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, 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/
Cite
@article{arxiv.2602.13024,
title = {FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments},
author = {Alejandro Dopico-Castro and Oscar Fontenla-Romero and Bertha Guijarro-Berdiñas and Amparo Alonso-Betanzos and Iván Pérez Digón},
journal= {arXiv preprint arXiv:2602.13024},
year = {2026}
}
Comments
Accepted for publication at the 34th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2026)