Semantic Communication Meets Heterogeneous Network : Emerging Trends, Opportunities, and Challenges

Zheng, Guhan and Ni, Qiang and Kaushik, Aryan and Yang, Lixia and Wang, Yushi and Zarakovitis, Charilaos (2025) Semantic Communication Meets Heterogeneous Network : Emerging Trends, Opportunities, and Challenges. IEEE Network. pp. 1-8. ISSN 0890-8044

Text (Author Accepted Version)
Author_Accepted_Version.pdf - Accepted Version
Available under License Creative Commons Attribution.
Download (2MB)

Abstract

Recent developments in machine learning (ML) techniques enable users to extract, transmit, and reconstruct information semantics at the semantic level through ML-based semantic communication (SemCom). This significantly increases network spectral efficiency and transmission robustness. The semantic codecs among various users and modalities, based on ML, however, inevitably experience semantic drift and necessitate collaborative updating to preserve transmission quality. The various heterogeneous characteristics of most networks, in turn, introduce emerging but unique challenges for semantic codec updating that are different from other general ML model updating. In this article, we propose a heterogeneity-aware semantic codec updating scheme to achieve efficient and reliable updating in heterogeneous networks. We begin with the introduction of the core components of SemCom and then highlight key issues in semantic codec updating under network heterogeneity, discussing several potential methods. Furthermore, the scheme is provided with performance metrics. Future research directions for advancing SemCom in complex, multi-modal environments are also discussed.