Heterogeneous Privacy-Preserving Federated Learning for Edge Intelligence

Summary

Researchers propose HeteroFed, a privacy-preserving federated learning framework for edge intelligence that targets data, model, and privacy heterogeneity across smart devices. It combines heterogeneous model construction, dynamic gradient clipping, adaptive noise addition, and deviation-aware aggregation. Experiments report global model accuracy gains of 18%, 15%, 13%, and 18% on MNIST, Fashion-MNIST, CIFAR-10, and THUCNews, respectively.