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

2025-11-10

AI Summary

Hybrid beamforming (HBF) suffers from insufficient robustness under imperfect channel state information (CSI), particularly in practical wireless systems. Method: This paper proposes a joint CSI recovery and beamforming framework leveraging graph neural networks (GNNs) and score-based generative models. Specifically, it introduces a hierarchical multi-hop graph attention network (HMGAT) to model the base station–user topological relationships; incorporates a BERT-inspired architecture to capture CSI statistical distributions; and constructs a noise-conditional score network (NCSN) coupled with a denoising score network (DSN) for CSI enhancement and denoising across arbitrary error levels. Contribution/Results: Evaluated on the DeepMIMO urban dataset, the proposed framework significantly improves HBF robustness, generalizability, and scalability under challenging conditions—including low signal-to-noise ratios and high user mobility—thereby establishing a novel paradigm for CSI-constrained beamforming in real-world wireless systems.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Generating high-resolution CSI for hybrid beamforming systems
• Denoising imperfect CSI under arbitrary channel error levels
• Enabling robust hybrid beamforming under imperfect CSI conditions

Innovation

• GNN-based Hybrid Message Graph Attention Network for beamforming
• BERT-enhanced score network for CSI generation and augmentation
• Denoising Score Network framework for robust channel estimation