Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kou, Wei-Bin, Wang, Shuai, Zhu, Guangxu, Luo, Bin, Chen, Yingxian, Ng, Derrick Wing Kwan, Wu, Yik-Chung
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909194228072448
author Kou, Wei-Bin
Wang, Shuai
Zhu, Guangxu
Luo, Bin
Chen, Yingxian
Ng, Derrick Wing Kwan
Wu, Yik-Chung
author_facet Kou, Wei-Bin
Wang, Shuai
Zhu, Guangxu
Luo, Bin
Chen, Yingxian
Ng, Derrick Wing Kwan
Wu, Yik-Chung
contents While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server. Hierarchical federated learning (HFL) overcomes such drawbacks via introduction of mid-point edge servers. However, the orchestration between constrained communication resources and HFL performance becomes an urgent problem. This paper proposes an optimization-based Communication Resource Constrained Hierarchical Federated Learning (CRCHFL) framework to minimize the generalization error of the autonomous driving model using hybrid data and model aggregation. The effectiveness of the proposed CRCHFL is evaluated in the Car Learning to Act (CARLA) simulation platform. Results show that the proposed CRCHFL both accelerates the convergence rate and enhances the generalization of federated learning autonomous driving model. Moreover, under the same communication resource budget, it outperforms the HFL by 10.33% and the SFL by 12.44%.
format Preprint
id arxiv_https___arxiv_org_abs_2306_16169
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving
Kou, Wei-Bin
Wang, Shuai
Zhu, Guangxu
Luo, Bin
Chen, Yingxian
Ng, Derrick Wing Kwan
Wu, Yik-Chung
Robotics
Distributed, Parallel, and Cluster Computing
Machine Learning
While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server. Hierarchical federated learning (HFL) overcomes such drawbacks via introduction of mid-point edge servers. However, the orchestration between constrained communication resources and HFL performance becomes an urgent problem. This paper proposes an optimization-based Communication Resource Constrained Hierarchical Federated Learning (CRCHFL) framework to minimize the generalization error of the autonomous driving model using hybrid data and model aggregation. The effectiveness of the proposed CRCHFL is evaluated in the Car Learning to Act (CARLA) simulation platform. Results show that the proposed CRCHFL both accelerates the convergence rate and enhances the generalization of federated learning autonomous driving model. Moreover, under the same communication resource budget, it outperforms the HFL by 10.33% and the SFL by 12.44%.
title Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving
topic Robotics
Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2306.16169