Learned conjugate gradient descent network for massive MIMO detection

Yi Wei, Ming Min Zhao, Mingyi Hong, Min Jian Zhao, Ming Lei

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


In this work, we consider the use of model-driven deep learning techniques for massive multiple-input multiple-output (MIMO) detection. Compared with conventional MIMO systems, massive MIMO promises improved spectral efficiency, coverage and range. Unfortunately, these benefits are at the expense of significantly increased computational complexity. To reduce the complexity of signal detection and guarantee the performance, we present a learned conjugate gradient descent network (LcgNet), which is constructed by unfolding the iterative conjugate gradient descent (CG) detector. In the proposed network, instead of calculating the exact values of the scalar step-sizes, we explicitly learn their universal values. Also, we can enhance the proposed network by augmenting the dimensions of these step-sizes. Furthermore, in order to reduce the memory costs, a novel quantized LcgNet is proposed, where a low-resolution nonuniform quantizer is used to quantize the learned parameters. The quantizer is based on a specially designed soft staircase function with learnable parameters to adjust its shape. Meanwhile, due to fact that the number of learnable parameters is limited, the proposed networks are relatively easy to train. Numerical results demonstrate that the proposed network can achieve promising performance with much lower complexity.

Original languageEnglish (US)
Article number3035832
Pages (from-to)6336-6349
Number of pages14
JournalIEEE Transactions on Signal Processing
StatePublished - 2020

Bibliographical note

Funding Information:
Manuscript received December 30, 2019; revised July 21, 2020; accepted October 26, 2020. Date of publication November 6, 2020; date of current version November 17, 2020. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Weiyu Xu. This work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1802303, in part by the National Natural Science Foundation of China under Grants 62001417 and 91938202, in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LQ20F010010, and in part by the Fundamental Research Funds for the Central Universities under Grant 2019QNA5011. (Corresponding authors: Ming-Min Zhao; Min-Jian Zhao.) Yi Wei, Ming-Min Zhao, Min-Jian Zhao, and Ming Lei are with the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China (e-mail: 21731133@zju.edu.cn; zmmblack@zju.edu.cn; Membermjzhao@zju.edu.cn; Memberlm1029@zju.edu.cn).

Publisher Copyright:
© 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.


  • Conjugate gradient descent
  • Deep learning
  • Massive MIMO detection
  • Model-driven method

Fingerprint Dive into the research topics of 'Learned conjugate gradient descent network for massive MIMO detection'. Together they form a unique fingerprint.

Cite this