DDA-Net: A Discrepancy-Based Domain Adaptation Network for CSI Feedback Transferability

被引:0
|
作者
Feng, Yijia [1 ]
Ye, Chenhui [1 ]
Li, Ruoyi [1 ]
Pan, Heng [1 ]
Korpi, Dani [2 ]
机构
[1] Nokia Bell Labs, Shanghai, Peoples R China
[2] Nokia Bell Labs, Espoo, Finland
关键词
CSI feedback; transfer learning; domain adaption; unsupervised learning;
D O I
10.1109/ICC45041.2023.10278810
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
The deep learning (DL)-based channel state information (CSI) feedback methods have been intensively explored in recent years. Most existing works are trained offline based on the prestored datasets. However, in real-world deployment, the pretrained model may not fit the field environment due to the wireless environment changes. In a previous study, a supervised learning approach has been introduced to deal with this CSI feedback transferability problem by finetuning the model. Nevertheless, the transmission for the original uncompressed CSI data will cause intense traffic in air interface. In this paper, a novel unsupervised transfer learning framework named Discrepancy-based Domain Adaptation Network (DDA-Net) is proposed to solve this problem. By minimizing the discrepancy between the CSI codeword datasets from the pretrained environment and field environment, the encoder and decoder are finetuned to extract the common features in both environments, so that the DL-based CSI feedback model can also work properly in a drifted environment without transmitting any original uncompressed CSI data. Simulation results show that the DDA approach can augment CSI feedback reconstruction accuracy and combat overfitting problems in the deployment environment. Compared to the existing supervised learning approach, the DDA approach can achieve similar CSI recovery performance without transmitting the original uncompressed CSI data, reducing considerable transmission traffic.
引用
收藏
页码:4157 / 4162
页数:6
相关论文
共 50 条
  • [1] Unsupervised Discrepancy-Based Domain Adaptation Network to Detect Rail Joint Condition
    Jiang, Gao-Feng
    Wang, Su-Mei
    Ni, Yi-Qing
    Liu, Wen-Qiang
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
  • [2] Weighted quantile discrepancy-based deep domain adaptation network for intelligent fault diagnosis
    Fan, Zhenhua
    Xu, Qifa
    Jiang, Cuixia
    Ding, Steven X.
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 240
  • [3] Discrepancy-based networks for unsupervised domain adaptation: a comparative study
    Csurka, Gabriela
    Baradel, Fabien
    Chidlovskii, Boris
    Clinchant, Stephane
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, : 2630 - 2636
  • [4] DDA-Net: Unsupervised cross-modality medical image segmentation via dual domain adaptation
    Bian, Xuesheng
    Luo, Xiongbiao
    Wang, Cheng
    Liu, Weiquan
    Lin, Xiuhong
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2022, 213
  • [5] A Graph Embedding Framework for Maximum Mean Discrepancy-Based Domain Adaptation Algorithms
    Chen, Yiming
    Song, Shiji
    Li, Shuang
    Wu, Cheng
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 199 - 213
  • [6] DDA-Net: Deep Distribution-Aware Network for Point Cloud Compression
    Ahn, Junghyun
    Pang, Jiahao
    Lodhi, Muhammad Asad
    Tian, Dong
    [J]. 2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS, 2023,
  • [7] Adaptation of discrepancy-based methods for solving Hybrid Flow Shop problems
    Ben Hmida, Abir
    Huguet, Marie-Jose
    Lopez, Pierre
    Haouari, Mohamed
    [J]. 2006 INTERNATIONAL CONFERENCE ON SERVICE SYSTEMS AND SERVICE MANAGEMENT, VOLS 1 AND 2, PROCEEDINGS, 2006, : 1120 - 1125
  • [8] Confidence based class weight and embedding discrepancy constraint network for partial domain adaptation
    Luo, Mingkai
    Yang, Zhao
    Ai, Weiwei
    Liu, Jiehao
    [J]. Journal of Visual Communication and Image Representation, 2022, 88
  • [9] Confidence based class weight and embedding discrepancy constraint network for partial domain adaptation
    Luo, Mingkai
    Yang, Zhao
    Ai, Weiwei
    Liu, Jiehao
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2022, 88
  • [10] A discrepancy-based parameter adaptation and stopping rule for minimization algorithms aiming at Tikhonov-type regularization
    Bredies, Kristian
    Zhariy, Mariya
    [J]. INVERSE PROBLEMS, 2013, 29 (02)