Federated Learning (FL) is a machine learning paradigm where many clients collaboratively learn a shared global model with decentralized training data. Personalized FL additionally adapts the global model to different clients, achieving promising results on consistent local training and test distributions. However, for real-world personalized FL applications, it is crucial to go one step further: robustifying FL models under the evolving local test set during deployment, where various distribution shifts can arise. In this work, we identify the pitfalls of existing works under test-time distribution shifts and propose Federated Test-time Head Ensemble plus tuning(FedTHE+), which personalizes FL models with robustness to various test-time distribution shifts. We illustrate the advancement of FedTHE+ (and its computationally efficient variant FedTHE) over strong competitors, by training various neural architectures (CNN, ResNet, and Transformer) on CIFAR10 andImageNet with various test distributions. Along with this, we build a benchmark for assessing the performance and robustness of personalized FL methods during deployment. Code: https://github.com/LINs-lab/FedTHE.

翻译：联邦学习（FL）是一种机器学习范式，其中众多客户端利用去中心化训练数据协同学习共享的全局模型。个性化FL进一步将全局模型适配至不同客户端，在一致的本地训练与测试分布上取得了显著成果。然而，对于实际应用中的个性化FL场景，亟需更进一步：在部署过程中，面对动态演变的本地测试集（可能产生多种分布偏移）时，增强FL模型的鲁棒性。本研究揭示了现有方法在测试时分布偏移下的缺陷，并提出联邦测试时头部集成与微调（FedTHE+），该方法可针对多种测试时分布偏移实现FL模型的个性化鲁棒化。通过在CIFAR10和ImageNet数据集及多种测试分布上训练不同神经网络架构（CNN、ResNet和Transformer），我们展示了FedTHE+（及其计算高效变体FedTHE）相较于强基线方法的优势。与此同时，我们构建了一个基准测试框架，用于评估个性化FL方法在部署阶段的性能与鲁棒性。代码：https://github.com/LINs-lab/FedTHE。