GNN-Enabled Robust Hybrid Beamforming with Score-Based CSI Generation and Denoising

TL;DR

This paper introduces a novel GNN-based framework with score-based generative models to improve hybrid beamforming in wireless systems by generating and denoising high-resolution CSI under imperfect conditions.

Contribution

It proposes a new GNN architecture and a score-based denoising model for robust CSI generation and hybrid beamforming, addressing practical CSI imperfections.

Findings

Models outperform existing methods in robustness and accuracy.

Demonstrates superior generalization across diverse datasets.

Effective in various channel error scenarios.

Abstract

Accurate Channel State Information (CSI) is critical for Hybrid Beamforming (HBF) tasks. However, obtaining high-resolution CSI remains challenging in practical wireless communication systems. To address this issue, we propose to utilize Graph Neural Networks (GNNs) and score-based generative models to enable robust HBF under imperfect CSI conditions. Firstly, we develop the Hybrid Message Graph Attention Network (HMGAT) which updates both node and edge features through node-level and edge-level message passing. Secondly, we design a Bidirectional Encoder Representations from Transformers (BERT)-based Noise Conditional Score Network (NCSN) to learn the distribution of high-resolution CSI, facilitating CSI generation and data augmentation to further improve HMGAT's performance. Finally, we present a Denoising Score Network (DSN) framework and its instantiation, termed DeBERT, which can denoise imperfect CSI under arbitrary channel error levels, thereby facilitating robust HBF. Experiments on DeepMIMO urban datasets demonstrate the proposed models' superior generalization, scalability, and robustness across various HBF tasks with perfect and imperfect CSI.