Xinqian Chen

G2G: Generalized Learning by Cross-Domain Knowledge Transfer for Federated Domain Generalization

We propose G2G, based on the global model of Generalized learning to solve the Federated Domain Generalization (FedDG) task. FedDG aims to collaboratively train a global model that can directly generalize to the unseen target domain without data sharing. Existing methods face challenges from both da…