TY - JOUR
T1 - SALDR
T2 - Joint Self-Attention Learning and Dense Refine for Massive MIMO CSI Feedback with Multiple Compression Ratio
AU - Song, Xuan
AU - Wang, Jun
AU - Wang, Jie
AU - Gui, Guan
AU - Ohtsuki, Tomoaki
AU - Gacanin, Haris
AU - Sari, Hikmet
N1 - Funding Information:
Manuscript received April 29, 2021; revised May 10, 2021; accepted May 27, 2021. Date of publication June 2, 2021; date of current version September 9, 2021. This work was supported in part by the National Natural Science Fodunation of China under Grant 31671006 and Grant 61771251; in part by the Natural Science Research Major Program in Universities of Jiangsu Province under Grant 16KJA310002; in part by the Major Project of the Ministry of Industry and Information Technology of China under Grant TC190A3WZ-2; in part by the JSPS KAKENHI under Grant JP19H02142; in part by Jiangsu Province Innovation and Entrepreneurship Team under Grant CZ002SC19001; in part by the Six Top Talents Program of Jiangsu under Grant XYDXX-010; and in part by the Postgraduate Research and Practice Innovation Program of Jiangsu Province under Grant KYCX19_0903. The associate editor coordinating the review of this article and approving it for publication was C. K. Wen. (Corresponding authors: Jun Wang; Guan Gui.) Xuan Song, Jie Wang, Guan Gui, and Hikmet Sari are with the College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China (e-mail: 1220013604@njupt.edu.cn; 2018010223@njupt.edu.cn; guiguan@njupt.edu.cn; hikmet@njupt.edu.cn).
Publisher Copyright:
© 2012 IEEE.
PY - 2021/9
Y1 - 2021/9
N2 - The advantages of massive multiple-input multiple-output (MIMO) techniques depend heavily on the accuracy of channel state information (CSI). In frequency division duplexing (FDD) massive MIMO systems, the user equipment (UE) needs to feed downlink CSI back to the base station (BS) through the feedback link. The excessive feedback overheads and low reconstruction accuracy are the main obstacles for actual deployment of FDD massive MIMO systems. In recent years, deep learning (DL) has been widely used to address the above problems. In this letter, we propose a neural network by utilizing the self-attention learning and dense refine (SALDR), which improves the accuracy of CSI feedback. Furthermore, a unified decoder named SALDR-U is designed to realize different compression ratios for CSI feedback without changing any parameter. Simulation results show that the proposed SALDR and SALDR-U outperform the state-of-the-art network in terms of accuracy and overhead of CSI feedback. The source code for all the experiments is available at GitHub.The code of this letter can be downloaded from GitHub link: https://github.com/XS96/SALDR.
AB - The advantages of massive multiple-input multiple-output (MIMO) techniques depend heavily on the accuracy of channel state information (CSI). In frequency division duplexing (FDD) massive MIMO systems, the user equipment (UE) needs to feed downlink CSI back to the base station (BS) through the feedback link. The excessive feedback overheads and low reconstruction accuracy are the main obstacles for actual deployment of FDD massive MIMO systems. In recent years, deep learning (DL) has been widely used to address the above problems. In this letter, we propose a neural network by utilizing the self-attention learning and dense refine (SALDR), which improves the accuracy of CSI feedback. Furthermore, a unified decoder named SALDR-U is designed to realize different compression ratios for CSI feedback without changing any parameter. Simulation results show that the proposed SALDR and SALDR-U outperform the state-of-the-art network in terms of accuracy and overhead of CSI feedback. The source code for all the experiments is available at GitHub.The code of this letter can be downloaded from GitHub link: https://github.com/XS96/SALDR.
KW - CSI feedback
KW - Massive MIMO
KW - frequency division duplex
KW - multiple compression ratio
KW - self-attention learning
UR - http://www.scopus.com/inward/record.url?scp=85107354639&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107354639&partnerID=8YFLogxK
U2 - 10.1109/LWC.2021.3085317
DO - 10.1109/LWC.2021.3085317
M3 - Article
AN - SCOPUS:85107354639
SN - 2162-2337
VL - 10
SP - 1899
EP - 1903
JO - IEEE Wireless Communications Letters
JF - IEEE Wireless Communications Letters
IS - 9
M1 - 9445070
ER -