Inference-Time Unlabeled Personalized Federated Learning

In Federated learning (FL), multiple clients collaborate to learn a shared model through a central server while they keep data decentralized. Personalized federated learning (PFL) further extends FL by learning personalized models per client. In both FL and PFL, all clients participate in the training process and their labeled data is used for training. However, in reality, novel clients may wish to join a prediction service after it has been deployed, obtaining predictions for their own unlabeled data. Here, we introduce a new learning setup, Inference-Time Unlabeled PFL (ITU-PFL), where a system trained on a set of clients, needs to be later applied to novel unlabeled clients at inference time. We propose a novel approach to this problem, ITUFL-HN, which uses a hypernetwork to produce a new model for the late-to-the-party client. Specifically, we train an encoder network that learns a representation for a client given its unlabeled data. That client representation is fed to a hypernetwork that generates a personalized model for that client. Evaluated on five benchmark datasets, we find that ITUFL-HN generalizes better than current FL and PFL methods, especially when the novel client has a large domain shift from training clients. We also analyzed the generalization error for novel clients, and showed analytically and experimentally how they can apply differential privacy to their data.