Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks

doi:10.1109/TWC.2024.3416375

	Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks
	Yinan Zou1 ; Yong Zhou1 ; Xu Chen 2; Yonina C. Eldar 3
	2024-10
发表期刊	IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (IF:8.9[JCR-2023],8.6[5-Year])
ISSN	1558-2248
EISSN	1558-2248
卷号	23 期号:10 页码:14530-14545
发表状态	已发表
DOI	10.1109/TWC.2024.3416375
摘要	Grant-free random access is an effective technology for enabling low-overhead and low-latency massive access, where joint activity detection and channel estimation (JADCE) is a critical issue. Although existing compressed sensing algorithms can be applied for JADCE, they usually fail to simultaneously harvest the following properties: effective sparsity inducing, fast convergence, robust to different pilot sequences, and adaptive to time-varying networks. To this end, we propose an unfolding framework for JADCE based on the proximal gradient method. Specifically, we formulate the JADCE problem as a group-row-sparse matrix recovery problem and leverage a minimax concave penalty rather than the widely-used ℓ1-norm to induce sparsity. We then develop a proximal gradient-based unfolding neural network that parameterizes the algorithmic iterations. To improve convergence rate, we incorporate momentum into the unfolding neural network, and prove the accelerated convergence theoretically. Based on the convergence analysis, we further develop an adaptive-tuning algorithm, which adjusts its parameters to different signal-to-noise ratio settings. Simulations show that the proposed unfolding neural network achieves better recovery performance, convergence rate, and adaptivity than current baselines.
关键词	Channel estimation Computer system recovery Gradient methods Internet of things Neural networks Signal reconstruction Signal to noise ratio Activity detection Compressed-Sensing Convergence Gradient's methods Joint activity Joint activity detection and channel estimation Massive random access Neural-networks Proximal gradient unfolding Random access Signal processing algorithms Unfoldings
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20242816661188
EI主题词	Compressed sensing
EI分类号	716.1 Information Theory and Signal Processing ; 722.3 Data Communication, Equipment and Techniques ; 723 Computer Software, Data Handling and Applications ; 921.6 Numerical Methods
原始文献类型	Article in Press
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/395946
专题	信息科学与技术学院信息科学与技术学院_PI研究组_周勇组信息科学与技术学院_硕士生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China 3.Faculty of Math and CS, Weizmann Institute of Science, Rehovot, Israel
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Yinan Zou,Yong Zhou,Xu Chen,et al. Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks[J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,2024,23(10):14530-14545.
APA	Yinan Zou,Yong Zhou,Xu Chen,&Yonina C. Eldar.(2024).Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks.IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS,23(10),14530-14545.
MLA	Yinan Zou,et al."Proximal Gradient-Based Unfolding for Massive Random Access in IoT Networks".IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 23.10(2024):14530-14545.