Byzantine-Robust Federated Learning with Learnable Aggregation Weights

TL;DR

This paper introduces a new federated learning method that uses learnable aggregation weights to improve robustness against malicious clients, especially in heterogeneous data environments, with proven convergence and superior experimental performance.

Contribution

It proposes a novel adaptive weighting scheme for aggregation in Byzantine-robust federated learning, jointly optimized with model parameters, with strong convergence guarantees and improved robustness.

Findings

Outperforms existing Byzantine-robust FL methods in heterogeneous settings

Achieves strong convergence guarantees under adversarial attacks

Demonstrates superior robustness in diverse datasets and attack scenarios

Abstract

Federated Learning (FL) enables clients to collaboratively train a global model without sharing their private data. However, the presence of malicious (Byzantine) clients poses significant challenges to the robustness of FL, particularly when data distributions across clients are heterogeneous. In this paper, we propose a novel Byzantine-robust FL optimization problem that incorporates adaptive weighting into the aggregation process. Unlike conventional approaches, our formulation treats aggregation weights as learnable parameters, jointly optimizing them alongside the global model parameters. To solve this optimization problem, we develop an alternating minimization algorithm with strong convergence guarantees under adversarial attack. We analyze the Byzantine resilience of the proposed objective. We evaluate the performance of our algorithm against state-of-the-art Byzantine-robust FL approaches across various datasets and attack scenarios. Experimental results demonstrate that our method consistently outperforms existing approaches, particularly in settings with highly heterogeneous data and a large proportion of malicious clients.