FedCCRL: Federated Domain Generalization with Cross-Client Representation Learning

Domain Generalization (DG) aims to train models that can effectively generalize to unseen domains. However, in the context of Federated Learning (FL), where clients collaboratively train a model without directly sharing their data, most existing DG algorithms are not directly applicable to the FL setting due to privacy constraints, as well as the limited data quantity and domain diversity at each client. To tackle these challenges, we propose FedCCRL, a novel federated domain generalization method that significantly improves the model's generalization ability without compromising privacy or incurring excessive computational and communication costs. Specifically, we design a lightweight cross-client feature extension module that effectively increases domain diversity on each client. Furthermore, we leverage representation and prediction dual-stage alignment to enable the model to capture domain-invariant features. Extensive experimental results demonstrate that FedCCRL achieves the state-of-the-art performances on the PACS, OfficeHome and miniDomainNet datasets across FL settings of varying numbers of clients. Code is available at https://github.com/SanphouWang/FedCCRL.