Byzantine-Robust Federated Learning with Learnable Aggregation Weights
By: Javad Parsa , Amir Hossein Daghestani , André M. H. Teixeira and more
Potential Business Impact:
Keeps smart learning safe from bad guys.
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.
Similar Papers
Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
Machine Learning (CS)
Protects smart learning from bad data.
Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
Machine Learning (CS)
Keeps AI learning safe from bad data.
A Weighted Loss Approach to Robust Federated Learning under Data Heterogeneity
Machine Learning (CS)
Keeps AI learning safe from bad data.