Model-Driven Deep Learning for Physical Layer Communications

He, Hengtao; Jin, Shi; Wen, Chao-Kai; Gao, Feifei; Li, Geoffrey Ye; Xu, Zongben

doi:10.1109/mwc.2019.1800447

Cited by 403 publications

(225 citation statements)

References 20 publications

Supporting

Mentioning

225

Contrasting

Order By: Relevance

“…As shown in Fig. 4, K B red dash-dotted lines point to the next position of parameter Ω, which implies that K B trained source-task-specific parameters for k = 1, · · · , K B do 9 Initialize the parameter Ω k ← Ω 10 for g = 1, · · · , G Tr do 11 Obtain truncated gradient υ S,k using Eq. (18) 12 Update the parameter Ω S,k with gradient descent: Ω S,k ← Ω S,k − βυ S,k Update the parameter Ω unbiased 1 st and 2 nd moment vectors: Ω ← Ω − γμ 3 /( √ν 3 + ε) 19 end 20 Meta-trained network parameter: Ω Mt ← Ω 21 Meta-adaption and Testing 22 Initialize NMSE: NMSE Mt ← 0 23 for k = 1, · · · , K T do 24 Generate the datasets D Ad (k) and D Te (k) for T T (k) 25 Meta-adaption stage 26 Load the network parameter Ω T,k ← Ω Mt 27 for g = 1, · · · , G Ad do 28 Obtain truncated gradient υ T,k using Eq.…”

Section: Meta-adaption and Testing Stagesmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System

et al. 2019

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) based downlink channel state information (CSI) prediction for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems has attracted growing attention recently. However, existing works focus on the downlink CSI prediction for the users under a given environment and is hard to adapt to users in new environment especially when labeled data is limited. To address this issue, we formulate the downlink channel prediction as a deep transfer learning (DTL) problem, where each learning task aims to predict the downlink CSI from the uplink CSI for one single environment. Specifically, we develop the directtransfer algorithm based on the fully-connected neural network architecture, where the network is trained on the data from all previous environments in the manner of classical deep learning and is then fine-tuned for new environments. To further improve the transfer efficiency, we propose the meta-learning algorithm that trains the network by alternating inner-task and acrosstask updates and then adapts to a new environment with a small number of labeled data. Simulation results show that the direct-transfer algorithm achieves better performance than the deep learning algorithm, which implies that the transfer learning benefits the downlink channel prediction in new environments. Moreover, the meta-learning algorithm significantly outperforms the direct-transfer algorithm in terms of both prediction accuracy and stability, which validates its effectiveness and superiority.

show abstract

Section: Meta-adaption and Testing Stagesmentioning

confidence: 99%

“…Initialize the 1 st and 2 nd moment vectors: µ 2 , ν 2 ← 0 10 for g = 1, · · · , G Ad do 11 Update biased 1 st and 2 nd moment vectors using Eq. (15) 12…”

mentioning

confidence: 99%

Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…training time in addition to a huge data set. On the other hand, model-driven DL constructs the network topology based on known domain knowledge and has been successfully applied to image reconstruction [29], sparse signal recovery [30]- [33], and wireless communications recently [1], [11].…”

Section: Introductionmentioning

confidence: 99%

Model-Driven Deep Learning for MIMO Detection

Wen

Jin

et al. 2020

IEEE Trans. Signal Process.

Self Cite

333

164

View full text Add to dashboard Cite

In this paper, we investigate the model-driven deep learning (DL) for joint MIMO channel estimation and signal detection (JCESD), where signal detection considers channel estimation error and channel statistics while channel estimation is refined by detected data and takes the signal detection error into consideration. In particular, the MIMO signal detector is specially designed by unfolding an iterative algorithm and adding some trainable parameters. Since the number of trainable parameters is much fewer than the data-driven DL based signal detector, the model-driven DL based MIMO signal detector can be rapidly trained with a much smaller data set. Furthermore, the proposed signal detector can be extended to soft-input soft-output detection easily. Based on numerical results, the model-driven DL based JCESD scheme significantly improves the performance of the corresponding traditional iterative detector and the signal detector exhibits superior robustness to signal-to-noise ratio (SNR) and channel correlation mismatches. Recently, it has been applied in physical layer communications [10]-[12], such as channel estimation [13]-[15], CSI feedback [16], signal detection [17]-[25], and channel coding [26], [27]. In particular, a five-layer fully connected deep neural network (DNN) is embedded into an orthogonal frequency-division multiplexing (OFDM) system for joint channel estimation and signal detection (JCESD) by treating the receiver as a black box and without exploiting domain knowledge [17]. However, training such a black-box-based network requires a lot of 1 A matrix A = UΣV is unitarily-invariant if U, Σ and V are mutually independent, and U, V are Haar-distributed. The independent and identically distributed (i.i.d.) Gaussian matrix is a typical unitarily-invariant matrix.

show abstract

“…In this paper, we propose a DL enabled beamforming optimization approach for SINR balancing to provide an improved performance-complexity tradeoff under perantenna power constraints. Inspired by the model driven learning philosophy [48], we propose to first learn the dual variables with reduced dimension rather than the original large beamforming matrix and then recover the beamforming solution from the learned dual solution, by exploiting the structure or model of the beamforming optimization problem. Our main contributions are summarized as follows:…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration

Zhang

Xia

You

et al. 2020

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

This paper studies fast downlink beamforming algorithms using deep learning in multiuser multiple-inputsingle-output systems where each transmit antenna at the base station has its own power constraint. We focus on the signal-to-interference-plus-noise ratio (SINR) balancing problem which is quasi-convex but there is no efficient solution available. We first design a fast subgradient algorithm that can achieve near-optimal solution with reduced complexity. We then propose a deep neural network structure to learn the optimal beamforming based on convolutional networks and exploitation of the duality of the original problem. Two strategies of learning various dual variables are investigated with different accuracies, and the corresponding recovery of the original solution is facilitated by the subgradient algorithm. We also develop a generalization method of the proposed algorithms so that they can adapt to the varying number of users and antennas without re-training. We carry out intensive numerical simulations and testbed experiments to evaluate the performance of the proposed algorithms. Results show that the proposed algorithms achieve close to optimal solution in simulations with perfect channel information and outperform the alleged theoretically optimal solution in experiments, illustrating a better performance-complexity tradeoff than existing schemes.Index Terms-Deep learning, beamforming, MISO, SINR balancing, per-antenna power constraints. ).We gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan Xp GPU used for this research.

show abstract

Model-Driven Deep Learning for Physical Layer Communications

Cited by 403 publications

References 20 publications

Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System

Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System

Model-Driven Deep Learning for MIMO Detection

Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration

Contact Info

Product

Resources

About