Personalized Federated Learning with Contextualized Generalization

Understand

The prevalent personalized federated learning (PFL) usually pursues a trade-off between personalization and generalization by maintaining a shared global model to guide the training process of local models.

• However, the sole global model may easily transfer deviated context knowledge to some local models when multiple latent contexts exist across the local datasets.
• In this paper, we propose a novel concept called contextualized generalization (CG) to provide each client with fine-grained context knowledge that can better fit the local data distributions and facilitate faster model convergence, based on which we properly design a framework of PFL, dubbed CGPFL.
• We conduct detailed theoretical analysis, in which the convergence guarantee is presented and $\mathcal{O}(\sqrt{K})$ speedup over most existing methods is granted.