Differentially Private Generative Models Through Optimal Transport

Tianshi Cao, Alex Bie, Karsten Kreis, Sanja Fidler

Keywords: Differential Privacy, Generative Learning, GAN, Optimal Transport

Abstract: Although machine learning models trained on massive data have led to breakthroughs in several areas, their deployment in privacy-sensitive domains remains limited due to restricted access to data. Generative models trained with privacy constraints on private data can sidestep this challenge and provide indirect access to the private data instead. We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. DP-Sinkhorn relies on minimizing the Sinkhorn divergence---a computationally efficient approximation to the exact optimal transport distance---between the model and the data in a differentially private manner and also uses a novel technique for conditional generation in the Sinkhorn framework. Unlike existing approaches for training differentially private generative models, which are mostly based on generative adversarial networks, we do not rely on adversarial objectives, which are notoriously difficult to optimize, especially in the presence of noise imposed by the privacy constraints. Hence, DP-Sinkhorn is easy to train and deploy. Experimentally, despite our method's simplicity we improve upon the state-of-the-art on multiple image modeling benchmarks. We also show differentially private synthesis of informative RGB images, which has not been demonstrated before by differentially private generative models without the use of auxiliary public data.

One-sentence Summary: Learning generative models that satisfy differential privacy guarantees using optimal transport.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=3hIqwAXEv9