Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911088782606336 |
|---|---|
| author | Hou, Xiangwang Wang, Jingjing Guan, Fangming Du, Jun Jiang, Chunxiao Ren, Yong |
| author_facet | Hou, Xiangwang Wang, Jingjing Guan, Fangming Du, Jun Jiang, Chunxiao Ren, Yong |
| contents | Emerging real-time computer vision (CV) applications on wireless edge devices demand energy-efficient and privacy-preserving learning. Federated learning (FL) enables on-device training without raw data sharing, yet remains challenging in resource-constrained environments due to energy-intensive computation and communication, as well as limited and non-i.i.d. local data. We propose FedDPQ, an ultra energy-efficient FL framework for real-time CV over unreliable wireless networks. FedDPQ integrates diffusion-based data augmentation, model pruning, communication quantization, and transmission power control to enhance training efficiency. It expands local datasets using synthetic data, reduces computation through pruning, compresses updates via quantization, and mitigates transmission outages with adaptive power control. We further derive a closed-form energy-convergence model capturing the coupled impact of these components, and develop a Bayesian optimization(BO)-based algorithm to jointly tune data augmentation strategy, pruning ratio, quantization level, and power control. To the best of our knowledge, this is the first work to jointly optimize FL performance from the perspectives of data, computation, and communication under unreliable wireless conditions. Experiments on representative CV tasks show that FedDPQ achieves superior convergence speed and energy efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01745 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design Hou, Xiangwang Wang, Jingjing Guan, Fangming Du, Jun Jiang, Chunxiao Ren, Yong Machine Learning Distributed, Parallel, and Cluster Computing Emerging real-time computer vision (CV) applications on wireless edge devices demand energy-efficient and privacy-preserving learning. Federated learning (FL) enables on-device training without raw data sharing, yet remains challenging in resource-constrained environments due to energy-intensive computation and communication, as well as limited and non-i.i.d. local data. We propose FedDPQ, an ultra energy-efficient FL framework for real-time CV over unreliable wireless networks. FedDPQ integrates diffusion-based data augmentation, model pruning, communication quantization, and transmission power control to enhance training efficiency. It expands local datasets using synthetic data, reduces computation through pruning, compresses updates via quantization, and mitigates transmission outages with adaptive power control. We further derive a closed-form energy-convergence model capturing the coupled impact of these components, and develop a Bayesian optimization(BO)-based algorithm to jointly tune data augmentation strategy, pruning ratio, quantization level, and power control. To the best of our knowledge, this is the first work to jointly optimize FL performance from the perspectives of data, computation, and communication under unreliable wireless conditions. Experiments on representative CV tasks show that FedDPQ achieves superior convergence speed and energy efficiency. |
| title | Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2508.01745 |