Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders

Ciro Antonio Mami, Andrea Coser, Eric Medvet, Alexander Theodorus Petrus Boudewijn, Michael Whitworth, Marco Volpe, Gabriele Sgroi, Borut Svara, Daniele Panfilo, Sebastiano Saccani

Keywords: Synthetic data, Variational autoencoder, Relational data, Graph neural network, Graph variational autoencoder

TL;DR: Through a combination of graph neural networks and variational autoencoders, realistic synthetic relational data can be generated that accurately preserves inter-tabular relations.

Abstract: Synthetic data generation has recently gained widespread attention as a more reliable alternative to traditional data anonymization. The involved methods are originally developed for image synthesis. Hence, their application to the typically tabular and relational datasets from healthcare, finance and other industries is non-trivial. While substantial research has been devoted to the generation of realistic tabular datasets, the study of synthetic relational databases is still in its infancy. In this paper, we combine the variational autoencoder framework with graph neural networks to generate realistic synthetic relational databases. We then apply the obtained method to two publicly available databases in computational experiments. The results indicate that real databases' structures are accurately preserved in the resulting synthetic datasets, even for large datasets with advanced data types.