# RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models

arXiv: https://arxiv.org/abs/2506.00710 · HTML: https://mlsanity.com/paper/2506.00710/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 34 of its 70 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 34)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [Why Tabular Foundation Models Should Be a Research Priority](https://mlsanity.com/paper/2405.01147/) (2024)
- [Graph Normalizing Flows](https://mlsanity.com/paper/1905.13177/) (2019)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers](https://mlsanity.com/paper/2302.02041/) (2023)
- [AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data](https://mlsanity.com/paper/2201.12677/) (2022)
- [TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation](https://mlsanity.com/paper/2410.20626/) (2024)
- [Hierarchical Block Structures and High-resolution Model Selection in Large Networks](https://mlsanity.com/paper/1310.4377/) (2013)
- [Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data](https://mlsanity.com/paper/2304.03722/) (2023)
- [ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models](https://mlsanity.com/paper/2405.17724/) (2024)
- [Bayesian stochastic blockmodeling](https://mlsanity.com/paper/1705.10225/) (2017)
- [Kamino: Constraint-Aware Differentially Private Data Synthesis](https://mlsanity.com/paper/2012.15713/) (2020)
- [Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark](https://mlsanity.com/paper/2310.16981/) (2023)
- [Nonparametric Bayesian inference of the microcanonical stochastic block model](https://mlsanity.com/paper/1610.02703/) (2016)
- [GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?](https://mlsanity.com/paper/2310.13833/) (2023)
- [A Simple and Scalable Representation for Graph Generation](https://mlsanity.com/paper/2312.02230/) (2023)
- [Row Conditional-TGAN for generating synthetic relational databases](https://mlsanity.com/paper/2211.07588/) (2022)
- [TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data](https://mlsanity.com/paper/2501.12012/) (2025)
- [PrivLava: Synthesizing Relational Data with Foreign Keys under Differential Privacy](https://mlsanity.com/paper/2304.04545/) (2023)
- [Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders](https://mlsanity.com/paper/2211.16889/) (2022)

## Built on by (most cited first, 4 of 4)

- [RelBench v2: A Large-Scale Benchmark and Repository for Relational Data](https://mlsanity.com/paper/2602.12606/) (2026)
- [Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark](https://mlsanity.com/paper/2606.08736/) (2026)
- [Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss](https://mlsanity.com/paper/2606.31904/) (2026)
- [When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model Behavior](https://mlsanity.com/paper/2610.03057/) (2026)

## Abstract (arXiv)

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.