributes jointly with a graph-conditioned diffusion model.
Generating synthetic data in finance: opportunities, challenges and pitfalls // Proceedings of the First ACM International Conference on AI in Finance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models
RelDiff synthesizes relational databases by generating their foreign-key graph with a stochastic block model and denoising all attributes jointly with a graph-conditioned diffusion model.