D2p-fed:Differentially Private Federated Learning with Efficient Communication

Lun Wang, Ruoxi Jia, Dawn Song

Keywords: Differential Privacy, Federated Learning, Communication Efficiency

Abstract: 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. We evaluated D2p-fed on INFIMNIST and CIFAR10. The results show that D2p-fed outperforms the-state-of-the-art by 4.7% to 13.0% in terms of model accuracy while saving one third of the communication cost. The code for evaluation is available in the supplementary material.

One-sentence Summary: We propose D2p-fed, a differentially private federated learning protocol with efficient communication.

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=le8yUy1IbV