Paper ID: 2405.18670

Adapting Differentially Private Synthetic Data to Relational Databases

Kaveh Alimohammadi, Hao Wang, Ojas Gulati, Akash Srivastava, Navid Azizan

Existing differentially private (DP) synthetic data generation mechanisms typically assume a single-source table. In practice, data is often distributed across multiple tables with relationships across tables. In this paper, we introduce the first-of-its-kind algorithm that can be combined with any existing DP mechanisms to generate synthetic relational databases. Our algorithm iteratively refines the relationship between individual synthetic tables to minimize their approximation errors in terms of low-order marginal distributions while maintaining referential integrity. Finally, we provide both DP and theoretical utility guarantees for our algorithm.

Submitted: May 29, 2024