Scalable Extraction Based Semantic Communication for 6G Wireless Networks (2407.11334v1)

Abstract: Due to the challenges of satisfying the demands for communication efficiency and intelligent connectivity, sixth-generation (6G) wireless network requires new communication frameworks to enable effective information exchange and the integrated AI and communication. The Deep Learning (DL) based semantic communication, which can integrate application requirements and the data meanings into data processing and transmission, is expected to become a new paradigm in 6G wireless networks. However, existing semantic communications frameworks rely on sending full semantic feature, which can maximize the semantic fidelity but fail to achieve the efficient semantic communications. In this article, we introduce a novel Scalable Extraction based Semantic Communication (SE-SC) model to support the potential applications in 6G wireless networks and then analyze its feasibility. Then, we propose a promising the SE-SC framework to highlight the potentials of SE-SC model in 6G wireless networks. Numerical results show that our proposed SE-SC scheme can offer an identical Quality of Service (QoS) for the downstream task with much fewer transmission symbols than the full semantic feature transmission and the traditional codec scheme. Finally, we discuss several challenges for further investigating the scalable extraction based semantic communications.