Learning Joint Source-Channel Encoding in IRS-assisted Multi-User Semantic Communications
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916683235459072 |
|---|---|
| author | Wang, Haidong Zhao, Songhan Li, Lanhua Gu, Bo Xu, Jing Gong, Shimin Kang, Jiawen |
| author_facet | Wang, Haidong Zhao, Songhan Li, Lanhua Gu, Bo Xu, Jing Gong, Shimin Kang, Jiawen |
| contents | In this paper, we investigate a joint source-channel encoding (JSCE) scheme in an intelligent reflecting surface (IRS)-assisted multi-user semantic communication system. Semantic encoding not only compresses redundant information, but also enhances information orthogonality in a semantic feature space. Meanwhile, the IRS can adjust the spatial orthogonality, enabling concurrent multi-user semantic communication in densely deployed wireless networks to improve spectrum efficiency. We aim to maximize the users' semantic throughput by jointly optimizing the users' scheduling, the IRS's passive beamforming, and the semantic encoding strategies. To tackle this non-convex problem, we propose an explainable deep neural network-driven deep reinforcement learning (XD-DRL) framework. Specifically, we employ a deep neural network (DNN) to serve as a joint source-channel semantic encoder, enabling transmitters to extract semantic features from raw images. By leveraging structural similarity, we assign some DNN weight coefficients as the IRS's phase shifts, allowing simultaneous optimization of IRS's passive beamforming and DNN training. Given the IRS's passive beamforming and semantic encoding strategies, user scheduling is optimized using the DRL method. Numerical results validate that our JSCE scheme achieves superior semantic throughput compared to the conventional schemes and efficiently reduces the semantic encoder's mode size in multi-user scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07498 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Joint Source-Channel Encoding in IRS-assisted Multi-User Semantic Communications Wang, Haidong Zhao, Songhan Li, Lanhua Gu, Bo Xu, Jing Gong, Shimin Kang, Jiawen Signal Processing In this paper, we investigate a joint source-channel encoding (JSCE) scheme in an intelligent reflecting surface (IRS)-assisted multi-user semantic communication system. Semantic encoding not only compresses redundant information, but also enhances information orthogonality in a semantic feature space. Meanwhile, the IRS can adjust the spatial orthogonality, enabling concurrent multi-user semantic communication in densely deployed wireless networks to improve spectrum efficiency. We aim to maximize the users' semantic throughput by jointly optimizing the users' scheduling, the IRS's passive beamforming, and the semantic encoding strategies. To tackle this non-convex problem, we propose an explainable deep neural network-driven deep reinforcement learning (XD-DRL) framework. Specifically, we employ a deep neural network (DNN) to serve as a joint source-channel semantic encoder, enabling transmitters to extract semantic features from raw images. By leveraging structural similarity, we assign some DNN weight coefficients as the IRS's phase shifts, allowing simultaneous optimization of IRS's passive beamforming and DNN training. Given the IRS's passive beamforming and semantic encoding strategies, user scheduling is optimized using the DRL method. Numerical results validate that our JSCE scheme achieves superior semantic throughput compared to the conventional schemes and efficiently reduces the semantic encoder's mode size in multi-user scenarios. |
| title | Learning Joint Source-Channel Encoding in IRS-assisted Multi-User Semantic Communications |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2504.07498 |