Scalable Extraction Based Semantic Communication for 6G Wireless Networks

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 Artificial Intelligence (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.

Generative AI Driven Task-Oriented Adaptive Semantic Communications

Task-Oriented Semantic Communication (TOSC) has been regarded as a promising communication framework, serving for various Artificial Intelligence (AI) task driven applications. The existing TOSC frameworks focus on extracting the full semantic features of source data and learning low-dimensional channel inputs to transmit them within limited bandwidth resources. Although transmitting full semantic features can preserve the integrity of data meaning, this approach does not attain the performance threshold of the TOSC. In this paper, we propose a Task-oriented Adaptive Semantic Communication (TasCom) framework, which aims to effectively facilitate the execution of AI tasks by only sending task-related semantic features. In the TasCom framework, we first propose a Generative AI (GAI) architecture based Generative Joint Source-Channel Coding (G-JSCC) for efficient semantic transmission. Then, an Adaptive Coding Controller (ACC) is proposed to find the optimal coding scheme for the proposed G-JSCC, which allows the semantic features with significant contributions to the AI task to preferentially occupy limited bandwidth resources for wireless transmission. Furthermore, we propose a generative training algorithm to train the proposed TasCom for optimal performance. The simulation results show that the proposed TasCom outperforms the existing TOSC and traditional codec schemes on the object detection and instance segmentation tasks at all considered channel conditions.

Digital-Analog Transmission Framework for Task-Oriented Semantic Communications

Task-Oriented Semantic Communication (TOSC) has been considered as a new communication paradigm to serve various samrt devices that depend on Artificial Intelligence (AI) tasks in future wireless networks. The existing TOSC frameworks rely on the Neural Network (NN) model to extract the semantic feature from the source data. The semantic feature, constituted by analog vectors of a lower dimensionality relative to the original source data, reserves the meaning of the source data. By conveying the semantic feature, TOSCs can significantly reduce the amount of data transmission while ensuring the correct execution of the AI-driven downstream task. However, standardized wireless networks depend on digital signal processing for data transmission, yet they necessitate the conveyance of semantic features that are inherently analog. Although existing TOSC frameworks developed the Deep Learning (DL) based \emph{analog approach} or conventional \emph{digital approach} to transmit the semantic feature, but there are still many challenging problems to urgently be solved in actual deployment. In this article, we first propose several challenging issues associated with the development of the TOSC framework in the standardized wireless network. Then, we develop a Digital-Analog transmission framework based TOSC (DA-TOSC) to resolve these challenging issues. Future research directions are discussed to further improve the DA-TOSC.