Semi-Asynchronous Federated Learning with Trajectory Prediction for Vehicular Edge Computing

Federated learning, as a distributed machine learning paradigm, offers promising solutions for vehicular edge computing (VEC) networks. However, federated learning in VEC with classification tasks still faces two key challenges: i) Delayed data labeling hampers supervised training; ii) Dynamic vehic...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE/ACM ... International Symposium on Quality of Service (Online) S. 1 - 10
Hauptverfasser: Deng, Yuxuan, Li, Xiuhua, Sun, Chuan, Fan, Qilin, Wang, Xiaofei, Leung, Victor C. M.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 19.06.2024
Schlagworte:
Data models
Federated learning
Heuristic algorithms
Knowledge distillation
Prediction algorithms
Predictive models
Training
Trajectory
Trajectory prediction
Vehicular edge computing
ISSN:2766-8568
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Federated learning, as a distributed machine learning paradigm, offers promising solutions for vehicular edge computing (VEC) networks. However, federated learning in VEC with classification tasks still faces two key challenges: i) Delayed data labeling hampers supervised training; ii) Dynamic vehicle behavior complicates training scheduling and model uploads to edge servers. In this paper, we propose a semi-asynchronous federated learning algorithm for VEC. Specifically, it utilizes knowledge distillation to generate soft labels from raw data for supervised training, and estimates model training and uploading time through trajectory prediction. We further logically group vehicles based on the characteristics of their dynamic behavior. We then employ synchronous aggregation within groups and asynchronous aggregation between groups to optimize model performance while reducing latency. Finally, we conduct separate comparative experiments for all components, demonstrating that each component possesses unique advantages. Experiment results show that the proposed algorithm outperforms existing schemes in terms of accuracy and latency. The code is available at: https://github.com/dyxcode/Semi-Asynchronous-Federated-Learning.
ISSN:2766-8568
DOI:10.1109/IWQoS61813.2024.10682953