Changeable Rate and Novel Quantization for CSI Feedback Based on Deep Learning

Liang, Xin; Chang, Haoran; Li, Haozhen; Xu, Gu; Zhang, Lin

doi:10.1109/twc.2022.3182216

Cited by 22 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[27] equips the µ-law quantizer into its system and improves the feedback performance through end-to-end training. Focusing on the non-differentiable problem brought by the quantization module, [28] designs a differentiable function to approximate the gradients.…”

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

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

show abstract

“…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: 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%

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