FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
This addresses the challenge of data heterogeneity in federated learning, which is critical for real-world applications, though it appears incremental as it builds on existing methods like FedSAM.
The paper tackles the problem of poor generalization in federated learning under highly heterogeneous data, proposing FedSWA and FedMoSWA algorithms that achieve superior performance compared to FedSAM and FedAvg on datasets like CIFAR10/100 and Tiny ImageNet.
For federated learning (FL) algorithms such as FedSAM, their generalization capability is crucial for real-word applications. In this paper, we revisit the generalization problem in FL and investigate the impact of data heterogeneity on FL generalization. We find that FedSAM usually performs worse than FedAvg in the case of highly heterogeneous data, and thus propose a novel and effective federated learning algorithm with Stochastic Weight Averaging (called \texttt{FedSWA}), which aims to find flatter minima in the setting of highly heterogeneous data. Moreover, we introduce a new momentum-based stochastic controlled weight averaging FL algorithm (\texttt{FedMoSWA}), which is designed to better align local and global models. Theoretically, we provide both convergence analysis and generalization bounds for \texttt{FedSWA} and \texttt{FedMoSWA}. We also prove that the optimization and generalization errors of \texttt{FedMoSWA} are smaller than those of their counterparts, including FedSAM and its variants. Empirically, experimental results on CIFAR10/100 and Tiny ImageNet demonstrate the superiority of the proposed algorithms compared to their counterparts. Open source code at: https://github.com/junkangLiu0/FedSWA.