This academic article by researchers from the University of Waterloo focuses on the challenge of generating synthetic data with differential privacy (DP) guarantees when the input data has missing values. It proposes three adaptive strategies that significantly improve the utility of the synthetic data on four real-world datasets with different types and levels of missing data and privacy requirements. The study also explores the relationship between privacy impact for the complete ground truth data and incomplete data for these DP synthetic data generation algorithms. The findings contribute to a better understanding of the challenges and opportunities for using private synthetic data generation algorithms in the presence of missing data.
Publication date: 19 Oct 2023
Project Page: Not Provided
Paper: https://arxiv.org/pdf/2310.11548
