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 2007.05703eess.SPcs.LG
收藏

基于图神经网络的大规模多输入多输出检测

Graph Neural Networks for Massive MIMO Detection

KTH Royal Institute of Technology(瑞典皇家理工学院);Huawei Technologies Sweden AB(华为技术(瑞典)有限公司)

Andrea Scotti, Nima N. Moghadam, Dong Liu, Karl Gafvert, Jinliang Huang

摘要:

在本文中,我们创新地使用图神经网络(GNNs)学习的消息传递解决方案的推理任务的大规模多个多输入多输出(MIMO)检测在无线通信。我们采用了一个图形模型的基础上的马尔可夫随机场(MRF)的信念传播(BP)产生不良的结果时,它假设一个统一的先验传输的符号。数值仿真结果表明,在一致先验假设下,与BP算法相比,基于GNN的MIMO检测算法性能优于基于最小均方误差(MMSE)的基线检测算法.此外,实验表明,该算法的性能略有改善,通过将MMSE信息纳入先验。

英文摘要:

In this paper, we innovately use graph neural networks (GNNs) to learn a message-passing solution for the inference task of massive multiple multiple-input multiple-output (MIMO) detection in wireless communication. We adopt a graphical model based on the Markov random field (MRF) where belief propagation (BP) yields poor results when it assumes a uniform prior over the transmitted symbols. Numerical simulations show that, under the uniform prior assumption, our GNN-based MIMO detection solution outperforms the minimum mean-squared error (MMSE) baseline detector, in contrast to BP. Furthermore, experiments demonstrate that the performance of the algorithm slightly improves by incorporating MMSE information into the prior.

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。

↑