Federated Learning (FL) aims to infer a shared model from private and decentralized data stored by multiple clients. Personalized FL (PFL) enhances the model’s fit for each client by adapting the global model to the clients. A significant level of personalization is required for highly heterogeneous clients but can be challenging to achieve, especially when clients’ datasets are small. 

To address this issue, we introduce the PAC-PFL framework for PFL of probabilistic models. PAC-PFL infers a shared hyper-posterior and treats each client’s posterior inference as the personalization step. Unlike previous PFL algorithms, PAC-PFL does not regularize all personalized models towards a single shared model, thereby greatly enhancing its personalization flexibility.

By establishing and minimizing a PAC-Bayesian generalization bound on the average true loss of clients, PAC-PFL effectively mitigates over-fitting even in data-poor scenarios. Additionally, PAC-PFL provides generalization bounds for new clients joining later. PAC-PFL achieves accurate and well-calibrated predictions, as supported by our experiments.