基于谱聚类的傅里叶个性化联邦学习研究

为了缓解联邦学习中跨不同用户终端数据非独立同分布(non-IID)引起的负面影响，该文提出一种基于谱聚类的傅里叶个性化联邦学习算法。具体地，构建一个面向图像分类识别的云边端协同个性化联邦学习模型，提出在云端协同下通过谱聚类将用户终端划分为多个聚类域，以充分利用相似用户终端学到的知识提升模型性能。其次，设计边端协同的局部联邦学习方法，通过代理模型在用户终端对个性化局部模型执行恢复与再更新的操作，可有效恢复聚合过程中丢失的本地知识。
进一步地，设计云边协同的傅里叶个性化联邦学习方法，即云服务器通过傅里叶变换将局部模型参数转换到频域空间上进行聚合，为每个边缘节点定制高质量的个性化局部模型，可使全局模型更适用于各个分布式用户终端。最后，实验结果表明，与现有相关算法相比，所提算法收敛速度更快，准确率提高了3%～13%。

Fourier Personalized Federated Learning Mechanism Based on Spectral Clustering

To relieve the negative impacts caused by non-Independent and Identically Distributed (non-IID) data across different clients in federated learning, a spectral clustering-based Fourier personalized federated learning mechanism is proposed to overcome the performance drops from data heterogeneity. Specifically, a cloud-edge-end collaborative personalized federated learning model for image recognition is constructed, and in order to make full use of the knowledge learned by similar clients, the clients are divided into multiple clusters by spectral clustering under cloud-edge collaboration. Next, a local federated learning method based on edge-end collaboration is proposed, in which an agent model is used to perform the process of restoring and re-updating the personalized local model at the clients to restore the local knowledge loss during aggregation.
Furthermore, a cloud-edge collaborative Fourier personalized federated learning method is proposed to adapt the global model to each distributed client. In this method, the cloud server converts the local model parameters to the frequency domain space for aggregation through Fourier transform, and customizes high-quality personalized local model for each edge node. Finally, the experimental results demonstrate that the proposed algorithm obtains competitive convergence speed compared with existing representative works and the accuracy is 3%～13% higher.