Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models
This work addresses efficiency and privacy challenges in federated learning for distributed systems, but it is incremental as it builds on existing one-shot and diffusion model methods.
The paper tackled data heterogeneity and privacy in one-shot federated learning by proposing FedDiff, a diffusion model approach, and a Fourier Magnitude Filtering method, showing improved performance and sample quality under differential privacy.
Federated learning (FL) enables multiple clients to train models collectively while preserving data privacy. However, FL faces challenges in terms of communication cost and data heterogeneity. One-shot federated learning has emerged as a solution by reducing communication rounds, improving efficiency, and providing better security against eavesdropping attacks. Nevertheless, data heterogeneity remains a significant challenge, impacting performance. This work explores the effectiveness of diffusion models in one-shot FL, demonstrating their applicability in addressing data heterogeneity and improving FL performance. Additionally, we investigate the utility of our diffusion model approach, FedDiff, compared to other one-shot FL methods under differential privacy (DP). Furthermore, to improve generated sample quality under DP settings, we propose a pragmatic Fourier Magnitude Filtering (FMF) method, enhancing the effectiveness of generated data for global model training.