Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach

TL;DR

This paper introduces a resource-efficient CSI prediction model combining gated fusion, attention, and factorized projection, achieving high accuracy with fewer parameters and higher throughput for MIMO systems.

Contribution

It proposes a novel CSI predictor that reduces computational cost while maintaining accuracy, using a gated fusion module and a dimension-wise separable linear head.

Findings

Achieves an average NMSE of -13.84 dB on 3GPP channels.

Uses 26% fewer parameters than baseline models.

Provides approximately 2.3x higher inference throughput.

Abstract

Accurate Channel State Information (CSI) prediction is essential for dynamic multiple-input multiple-output (MIMO) systems but remains computationally demanding. This letter proposes a resource-efficient predictor that combines a gated recurrent unit (GRU) encoder with Luong attention, a bottleneck gated fusion module, and a Dimension-wise Separable Linear Head (DSLH). The gated fusion module integrates local recurrent features with global attention context, while the DSLH reduces the cost of the output mapping. Evaluated on 3GPP TR 38.901-compliant channels, the proposed model achieves an average NMSE of -13.84 dB with 26% fewer parameters and approximately 2.3x higher inference throughput than a dimension-matched LinFormer baseline. The proposed model is best suited to LOS and mixed-condition scenarios, offering a practical accuracy-efficiency trade-off for short-horizon CSI prediction at moderate sequence lengths.