Learning Proximal Operator Methods for Massive Connectivity in IoT Networks

doi:10.1109/GLOBECOM46510.2021.9685447

	Learning Proximal Operator Methods for Massive Connectivity in IoT Networks
	Zou, Yinan1 ; Zhou, Yong1 ; Shi, Yuanming1 ; Chen, Xu 2
	2021
会议录名称	2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM)
ISSN	2334-0983
发表状态	已发表
DOI	10.1109/GLOBECOM46510.2021.9685447
摘要	Grant-free random access has the potential to support massive connectivity in Internet of Things (IoT) networks, where joint activity detection and channel estimation (JADCE) is a key issue that needs to be tackled. The existing methods for JADCE usually suffer from one of the following limitations: high computational complexity, ineffective in inducing sparsity, and incapable of handling complex matrix estimation. To mitigate all the aforementioned limitations, we in this paper develop an effective unfolding neural network framework built upon the proximal operator method to tackle the JADCE problem in IoT networks, where the base station is equipped with multiple antennas. Specifically, the JADCE problem is formulated as a group-sparse-matrix estimation problem, which is regularized by non-convex minimax concave penalty (MCP). This problem can be iteratively solved by using the proximal operator method, based on which we develop a unfolding neural network structure by parameterizing the algorithmic iterations. By further exploiting the coupling structure among the training parameters as well as the analytical computation, we develop two additional unfolding structures to reduce the training complexity. We prove that the proposed algorithm achieves a linear convergence rate. Results show that our proposed three unfolding structures not only achieve a faster convergence rate but also obtain a higher estimation accuracy than the baseline methods.
会议名称	IEEE Global Communications Conference (GLOBECOM)
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	null,Madrid,SPAIN
会议日期	DEC 07-11, 2021
URL	查看原文
收录类别	CPCI-S ; EI ; CPCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[U20A20159]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000790747202052
出版者	IEEE
EISSN	2576-6813
来源库	IEEE
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/183437
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_石远明组信息科学与技术学院_PI研究组_周勇组
通讯作者	Zou, Yinan
作者单位	1.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 2.Sun Yat Sen Univ, Sch Comp Sci & Engn, Guangzhou, Peoples R China
第一作者单位	信息科学与技术学院
通讯作者单位	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	Zou, Yinan,Zhou, Yong,Shi, Yuanming,et al. Learning Proximal Operator Methods for Massive Connectivity in IoT Networks[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021.