Approximate Message Passing-Enhanced Graph Neural Network for OTFS Data Detection

被引:0
|
作者
Zhuang, Wenhao [1 ]
Mao, Yuyi [1 ]
He, Hengtao [2 ]
Xie, Lei [2 ]
Song, Shenghui [2 ]
Ge, Yao [3 ]
Ding, Zhi [4 ]
机构
[1] Hong Kong Polytech Univ, Dept Elect & Elect Engn, Hong Kong, Peoples R China
[2] Hong Kong Univ Sci & Technol, Dept Elect & Comp Engn, Hong Kong, Peoples R China
[3] Nanyang Technol Univ, Continental NTU Corp Lab, Singapore 637553, Singapore
[4] Univ Calif Davis, Dept Elect & Comp Engn, Davis, CA 95616 USA
关键词
Detectors; Symbols; Graph neural networks; Signal processing algorithms; Time-frequency analysis; Message passing; Indexes; Orthogonal time frequency space (OTFS) modulation; data detection; approximate message passing (AMP); graph neural network (GNN); INTERFERENCE CANCELLATION;
D O I
10.1109/LWC.2024.3395700
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Orthogonal time frequency space (OTFS) modulation has emerged as a promising solution to support high-mobility wireless communications, for which, cost-effective data detectors are critical. Although graph neural network (GNN)-based data detectors can achieve decent detection accuracy at reasonable computational cost, they fail to best harness prior information of transmitted data. To further minimize the data detection error of OTFS systems, this letter develops an AMP-GNN-based detector, leveraging the approximate message passing (AMP) algorithm to iteratively improve the symbol estimates of a GNN. Given the inter-Doppler interference (IDI) symbols incur substantial computational overhead to the constructed GNN, learning-based IDI approximation is implemented to sustain low detection complexity. Simulation results demonstrate a remarkable bit error rate (BER) performance achieved by the proposed AMP-GNN-based detector compared to existing baselines. Meanwhile, the proposed IDI approximation scheme avoids a large amount of computations with negligible BER degradation.
引用
收藏
页码:1913 / 1917
页数:5
相关论文
共 50 条
  • [1] Cross Message Passing Graph Neural Network
    Zhang, Zeyu
    Liu, Zheng
    Zhou, Qiyun
    Qu, Yanwen
    [J]. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [2] Hybrid Message Passing Detection for OTFS Modulation
    Li, Xiang
    Yuan, Weijie
    Li, Zhongjie
    [J]. 2023 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC, 2023,
  • [3] Propagation Enhanced Neural Message Passing for Graph Representation Learning
    Fan, Xiaolong
    Gong, Maoguo
    Wu, Yue
    Qin, A. K.
    Xie, Yu
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (02) : 1952 - 1964
  • [4] Generalized Approximate Message Passing Detector for GSM-OTFS Systems
    Wang, Tiebin
    Fan, Shiwen
    Chen, Hao
    Xiao, Yue
    Guan, Xuemei
    Song, Wenlong
    [J]. IEEE ACCESS, 2022, 10 : 22997 - 23007
  • [5] Explicit Message-Passing Heterogeneous Graph Neural Network
    Xu, Lei
    He, Zhen-Yu
    Wang, Kai
    Wang, Chang-Dong
    Huang, Shu-Qiang
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (07) : 6916 - 6929
  • [6] BeMap: Balanced Message Passing for Fair Graph Neural Network
    Lin, Xiao
    Kang, Jian
    Cong, Weilin
    Tong, Hanghang
    [J]. LEARNING ON GRAPHS CONFERENCE, VOL 231, 2023, 231
  • [7] Domain-adaptive message passing graph neural network
    Shen, Xiao
    Pan, Shirui
    Choi, Kup-Sze
    Zhou, Xi
    [J]. NEURAL NETWORKS, 2023, 164 : 439 - 454
  • [8] A graph neural network with negative message passing and uniformity maximization for graph coloring
    Xiangyu Wang
    Xueming Yan
    Yaochu Jin
    [J]. Complex & Intelligent Systems, 2024, 10 : 4445 - 4455
  • [9] A graph neural network with negative message passing and uniformity maximization for graph coloring
    Wang, Xiangyu
    Yan, Xueming
    Jin, Yaochu
    [J]. COMPLEX & INTELLIGENT SYSTEMS, 2024, 10 (03) : 4445 - 4455
  • [10] Graph Neural Network with Virtual Edge Message Passing for Heterophilous Graphs
    Sun, Chengcheng
    Niu, Qiang
    Rui, Xiaobin
    Wang, Zhixiao
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,