• Overview
• Baselines
• QuickStart
• Citation
• Acknowledgements

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. The results show that FedFSA outperforms seven baselines by up to 8.26% in test accuracy.

FedAvg:Communication-Efficient Learning of Deep Networks from Decentralized Data

FedCR:Communication-Efficient Learning of Deep Networks from Decentralized Data

FedALA:FedALA: Adaptive Local Aggregation for Personalized Federated Learning

FedSAM/MoFedSAM:Generalized Federated Learning via Sharpness Aware Minimization

FedSpeed:FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy

FedSMOO:Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape

Refer to the ./FedFSA/run.sh script for basic usage. For detailed hyperparameter configurations, please refer to our paper and Appendix.

@inproceedings{xing2025fedfsa,
    title={Flexible Sharpness-Aware Personalized Federated Learning},
    author={Xing, Xinda and Zhan, Qiugang and Xie, Xiurui and Yang, Yuning and Wang, Qiang and Liu, Guisong},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    volume={39},
    number={20},
    pages={21707--21715},
    year={2025},
    address = {Philadelphia, Pennsylvania, USA}
}

This repo benefits from FedSpeed,FedSMOO and FedCR. Thanks for their wonderful works!