FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments
This addresses privacy and efficiency challenges in federated learning for sensitive visual data, though it is incremental as it builds on the FedHEONN framework.
The paper tackles the problem of costly and privacy-risky federated learning by proposing FedHENet, which uses a fixed feature extractor and homomorphic encryption to learn a single output layer in one communication round, achieving competitive accuracy with up to 70% better energy efficiency and hyperparameter-free operation.
Federated Learning (FL) enables collaborative training without centralizing data, essential for privacy compliance in real-world scenarios involving sensitive visual information. Most FL approaches rely on expensive, iterative deep network optimization, which still risks privacy via shared gradients. In this work, we propose FedHENet, extending the FedHEONN framework to image classification. By using a fixed, pre-trained feature extractor and learning only a single output layer, we avoid costly local fine-tuning. This layer is learned by analytically aggregating client knowledge in a single round of communication using homomorphic encryption (HE). Experiments show that FedHENet achieves competitive accuracy compared to iterative FL baselines while demonstrating superior stability performance and up to 70\% better energy efficiency. Crucially, our method is hyperparameter-free, removing the carbon footprint associated with hyperparameter tuning in standard FL. Code available in https://github.com/AlejandroDopico2/FedHENet/