FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning
This addresses server-side aggregation vulnerabilities in federated learning for privacy-preserving decentralized training, offering a solution to improve resilience and fairness in non-identically distributed settings.
The paper tackles challenges in federated learning, such as statistical heterogeneity and adversarial attacks, by introducing FedAA, which uses adaptive aggregation to enhance robustness against malicious clients and ensure fairness, outperforming state-of-the-art methods in robustness while maintaining comparable fairness.
Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called \textbf{FedAA}, which optimizes client contributions via \textbf{A}daptive \textbf{A}ggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, \textbf{FedAA} outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Our code is available at https://github.com/Gp1g/FedAA.