Flexible Sharpness-Aware Personalized Federated Learning

Personalized federated learning (PFL) is a new paradigm to address the statistical heterogeneity problem in federated learning. Most existing PFL methods focus on leveraging global and local information such as model interpolation or parameter decoupling. However, these methods often overlook the generalization potential during local client learning. From a local optimization perspective, we propose a simple and general PFL method, Federated learning with Flexible Sharpness-Aware Minimization (FedFSA). Specifically, we emphasize the importance of applying a larger perturbation to critical layers of the local model when using the Sharpness-Aware Minimization (SAM) optimizer. Then, we design a metric, perturbation sensitivity, to estimate the layer-wise sharpness of each local model. Based on this metric, FedFSA can flexibly select the layers with the highest sharpness to employ larger perturbation. Extensive experiments are conducted on four datasets with two types of statistical heterogeneity for image classification. The results show that FedFSA outperforms seven state-of-the-art baselines by up to 8.26% in test accuracy. Besides, FedFSA can be applied to different model architectures and easily integrated into other federated learning methods, achieving a 4.45% improvement.

Authors

• Xinda Xing Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
• Qiugang Zhan Complex Laboratory of New Finance and Economics, Southwest University of Finance and Economics, Chengdu, China Engineering Research Center of Intelligent Finance, Ministry of Education, Chengdu, China Kash Institute of Electronics and Information Industry, China
• Xiurui Xie University of Electronic Science and Technology of China
• Yuning Yang Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
• Qiang Wang
• Guisong Liu School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu, China Engineering Research Center of Intelligent Finance, Ministry of Education, Chengdu, China Kash Institute of Electronics and Information Industry, Kashgar, China

Keywords

No keywords are indexed for this paper.