TY - JOUR
T1 - A Variational Bayesian Inference-Inspired Unrolled Deep Network for MIMO Detection
AU - Wan, Qian
AU - Fang, Jun
AU - Huang, Yinsen
AU - Duan, Huiping
AU - Li, Hongbin
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2022
Y1 - 2022
N2 - The great success of deep learning (DL) has inspired researchers to develop more accurate and efficient symbol detectors for multi-input multi-output (MIMO) systems. Existing DL-based MIMO detectors, however, suffer several drawbacks. To address these issues, in this paper, we develop a model-driven DL detector based on variational Bayesian inference. Specifically, the proposed unrolled DL architecture is inspired by an inverse-free variational Bayesian learning framework which circumvents matrix inversion via maximizing a relaxed evidence lower bound. Two networks are respectively developed for independent and identically distributed (i.i.d.) Gaussian channels and arbitrarily correlated channels. The proposed networks, referred to as VBINet, have only a few learnable parameters and thus can be efficiently trained with a moderate amount of training samples. The proposed VBINet-based detectors can work in both offline and online training modes. An important advantage of our proposed networks over state-of-the-art MIMO detection networks such as OAMPNet and MMNet is that the VBINet can automatically learn the noise variance from data, thus yielding a significant performance improvement over the OAMPNet and MMNet in the presence of noise variance uncertainty. Simulation results show that the proposed VBINet-based detectors achieve competitive performance for both i.i.d. Gaussian and realistic 3GPP MIMO channels.
AB - The great success of deep learning (DL) has inspired researchers to develop more accurate and efficient symbol detectors for multi-input multi-output (MIMO) systems. Existing DL-based MIMO detectors, however, suffer several drawbacks. To address these issues, in this paper, we develop a model-driven DL detector based on variational Bayesian inference. Specifically, the proposed unrolled DL architecture is inspired by an inverse-free variational Bayesian learning framework which circumvents matrix inversion via maximizing a relaxed evidence lower bound. Two networks are respectively developed for independent and identically distributed (i.i.d.) Gaussian channels and arbitrarily correlated channels. The proposed networks, referred to as VBINet, have only a few learnable parameters and thus can be efficiently trained with a moderate amount of training samples. The proposed VBINet-based detectors can work in both offline and online training modes. An important advantage of our proposed networks over state-of-the-art MIMO detection networks such as OAMPNet and MMNet is that the VBINet can automatically learn the noise variance from data, thus yielding a significant performance improvement over the OAMPNet and MMNet in the presence of noise variance uncertainty. Simulation results show that the proposed VBINet-based detectors achieve competitive performance for both i.i.d. Gaussian and realistic 3GPP MIMO channels.
KW - MIMO detection
KW - unrolled deep networks
KW - variational Bayesian inference
UR - http://www.scopus.com/inward/record.url?scp=85122880349&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122880349&partnerID=8YFLogxK
U2 - 10.1109/TSP.2022.3140926
DO - 10.1109/TSP.2022.3140926
M3 - Article
AN - SCOPUS:85122880349
SN - 1053-587X
VL - 70
SP - 423
EP - 437
JO - IEEE Transactions on Signal Processing
JF - IEEE Transactions on Signal Processing
ER -