Hierarchical Federated Transfer Learning in Digital Twin-Based Vehicular Networks

2026-08-11

AI Summary

This work addresses the challenge of insufficient global model accuracy in federated learning for digital twin-enabled vehicular networks, primarily caused by the heterogeneity and sparsity of vehicle-generated data. To overcome this limitation, the authors propose a hierarchical federated transfer learning framework that clusters vehicles by type to establish intra-cluster collaborative training structures. The framework integrates global model aggregation at the cloud server with intra-cluster transfer learning and incorporates a data quality scoring mechanism to mitigate the adverse effects of malicious nodes. While preserving data privacy, the approach significantly enhances model generalization, robustness, and training efficiency. Experimental results on real-world datasets demonstrate consistent superiority over existing baseline methods across multiple performance metrics.

Abstract

In recent research on the Digital Twin-based Vehicular Ad hoc Network(DT-VANET), Federated Learning (FL) has shown its ability to provide data privacy. However, Federated learning struggles to adequately train a global model when confronted with data heterogeneity and data sparsity among vehicles, which ensure suboptimal accuracy in making precise predictions for different vehicle types. To address these challenges, this paper combines Federated Transfer Learning (FTL) to conduct vehicle clustering related to types of vehicles and proposes a novel Hierarchical Federated Transfer Learning (HFTL). We construct a framework for DT-VANET, along with two algorithms designed for cloud server model updates and intra-cluster federated transfer learning, to improve the accuracy of the global model. In addition, we developed a data quality score-based mechanism to prevent the global model from being affected by malicious vehicles. Lastly, detailed experiments on real-world datasets are conducted, considering different performance metrics that verify the effectiveness and efficiency of our algorithm.

Problem

• Federated Learning
• Data Heterogeneity
• Data Sparsity
• Digital Twin
• Vehicular Networks

Innovation

• Hierarchical Federated Transfer Learning
• Digital Twin-based VANET
• Data Heterogeneity
• Vehicle Clustering
• Data Quality Scoring