Graph-Conditional Flow Matching for Relational Data Generation

TL;DR

This paper introduces a graph-conditional flow matching model for relational data generation that captures complex dependencies and foreign-key relationships, improving the fidelity of synthetic relational datasets.

Contribution

It presents a novel deep generative model leveraging flow matching and graph neural networks to generate relational data with complex structures and long-range dependencies.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Supports complex relational structures with multiple foreign-key relationships.

Generates high-fidelity synthetic relational data.

Abstract

Data synthesis is gaining momentum as a privacy-enhancing technology. While single-table tabular data generation has seen considerable progress, current methods for multi-table data often lack the flexibility and expressiveness needed to capture complex relational structures. In particular, they struggle with long-range dependencies and complex foreign-key relationships, such as tables with multiple parent tables or multiple types of links between the same pair of tables. We propose a generative model for relational data that generates the content of a relational dataset given the graph formed by the foreign-key relationships. We do this by learning a deep generative model of the content of the whole relational database by flow matching, where the neural network trained to denoise records leverages a graph neural network to obtain information from connected records. Our method is flexible, as it can support relational datasets with complex structures, and expressive, as the generation of each record can be influenced by any other record within the same connected component. We evaluate our method on several benchmark datasets and show that it achieves state-of-the-art performance in terms of synthetic data fidelity.