Differentially Private Synthetic Data Generation for Relational Databases
Not on the map. Why?
Abstract (arXiv)
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. This algorithm eliminates the need to flatten a relational database into a master table (saving space), operates efficiently (saving time), and scales effectively to high-dimensional data. We provide both DP and theoretical utility guarantees for our algorithm. Through numerical experiments on real-world datasets, we demonstrate the effectiveness of our method in preserving fidelity to the original data.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 79 references that are in the map. First posted on arXiv 29 May 2024.
Builds on
37 of 79 references.
References · 37
- 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 346
- 2018Differentially Private Generative Adversarial Networkcited by 235
- 2021Winning the NIST Contest: A scalable and general approach to differentially private synthetic datacited by 102
- 2022AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Datacited by 90
- 2021Benchmarking Differentially Private Synthetic Data Generation Algorithmscited by 81
- 2019Graphical-model based estimation and inference for differential privacycited by 74
- 2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 59
- 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 56
- 2021Differentially Private Query Release Through Adaptive Projectioncited by 52
- 2020Supervised Learning on Relational Databases with Graph Neural Networkscited by 48
- 2022Composition of Differential Privacy & Privacy Amplification by Subsamplingcited by 45
- 2020New Oracle-Efficient Algorithms for Private Synthetic Data Releasecited by 43
25 more
- 2021Leveraging Public Data for Practical Private Query Releasecited by 39
- 2020Differentially Private Synthetic Data: Applied Evaluations and Enhancementscited by 36
- 2022Private Synthetic Data for Multitask Learning and Marginal Queriescited by 35
- 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Modelscited by 28
- 2014Dual Query: Practical Private Query Release for High Dimensional Datacited by 26
- 2020Kamino: Constraint-Aware Differentially Private Data Synthesiscited by 25
- 2021ARM-Net: Adaptive Relation Modeling Network for Structured Datacited by 24
- 2020Private Post-GAN Boostingcited by 20
- 2017Towards Practical Differential Privacy for SQL Queriescited by 19
- 2023Generating Private Synthetic Data with Genetic Algorithmscited by 18
- 2023Private GANs, Revisitedcited by 17
- 2019GPU Acceleration of ADMM for Large-Scale Quadratic Programmingcited by 16
- 2019Differentially Private Synthetic Mixed-Type Data Generation For Unsupervised Learningcited by 11
- 2023Algorithmically Effective Differentially Private Synthetic Datacited by 11
- 2023PrivLava: Synthesizing Relational Data with Foreign Keys under Differential Privacycited by 11
- 2021Privacy of synthetic data: a statistical frameworkcited by 10
- 2023Post-processing Private Synthetic Data for Improving Utility on Selected Measurescited by 9
- 2022Generating Realistic Synthetic Relational Data through Graph Variational Autoencoderscited by 8
- 2024Privacy-preserving data release leveraging optimal transport and particle gradient descentcited by 8
- 2023Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collectionscited by 7
- 2023Optimal Bounds on Private Graph Approximationcited by 6
- 2019Publishing Community-Preserving Attributed Social Graphs with a Differential Privacy Guaranteecited by 4
- 2023Differentially Private Data Generation with Missing Datacited by 4
- 2019Learning Models over Relational Data: A Brief Tutorialcited by 3
- 2024A Comparison of SynDiffix Multi-table versus Single-table Synthetic Datacited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.