arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2212.11531eess.SP
收藏

用于无线通信的多维图神经网络

Multidimensional Graph Neural Networks for Wireless Communications

Shengjie Liu, Jia Guo, Chenyang Yang

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出一种基于多维 GNN 的统一框架，通过超边表示更新和顶点标识方法学习可置换无线策略，并在预编码任务中验证其样本与参数效率。

摘要：

图神经网络（GNN）凭借其置换特性，在提升通信策略学习效率方面已展现出良好前景。然而，现有工作仅针对特定无线策略设计 GNN，缺乏一种用于图建模和结构选择的系统性方法。基于以下观察——策略置换特性不匹配以及隐藏表示更新过程中的信息损失会对学习性能和效率产生重大影响——本文提出一种统一框架，利用多维 GNN 学习可置换的无线策略。为避免信息损失，GNN 更新超边的隐藏表示。为利用策略的所有可能置换，我们提供了一种在图中标识顶点的方法。我们还研究了影响样本效率的无线信道可置换性，并展示了如何权衡 GNN 的训练、推理和设计复杂度。我们以不同系统中的预编码为例，演示如何应用该框架。仿真结果表明，所提出的 GNN 能够取得接近数值算法的性能，并且与常用的卷积神经网络相比，只需少得多的训练样本和可训练参数即可达到相同的学习性能。

英文摘要：

Graph neural networks (GNNs) have been shown promising in improving the efficiency of learning communication policies by leveraging their permutation properties. Nonetheless, existing works design GNNs only for specific wireless policies, lacking a systematical approach for modeling graph and selecting structure. Based on the observation that the mismatched permutation property from the policies and the information loss during the update of hidden representations have large impact on the learning performance and efficiency, in this paper we propose a unified framework to learn permutable wireless policies with multidimensional GNNs. To avoid the information loss, the GNNs update the hidden representations of hyper-edges. To exploit all possible permutations of a policy, we provide a method to identify vertices in a graph. We also investigate the permutability of wireless channels that affects the sample efficiency, and show how to trade off the training, inference, and designing complexities of GNNs. We take precoding in different systems as examples to demonstrate how to apply the framework. Simulation results show that the proposed GNNs can achieve close performance to numerical algorithms, and require much fewer training samples and trainable parameters to achieve the same learning performance as the commonly used convolutional neural networks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑