UPFL: Unsupervised Personalized Federated Learning towards New Clients
This addresses a relatively unexplored challenge in personalized federated learning for new clients, but it appears incremental as it builds on existing techniques like adaptive risk minimization.
The paper tackles the problem of providing personalized models for new, unlabeled clients in federated learning after deployment, proposing FedTTA with optimization strategies and knowledge distillation, achieving effectiveness demonstrated through experiments on five datasets against eleven baselines.
Personalized federated learning has gained significant attention as a promising approach to address the challenge of data heterogeneity. In this paper, we address a relatively unexplored problem in federated learning. When a federated model has been trained and deployed, and an unlabeled new client joins, providing a personalized model for the new client becomes a highly challenging task. To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA. We further improve FedTTA with two simple yet effective optimization strategies: enhancing the training of the adaptation model with proxy regularization and early-stopping the adaptation through entropy. Moreover, we propose a knowledge distillation loss specifically designed for FedTTA to address the device heterogeneity. Extensive experiments on five datasets against eleven baselines demonstrate the effectiveness of our proposed FedTTA and its variants. The code is available at: https://github.com/anonymous-federated-learning/code.