Clustering Algorithm-Based Quantization Method for Massive MIMO CSI Feedback

Shen, Jinghan; Liang, Xin; Xu, Gu; Zhang, Lin

doi:10.1109/lwc.2022.3195883

Cited by 8 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of the retraining decoder training mode are always different from those of an end-to-end fashion, with the latter generally performs better [15]. Hence, for the uniform quantization and µ-law quantization, we adopt an end-to-end fashion and set the gradient of quantizers to constant one to pass the back propagation, similar to the approach used in [9], [15], [16]. The training strategies and random seed are the same for all these quantization methods with 1000 epochs and cosine annealing learning rate.…”

Section: Quantization Module Evaluationmentioning

confidence: 93%

“…Note that the above quantization methods should be compared under the same training mode. The results of the retraining decoder training mode are always different from those of an end-to-end fashion, with the latter generally performs better [15]. Hence, for the uniform quantization and µ-law quantization, we adopt an end-to-end fashion and set the gradient of quantizers to constant one to pass the back propagation, similar to the approach used in [9], [15], [16].…”

Section: Quantization Module Evaluationmentioning

confidence: 99%

“…The residual learning [9], clustering schemes [15], and approximate gradient functions [16] are introduced to generate bitstream and reduce quantization distortion. DL-based networks can be generally divided into CNNs and attention frameworks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Lightweight Deep Network for Efficient CSI Feedback in Massive MIMO Systems

Sun

Liang

et al. 2021

IEEE Wireless Commun. Lett.

View full text Add to dashboard Cite

The efficacy of massive multiple-input multiple-output (MIMO) techniques heavily relies on the accuracy of channel state information (CSI) in frequency division duplexing (FDD) systems.Many works focus on CSI compression and quantization methods to enhance CSI reconstruction accuracy with lower feedback overhead. In this letter, we propose CsiConformer, a novel CSI feedback network that combines convolutional operations and self-attention mechanisms to improve CSI feedback accuracy. Additionally, a new quantization module is developed to improve encoding efficiency. Experiment results show that CsiConformer outperforms previous state-of-the-art networks, achieving an average accuracy improvement of 17.67% with lower computational overhead.

show abstract

Section: Quantization Module Evaluationmentioning

confidence: 93%

Section: Quantization Module Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

A Lightweight Deep Network for Efficient CSI Feedback in Massive MIMO Systems

Sun

Liang

et al. 2021

IEEE Wireless Commun. Lett.

View full text Add to dashboard Cite

show abstract

“…In this way, better system performance can be obtained with fewer feedback bits. A clustering algorithm-based quantization method is proposed in [30]. It utilizes the k-means method with vector quantization to divide codewords into different quantization intervals.…”

Section: Related Workmentioning

confidence: 99%

Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback

Zhang¹,

Lu²,

Zhou³

et al. 2022

Preprint

View full text Add to dashboard Cite

In massive multiple-input multiple-output (MIMO) systems, the user equipment (UE) needs to feed the channel state information (CSI) back to the base station (BS) for the following beamforming. But the large scale of antennas in massive MIMO systems causes huge feedback overhead. Deep learning (DL) based methods can compress the CSI at the UE and recover it at the BS, which reduces the feedback cost significantly. But the compressed CSI must be quantized into bit streams for transmission. In this paper, we propose an adaptor-assisted quantization strategy for bit-level DL-based CSI feedback. First, we design a network-aided adaptor and an advanced training scheme to adaptively improve the quantization and reconstruction accuracy. Moreover, for easy practical employment, we introduce the expert knowledge of data distribution and propose a pluggable and costfree adaptor scheme. Experiments show that compared with the state-of-the-art feedback quantization method, this adaptor-aided quantization strategy can achieve better quantization accuracy and reconstruction performance with less or no additional cost. The open-source codes are available at https://github.com/zhang-xd18/QCRNet.

show abstract