Semantic Communications for 6g Networks: Theory, Architectures, and Challenges
DOI:
https://doi.org/10.54097/vwsfa141Keywords:
Semantic Communication, 6G Networks, Cross-Domain Collaboration, Lightweight Models.Abstract
As 6G communication systems advance toward the grand vision of intelligent connectivity, the conventional bit-centric communication paradigm is encountering multiple bottlenecks in energy efficiency, spectrum utilization, and security when addressing the extreme demands of millisecond-level latency, terabit-per-second data rates, and massive connectivity. Semantic communication, as a paradigm shift from transmitting bits to conveying meaning, offers a critical pathway to overcoming these limitations. This survey provides a systematic review and forward-looking analysis of semantic communication technologies for 6G. We clarify the core value of semantic communication—namely, achieving a qualitative leap in communication efficiency and network intelligence by intelligently extracting and transmitting task-relevant semantic information. Furthermore, we examine three key technological evolution paths: interpretable approaches grounded in traditional model-based optimization; dedicated, efficient schemes driven by deep learning; and cognitive communication paradigms empowered by large-scale foundation models. For each path, we present a critical analysis of its strengths, limitations, and ongoing debates. We then summarize four representative 6G architectures enabled by semantic communication, elucidating their design goals, technical distinctions, and inherent trade-offs. Finally, we identify the open research challenges and outline promising future research directions. This survey aims to serve as a comprehensive reference for both academia and industry, fostering the deep integration of semantic communication technologies in the 6G era.
Downloads
References
[1] Zawish, M., Davy, S., & Abraham, L. (2022). Complexity-driven CNN compression for resource-constrained edge AI. arXiv. https://arxiv.org/abs/2208.12816
[2] Xu, W., Yang, Z., Ng, D. W. K., Levorato, M., Eldar, Y. C., & Debbah, M. (2023). Edge learning for B5G networks with distributed signal processing: Semantic communication, edge computing, and wireless sensing. IEEE Journal of Selected Topics in Signal Processing, 17(1), 1–37. https://doi.org/10.1109/JSTSP.2023.3239189
[3] Gunduz, D., Qin, Z., Aguerri, I. E., Dhillon, H. S., Yang, Z., Yener, A., Wong, K. K., & Chae, C.-B. (2023). Beyond transmitting bits: Context, semantics, and task-oriented communications. IEEE Journal on Selected Areas in Communications, 41(1), 5–41. https://doi.org/10.1109/JSAC.2022.3223408
[4] Letaief, K. B., Chen, W., Shi, Y., Zhang, J., & Zhang, Y.-J. A. (2019). The roadmap to 6G: AI empowered wireless networks. IEEE Communications Magazine, 57(8), 84–90. https://doi.org/10.1109/MCOM.2019.1900271
[5] Qin, Z., Tao, X., Lu, J., Tong, W., & Li, G. Y. (2023). Semantic communications: Principles and challenges. IEEE Journal on Selected Areas in Communications, 41(1), 1–32. https://doi.org/10.1109/JSAC.2022.3223408
[6] Shi, G., Xiao, Y., Li, Y., & Xie, X. (2021). From semantic communication to semantic-aware networking: Model, architecture, and open problems. IEEE Communications Magazine, 59(8), 41–49. https://doi.org/10.1109/MCOM.2021.9509448
[7] Luo, X., Chen, H.-H., & Guo, Q. (2022). Semantic communications: Overview, open issues, and future research directions. IEEE Wireless Communications, 29(1), 210–220. https://doi.org/10.1109/MWC.001.2100642
[8] Shao, Y., Cao, Q., & Gunduz, D. (2024). A theory of semantic communication. arXiv. https://arxiv.org/abs/2401.00635
[9] Lu, K., Zhou, Q., Li, R., Zhao, Z., Chen, X., Wu, J., & Zhang, H. (2022). Rethinking modern communication from semantic coding to semantic communication. IEEE Wireless Communications. https://doi.org/10.1109/MWC.013.2100642
[10] Xie, H., Qin, Z., Li, G. Y., & Juang, B.-H. (2021). Deep learning enabled semantic communication systems. IEEE Transactions on Signal Processing, 69, 2663–2675. https://doi.org/10.1109/TSP.2021.3071210
[11] Lee, H., Lee, S. H., & Quek, T. Q. S. (2019). Deep learning for distributed optimization: Applications to wireless resource management. IEEE Journal on Selected Areas in Communications, 37(10), 2257–2266. https://doi.org/10.1109/JSAC.2019.2933890
[12] Sun, H., Chen, X., Shi, Q., Hong, M., Fu, X., & Sidiropoulos, N. D. (2017). Learning to optimize: Training deep neural networks for wireless resource management. In 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) (pp. 1–6). IEEE. https://doi.org/10.1109/SPAWC.2017.8227772
[13] Xie, H., Qin, Z., Tao, X., & Letaief, K. B. (2022). Task-oriented multi-user semantic communications. IEEE Journal on Selected Areas in Communications, 40(9), 2584–2597. https://doi.org/10.1109/JSAC.2022.3184567
[14] Xie, H., & Qin, Z. (2021). A lite distributed semantic communication system for Internet of Things. IEEE Journal on Selected Areas in Communications, 39(1), 142–153. https://doi.org/10.1109/JSAC.2020.3036955
[15] Lokumarambage, M. U., Gowrisetty, V. S. S., Rezaei, H., Sivalingam, T., Rajatheva, N., & Fernando, A. (2023). Wireless end-to-end image transmission system using semantic communications. IEEE Access, 11, 37149–37163. https://doi.org/10.1109/ACCESS.2023.3266656
[16] Jiang, F., Peng, Y., Dong, L., et al. (2023). Large AI model-based semantic communications. arXiv. https://arxiv.org/abs/2307.03492v2
[17] Xie, H., Qin, Z., Tao, X., et al. (2024). Large model empowered semantic communications. arXiv. https://arxiv.org/abs/2402.13073v2
[18] Chaccour, C., Saad, W., Debbah, M., Han, Z., & Poor, H. V. (2025). Less data, more knowledge: Building next-generation semantic communication networks. IEEE Communications Surveys & Tutorials, 27(1), 38–74. https://doi.org/10.1109/COMST.2024.3412852
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Academic Journal of Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
