Massive MIMO CSI Feedback with Spiking Neural Networks

TL;DR

This paper introduces SpikingCSINet, a bio-inspired spiking neural network for massive MIMO CSI feedback that improves efficiency and reduces energy consumption while maintaining competitive performance.

Contribution

It develops a novel progressive residual architecture for SNNs, enabling effective high-dimensional CSI reconstruction with significantly lower energy use.

Findings

SpikingCSINet outperforms lightweight convolutional models in efficiency.

Achieves performance comparable to Transformer-based methods.

Reduces energy consumption by over 93%.

Abstract

Deep learning-based channel state information (CSI) feedback has achieved empirical success in massive multiple-input multiple-output (MIMO) systems. However, existing approaches largely rely on dense artificial neural networks (ANNs), whose computational overhead limits their practical applications. In this article, we exploit bio-inspired spiking neural networks (SNNs) for massive MIMO CSI feedback, referred to as SpikingCSINet, where both the feedback and the main network computations are implemented through spikes. To overcome the information bottleneck of binary spikes in high-dimensional reconstruction, we develop a progressive residual (PR) architecture that exploits the natural temporal dimension of SNNs, encoding successive residuals across time steps to enhance information compactness. Experiments on the COST 2100 benchmark show that SpikingCSINet attains a more favorable performance-efficiency tradeoff than lightweight convolutional baselines. Moreover, it achieves performance competitive with Transformer-based feedback while reducing energy consumption by over $93\%$.