通过动态图结构提升联邦学习个性化效果
Personalized Federated Learning via Learning Dynamic Graphs
- 基于图注意力网络构建客户端间动态关联
- 在三个数据集上均优于12种主流方法
- 适合数据分布差异大的个性化场景
个性化联邦学习（PFL）旨在为每个客户端训练适配其本地数据分布的模型，但现有方法多聚焦于个性化全局模型，忽视了客户端模型聚合过程的调控。同时，几乎未考虑客户端间形成的图结构。本文提出pFedGAT方法，利用图注意力网络捕捉客户端间的潜在图结构，动态确定各客户端对目标客户端的重要性，实现对聚合过程的细粒度控制。在Fashion MNIST、CIFAR-10和CIFAR-100三个数据集上，与12种先进方法对比，pFedGAT在多种数据分布场景下均表现优异。
原文摘要 · Abstract (English)
Personalized Federated Learning (PFL) aims to train a personalized model for each client that is tailored to its local data distribution, learning fails to perform well on individual clients due to variations in their local data distributions. Most existing PFL methods focus on personalizing the aggregated global model for each client, neglecting the fundamental aspect of federated learning: the regulation of how client models are aggregated. Additionally, almost all of them overlook the graph structure formed by clients in federated learning. In this paper, we propose a novel method, Personalized Federated Learning with Graph Attention Network (pFedGAT), which captures the latent graph structure between clients and dynamically determines the importance of other clients for each client, enabling fine-grained control over the aggregation process. We evaluate pFedGAT across multiple data distribution scenarios, comparing it with twelve state of the art methods on three datasets: Fashion MNIST, CIFAR-10, and CIFAR-100, and find that it consistently performs well.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。