FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918336877559808 |
|---|---|
| author | Dopico-Castro, Alejandro Fontenla-Romero, Oscar Guijarro-Berdiñas, Bertha Alonso-Betanzos, Amparo Digón, Iván Pérez |
| author_facet | Dopico-Castro, Alejandro Fontenla-Romero, Oscar Guijarro-Berdiñas, Bertha Alonso-Betanzos, Amparo Digón, Iván Pérez |
| contents | 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/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13024 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments Dopico-Castro, Alejandro Fontenla-Romero, Oscar Guijarro-Berdiñas, Bertha Alonso-Betanzos, Amparo Digón, Iván Pérez Computer Vision and Pattern Recognition Machine Learning 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/ |
| title | FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2602.13024 |