RUC. Repositorio da Universidade da Coruña
Publicación
Contribución de congreso (ConferenceOutput)
FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments
[Abstract]:
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, pretrained 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/, Work funded by Project PID2023-147404OB-I00 (MICIU/AEI/10.13039/501100011033; ERDF/EU; ESF+/EU), Horizon Europe (GA 101070381), and the Ministry for Digital Transformation and Civil Service and Next-GenerationEU/PRTR (TSI-100925-2023-1). CITIC, as a member of the CIGUS Network, receives subsidies from the “Xunta de Galicia” and from the ERDF Operational Programme Galicia 2021-2027 (Grant ED431G 2023/01), Xunta de Galicia; ED431G 2023/01