发表机构
Centre for Wireless Communications, University of Oulu; School of Electrical, Computer, and Energy Engineering, Arizona State University（奥卢大学无线通信中心; 亚利桑那州立大学电气、计算机与能源工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对毫米波无小区大规模MIMO系统波束成形需完整毫米波CSI导致训练开销大的问题，提出基于Sub-6 GHz CSI的图神经网络波束成形方法，其总速率性能优于或接近经典基线。
AI 中文摘要
毫米波（mmWave）无小区大规模多输入多输出（CFmMIMO）系统中的波束成形方法需要准确的信道状态信息（CSI），而获取该CSI会产生显著的训练开销。本文表明，可利用图神经网络（GNN）从Sub-6 GHz CSI中有效学习全数字无小区mmWave波束成形。具体而言，我们将CFmMIMO系统表示为无线图，并训练GNN基于可用的Sub-6 GHz CSI近似最大化下行链路总速率的波束成形器。提出了一种消息传递机制，以捕获不同网络拓扑下的用户间干扰和基站间协作。仿真结果表明，所提出的Sub-6 GHz辅助GNN波束成形器与依赖完整mmWave CSI的经典基线相比，总速率性能具有竞争力且通常更优。
英文摘要
Beamforming methods in millimeter-wave (mmWave) cell-free massive multiple-input multiple-output (CFmMIMO) systems require accurate channel state information (CSI), whose acquisition entails significant training overhead. This paper shows that fully digital cell-free mmWave beamforming can be effectively learned from sub-6 GHz CSI using a graph neural network (GNN). Specifically, we represent a CFmMIMO system as a wireless graph, and the GNN is trained to approximate beamformers that maximize the downlink sum-rate based on the available sub-6 GHz CSI. A message-passing mechanism is proposed to capture inter-user interference and inter-base-station cooperation across different network topologies. Simulation results demonstrate that the proposed sub-6 GHz-assisted GNN-based beamformer achieves competitive and often superior sum-rate performance compared to classical baselines that rely on full mmWave CSI.
Comments5 pages, 3 figures, Accepted for presentation at the 2026 IEEE 27th International Workshop on Signal Processing and Artificial Intelligence in Wireless Communications (IEEE SPAWC 2026)
