FedGCA: Global Consistent Augmentation Based Single-Source Federated Domain Generalization
This addresses domain generalization in federated learning for applications with limited cross-domain data, but it is incremental as it builds on existing FedDG methods.
The paper tackles the single-source federated domain generalization problem, where clients have non-IID data from a single domain, by proposing FedGCA with style augmentation and consistency mechanisms, achieving superior performance in experiments.
Federated Domain Generalization (FedDG) aims to train the global model for generalization ability to unseen domains with multi-domain training samples. However, clients in federated learning networks are often confined to a single, non-IID domain due to inherent sampling and temporal limitations. The lack of cross-domain interaction and the in-domain divergence impede the learning of domain-common features and limit the effectiveness of existing FedDG, referred to as the single-source FedDG (sFedDG) problem. To address this, we introduce the Federated Global Consistent Augmentation (FedGCA) method, which incorporates a style-complement module to augment data samples with diverse domain styles. To ensure the effective integration of augmented samples, FedGCA employs both global guided semantic consistency and class consistency, mitigating inconsistencies from local semantics within individual clients and classes across multiple clients. The conducted extensive experiments demonstrate the superiority of FedGCA.