A Unified View of Differentially Private Deep Generative Modeling
This work addresses the problem of enabling privacy-compliant data sharing and analysis for researchers and practitioners handling sensitive data, but it is incremental as it primarily organizes and synthesizes existing methods rather than introducing new techniques.
The paper tackles the challenge of generating high-dimensional data under differential privacy constraints by proposing a unified framework that systematizes existing deep generative modeling approaches, aiming to guide future research in privacy-preserving learning.
The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles in compliance with privacy considerations is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released, enabling privacy-preserving downstream analysis and reproducible research in sensitive domains. In recent years, various approaches have been proposed for achieving privacy-preserving high-dimensional data generation by private training on top of deep neural networks. In this paper, we present a novel unified view that systematizes these approaches. Our view provides a joint design space for systematically deriving methods that cater to different use cases. We then discuss the strengths, limitations, and inherent correlations between different approaches, aiming to shed light on crucial aspects and inspire future research. We conclude by presenting potential paths forward for the field of DP data generation, with the aim of steering the community toward making the next important steps in advancing privacy-preserving learning.