Home > Research > Publications & Outputs > Mobility-Aware Split-Federated With Transfer Le...

Electronic data

  • Author accepted final version

    Accepted author manuscript, 3.2 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License


Text available via DOI:

View graph of relations

Mobility-Aware Split-Federated With Transfer Learning for Vehicular Semantic Communication Networks

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Article number10
<mark>Journal publication date</mark>15/05/2024
<mark>Journal</mark>IEEE Internet of Things Journal
Issue number10
Number of pages12
Pages (from-to)17237-17248
Publication StatusPublished
Early online date30/01/24
<mark>Original language</mark>English


Machine learning-based semantic communication is a promising enabler for future-generation wireless network systems such as 6G networks. In practice, effective semantic communication requires online training for unknown content. In highly mobile vehicular networks, however, reliable, and efficient model training becomes significantly challenging. The existing distributed learning approaches are also unable to effectively operate in highly dynamic vehicular semantic communication networks. To address these challenges, we propose a novel mobility-aware split-federated with transfer learning (MSFTL) framework based on vehicle task offloading scenarios in this paper. To enable adaptation to the complex vehicle semantic communication, the proposed framework divides the training of the model into four parts and uses the proposed new splitfederated learning. Furthermore, to improve training efficiency, model accuracy, and the ability to adapt in highly mobile environments, we also present a new transfer learning approach integrated into the proposed framework. Particularly, we propose a high-mobility training resource optimisation mechanism based on a Stackelberg game for MSFTL to further reduce training costs and adapt vehicle mobility scenarios. We also investigate the performance of the proposed schemes through extensive simulations. The results validate the proposed approach and indicate its superiority compared to the conventional learning frameworks for semantic communication in vehicular networks.