FedRD: Reducing Divergences for Generalized Federated Learning via Heterogeneity-aware Parameter Guidance
This work addresses the challenge of federated domain generalization for unseen clients in heterogeneous federated learning, which is incremental as it builds on existing methods to reduce divergences.
The paper tackled the problem of generalizing federated learning models to unseen clients under heterogeneous data by addressing optimization and performance divergences, and the proposed FedRD algorithm demonstrated a substantial performance advantage over baselines in experiments on multi-domain datasets.
Heterogeneous federated learning (HFL) aims to ensure effective and privacy-preserving collaboration among different entities. As newly joined clients require significant adjustments and additional training to align with the existing system, the problem of generalizing federated learning models to unseen clients under heterogeneous data has become progressively crucial. Consequently, we highlight two unsolved challenging issues in federated domain generalization: Optimization Divergence and Performance Divergence. To tackle the above challenges, we propose FedRD, a novel heterogeneity-aware federated learning algorithm that collaboratively utilizes parameter-guided global generalization aggregation and local debiased classification to reduce divergences, aiming to obtain an optimal global model for participating and unseen clients. Extensive experiments on public multi-domain datasets demonstrate that our approach exhibits a substantial performance advantage over competing baselines in addressing this specific problem.