Personalized Federated Learning using Hypernetworks
This addresses the challenge of data heterogeneity and communication efficiency in federated learning for applications like healthcare or IoT, representing a novel method rather than an incremental improvement.
The paper tackles the problem of training personalized models for multiple clients with different data distributions in federated learning, proposing pFedHN which uses a central hypernetwork to generate client-specific models and achieves better performance than previous methods while decoupling communication costs from model size.
Personalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models in a collaborative way while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients, while maintaining the capacity to generate unique and diverse personal models. Furthermore, since hypernetwork parameters are never transmitted, this approach decouples the communication cost from the trainable model size. We test pFedHN empirically in several personalized federated learning challenges and find that it outperforms previous methods. Finally, since hypernetworks share information across clients we show that pFedHN can generalize better to new clients whose distributions differ from any client observed during training.