Latent Semantic Diffusion-based Channel Adaptive De-Noising SemCom for Future 6G Systems

被引:0
|
作者
Xu, Bingxuan [1 ]
Meng, Rui [1 ]
Chen, Yue [1 ]
Xu, Xiaodong [1 ,2 ]
Dong, Chen [1 ,2 ]
Sun, Hao [3 ]
机构
[1] BUPT, State Key Lab Networking & Switching Technol, Beijing, Peoples R China
[2] Peng Cheng Lab, Dept Broadband Commun, Shenzhen, Peoples R China
[3] Univ Cambridge, Dept Appl Math & Theoret Phys, Cambridge, England
基金
中国国家自然科学基金; 国家自然科学基金重大项目;
关键词
Semantic communication; sixth-generation (6G); diffusion model; image transmission;
D O I
10.1109/GLOBECOM54140.2023.10437849
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Compared with the current Shannon's Classical Information Theory (CIT) paradigm, semantic communication (SemCom) has recently attracted more attention, since it aims to transmit the meaning of information rather than bit-by-bit transmission, thus enhancing data transmission efficiency and supporting future human-centric, data-, and resource-intensive intelligent services in 6G systems. Nevertheless, channel noises are common and even serious in 6G-empowered scenarios, limiting the communication performance of SemCom, especially when Signal-to-Noise (SNR) levels during training and deployment stages are different, but training multi-networks to cover the scenario with a broad range of SNRs is computationally inefficient. Hence, we develop a novel De-Noising SemCom (DNSC) framework, where the designed de-noiser module can eliminate noise interference from semantic vectors. Upon the designed DNSC architecture, we further combine adversarial learning, variational autoencoder, and diffusion model to propose the Latent Diffusion DNSC (Latent-Diff DNSC) scheme to realize intelligent online de-noising. During the offline training phase, noises are added to latent semantic vectors in a forward Markov diffusion manner and then are eliminated in a reverse diffusion manner through the posterior distribution approximated by the U-shaped Network (U-Net), where the semantic de-noiser is optimized by maximizing evidence lower bound (ELBO). Such design can model real noisy channel environments with various SNRs and enable to adaptively remove noises from noisy semantic vectors during the online transmission phase. The simulations on open-source image datasets demonstrate the superiority of the proposed Latent-Diff DNSC scheme in PSNR and SSIM over different SNRs than the state-of-the-art schemes, including JPEG, Deep JSCC, and ADJSCC.
引用
收藏
页码:1229 / 1234
页数:6
相关论文
共 18 条
  • [1] Evaluating Diffusion-Based Image De-noising Techniques
    Nadernejad, E.
    Hassanpour, H.
    [J]. ICIAS 2007: INTERNATIONAL CONFERENCE ON INTELLIGENT & ADVANCED SYSTEMS, VOLS 1-3, PROCEEDINGS, 2007, : 565 - 570
  • [2] SVD-based De-noising and Parametric Channel Estimation for Power Line Communication Systems
    Gay, Matthias
    Lampe, Lutz
    Lampe, Alexander
    [J]. 2016 INTERNATIONAL SYMPOSIUM ON POWER LINE COMMUNICATIONS AND ITS APPLICATIONS (ISPLC), 2016, : 7 - 12
  • [3] ADAPTIVE6G: Adaptive Resource Management for Network Slicing Architectures in Current 5G and Future 6G Systems
    Anurag Thantharate
    Cory Beard
    [J]. Journal of Network and Systems Management, 2023, 31
  • [4] ADAPTIVE6G: Adaptive Resource Management for Network Slicing Architectures in Current 5G and Future 6G Systems
    Thantharate, Anurag
    Beard, Cory
    [J]. JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT, 2023, 31 (01)
  • [5] A Joint Channel Estimation and Compression Method Based on GAN in 6G Communication Systems
    Du, Ying
    Li, Yang
    Xu, Mingfeng
    Jiang, Jiamo
    Wang, Weidong
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (04):
  • [6] Quantum-Computing-Based Channel and Signal Modeling for 6G Wireless Systems
    Farouk, Ahmed
    Abuali, Najah Abed
    Mumtaz, Shahid
    [J]. IEEE COMMUNICATIONS MAGAZINE, 2024, 62 (02) : 64 - 70
  • [7] Integrating Network Digital Twinning into Future AI-based 6G Systems: The 6G-TWIN Vision
    Faye, Sebastien
    Camelo, Miguel
    Sottet, Jean-Sebastien
    Sommer, Christoph
    Franke, Mario
    Baudouin, Julien
    Castellanos, German
    Decorme, Regis
    Fanti, Maria Pia
    Fuladi, Ramin
    Kesik, Gunes
    Mendes, Beatriz
    Murphy, Chris
    Parker, Stephen
    Pryor, Simon
    Senouci, Sidi Mohammed
    Turcanu, Ion
    [J]. 2024 JOINT EUROPEAN CONFERENCE ON NETWORKS AND COMMUNICATIONS & 6G SUMMIT, EUCNC/6G SUMMIT 2024, 2024, : 883 - 888
  • [8] Machine Learning-based Predictive Channel Modeling for 6G Wireless Communications Using Image Semantic Segmentation
    Wu, Tong
    Wang, Cheng-Xiang
    Li, Junling
    Huang, Chen
    [J]. 2023 IEEE 34TH ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS, PIMRC, 2023,
  • [9] A Novel and Adaptive Angle Diversity-Based Receiver for 6G Underground Mining VLC Systems
    Palacios Jativa, Pablo
    Sanchez, Ivan
    Soto, Ismael
    Azurdia-Meza, Cesar A.
    Zabala-Blanco, David
    Ijaz, Muhammad
    Dehghan Firoozabadi, Ali
    Plets, David
    [J]. ENTROPY, 2022, 24 (11)
  • [10] A 3D Geometry-Based THz Channel Model for 6G Ultra Massive MIMO Systems
    Yuan, Yuan
    He, Ruisi
    Ai, Bo
    Ma, Zhangfeng
    Miao, Yang
    Niu, Yong
    Zhang, Jiayi
    Chen, Ruifeng
    Zhong, Zhangdui
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (03) : 2251 - 2266