Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees

TL;DR

This paper introduces Byzantine-robust federated learning protocols that achieve near-optimal statistical rates, improved dimension dependence, and can be combined with privacy guarantees, demonstrating empirical superiority over existing methods.

Contribution

The paper presents new federated learning protocols that are robust to Byzantine failures, improve statistical rate bounds, and integrate privacy features, surpassing prior approaches.

Findings

Protocols achieve nearly optimal statistical rates.

Empirical benchmarks show superiority over competing methods.

Protocols can be combined with privacy guarantees.

Abstract

We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the parameters for strongly convex losses. We benchmark against competing protocols and show the empirical superiority of the proposed protocols. Finally, we remark that our protocols with bucketing can be naturally combined with privacy-guaranteeing procedures to introduce security against a semi-honest server. The code for evaluation is provided in https://github.com/wanglun1996/secure-robust-federated-learning.