Reconfigurable intelligent surface (RIS) has become one of the key technologies for future 6G communications due to its characteristics of an intelligent and controllable wireless environment. In the frequency division duplex mode, the user equipment feeds back the downlink channel state information (CSI) to the base station through the feedback link, to obtain potential gains for the RIS-aided wireless communication system. A large number of RIS reflection elements greatly increase the feedback link cost of the system. In this letter, Quan-Transformer, a sample network framework for CSI compression and reconstruction, is proposed based on Transformer network. The proposed framework can not only compress CSI effectively but also recover CSI with high precision, which improves the performance of the RIS-aided wireless communication system. According to the experimental results, compared with the CsiNet scheme, the achievable sum-rate and normalized mean squared error of the proposed scheme are increased by 6.57% and 3.32%, respectively.
A novel digital semantic communication (D-SemCom) framework is proposed to enhance the adaptability and goodput of multi-user-multiple-input multiple-output (MU-MIMO) orthogonal frequency division multiplexing (OFDM) systems by integrating the non-orthogonal superposition pilot (NOSIP) scheme. However, this introduces challenges, such as inter-user interference, which limit the performance of traditional signal processing methods. To address these challenges, we propose SANet, which realizes the nonlinear mapping of received signals to log-likelihood ratios. SANet leverages a common subspace and a multi-head self-attention mechanism to effectively suppress interference and optimize signal decoding performance. Additionally, SANet addresses the coupling between the semantic encoder-decoder and the channel environment, reducing the dependency on channel variations and enabling the system to adapt more flexibly to different channel and data scenarios. We also introduce an adaptive data augmentation strategy that dynamically adjusts the data representation based on channel conditions, further enhancing the reliability and performance of D-SemCom. Numerical results show that: 1) SANet improves the goodput of D-SemCom by 7.01% compared to traditional approaches; 2) the goodput of D-SemCom is improved by 37.15% with the NOSIP scheme compared to the orthogonal pilot scheme; and 3) the effectiveness of the adaptive data augmentation strategy in enhancing D-SemCom performance is validated.
13 June 2025 in IEEE Communications Standards Magazine
With the rapid advancement of AI, deep learning has been increasingly integrated into communication systems, driving the evolution of semantic communication. By extracting and transmitting task-relevant semantics from raw signals, this paradigm enhances efficiency while alleviating bandwidth and redundancy constraints. Multimodal data, as a dominant representation form, has shown promising results in tasks like VQA and cross-modal retrieval. However, its application in semantic communication remains nascent, with most studies limited to unimodal scenarios. Challenges persist in achieving modality-coordinated compression, cross-modal semantic alignment (the process of ensuring consistency between transmitted and received semantics, or aligning representations across modalities), and robust task-oriented transmission under channel variations. Addressing these issues necessitates the development of a unified multimodal semantic communication (MMSC) framework. Such efforts are crucial for enabling intelligent communication in future systems, including 6G, the metaverse, and IoV. This article reviews recent progress in MMSC, outlines key challenges, and explores future research directions in this emerging field.
29 November 2024 in IEEE Wireless Communications Letters
To reduce the required pilot and feedback overhead in reconfigurable intelligent surface (RIS)-aided wireless communication systems under frequency division duplex (FDD) mode, a deep distributed learning-based joint channel estimation and feedback framework is proposed. Specifically, in the channel estimation stage, an RIS channel estimation network (RIS-CENet) is designed to reconstruct the channel from limited pilots by using the dual-channel attention mechanism. In the channel feedback stage, the RIS channel feedback network (RIS-CFNet), based on a multi-head attention mechanism, is designed to capture the global features of high-dimensional channel matrices, thereby enabling their effective compression. Furthermore, an efficient distributed learning framework is proposed to achieve channel estimation and feedback tasks in complex and rapidly changing wireless channel environments. Numerical results show that the performance of the proposed distributed learning architecture is comparable to that of the centralized learning architecture. Distributed scheme I has better feedback accuracy, while distributed scheme II can effectively reduce the complexity of the system.
25 May 2026 in IEEE Transactions on Wireless Communications
The non-orthogonal superimposed pilot (NOSIP) scheme significantly improves the spectrum efficiency of semantic communication (SemCom) systems by effectively reducing pilot overhead. However, existing SemCom systems based on NOSIP still face challenges, including strong model-channel coupling and limited adaptability to heterogeneous channels. To address these issues, this paper proposes a flexible, channel-adaptive digital SemCom (D-SemCom) architecture based on the NOSIP scheme. Specifically, we design a lightweight semantic codec, termed ShiftViT, and a semantic receiver, termed ShiftRx, which employ time- and frequency-domain shift mechanisms to decouple pilot and data and suppress multi-user interference, thereby enabling image transmission under complex channel conditions. Furthermore, a lightweight channel adaptation algorithm based on first-order meta-learning is proposed to facilitate rapid adaptation and mitigate the strong coupling between semantic models and channel environments. Numerical results demonstrate that the proposed D-SemCom system achieves approximately 25.14% and 1.16% goodput improvements over traditional receivers and existing state-of-the-art methods, respectively, while reducing the computational complexity in terms of FLOPs by approximately 40.37%. In addition, the proposed channel adaptation algorithm is shown to rapidly adapt to diverse channel scenarios within the D-SemCom system.