pith. sign in

arxiv: 2111.05454 · v2 · pith:EDS2TQEUnew · submitted 2021-11-09 · 💻 cs.LG · cs.CR· stat.ML

DP-REC: Private & Communication-Efficient Federated Learning

classification 💻 cs.LG cs.CRstat.ML
keywords privacycommunicationdp-recfederatedguaranteeslearningprivatealgorithm
0
0 comments X
read the original abstract

Privacy and communication efficiency are important challenges in federated training of neural networks, and combining them is still an open problem. In this work, we develop a method that unifies highly compressed communication and differential privacy (DP). We introduce a compression technique based on Relative Entropy Coding (REC) to the federated setting. With a minor modification to REC, we obtain a provably differentially private learning algorithm, DP-REC, and show how to compute its privacy guarantees. Our experiments demonstrate that DP-REC drastically reduces communication costs while providing privacy guarantees comparable to the state-of-the-art.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.