Personalized Federated Learning via Learning Dynamic Graphs
This addresses the challenge of training personalized models for clients with varying data distributions in federated learning, offering an incremental improvement by incorporating graph structures into aggregation.
The paper tackles the problem of personalized federated learning by proposing pFedGAT, a method that uses graph attention networks to dynamically model client relationships and control aggregation, achieving consistent performance improvements over 12 state-of-the-art methods on datasets like Fashion MNIST, CIFAR-10, and CIFAR-100.
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.