D2P-Fed: Differentially Private Federated Learning With Efficient Communication

Understand

In this paper, we propose the discrete Gaussian based differentially private federated learning (D2P-Fed), a unified scheme to achieve both differential privacy (DP) and communication efficiency in federated learning (FL).

• In particular, compared with the only prior work taking care of both aspects, D2P-Fed provides stronger privacy guarantee, better composability and smaller communication cost.
• The key idea is to apply the discrete Gaussian noise to the private data transmission.
• We provide complete analysis of the privacy guarantee, communication cost and convergence rate of D2P-Fed.