Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911760158556160 |
|---|---|
| author | Chen, Tan Yan, Jintao Sun, Yuxuan Zhou, Sheng Gündüz, Deniz Niu, Zhisheng |
| author_facet | Chen, Tan Yan, Jintao Sun, Yuxuan Zhou, Sheng Gündüz, Deniz Niu, Zhisheng |
| contents | Hierarchical federated learning (HFL) enables distributed training of models across multiple devices with the help of several edge servers and a cloud edge server in a privacy-preserving manner. In this paper, we consider HFL with highly mobile devices, mainly targeting at vehicular networks. Through convergence analysis, we show that mobility influences the convergence speed by both fusing the edge data and shuffling the edge models. While mobility is usually considered as a challenge from the perspective of communication, we prove that it increases the convergence speed of HFL with edge-level heterogeneous data, since more diverse data can be incorporated. Furthermore, we demonstrate that a higher speed leads to faster convergence, since it accelerates the fusion of data. Simulation results show that mobility increases the model accuracy of HFL by up to 15.1% when training a convolutional neural network on the CIFAR-10 dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09656 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks Chen, Tan Yan, Jintao Sun, Yuxuan Zhou, Sheng Gündüz, Deniz Niu, Zhisheng Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Hierarchical federated learning (HFL) enables distributed training of models across multiple devices with the help of several edge servers and a cloud edge server in a privacy-preserving manner. In this paper, we consider HFL with highly mobile devices, mainly targeting at vehicular networks. Through convergence analysis, we show that mobility influences the convergence speed by both fusing the edge data and shuffling the edge models. While mobility is usually considered as a challenge from the perspective of communication, we prove that it increases the convergence speed of HFL with edge-level heterogeneous data, since more diverse data can be incorporated. Furthermore, we demonstrate that a higher speed leads to faster convergence, since it accelerates the fusion of data. Simulation results show that mobility increases the model accuracy of HFL by up to 15.1% when training a convolutional neural network on the CIFAR-10 dataset. |
| title | Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2401.09656 |