Multi-user multiple-input multiple-output (MU-MIMO) systems can be used to meet high throughput requirements of 5G and beyond networks. A base station serves many users in an uplink MU-MIMO system, leading to a substantial multi-user interference (MUI). Designing a high-performance detector for dealing with a strong MUI is challenging. This paper analyses the performance degradation caused by the posterior distribution approximation used in the state-of-the-art message passing (MP) detectors in the presence of high MUI. We develop a graph neural network based framework to fine-tune the MP detectors’ cavity distributions and thus improve the posterior distribution approximation in the MP detectors. We then propose two novel neural network based detectors which rely on the expectation propagation (EP) and Bayesian parallel interference cancellation (BPIC), referred to as the GEPNet and GPICNet detectors, respectively. The GEPNet detector maximizes detection performance, while GPICNet detector balances the performance and complexity. We provide proof of the permutation equivariance property, allowing the detectors to be trained only once, even in the systems with dynamic changes of the number of users. The simulation results show that the proposed GEPNet detector performance approaches maximum likelihood performance in various configurations and GPICNet detector doubles the multiplexing gain of BPIC detector.

中文翻译：

---

图神经网络辅助 MU-MIMO 检测器

多用户多输入多输出 (MU-MIMO) 系统可用于满足 5G 及以上网络的高吞吐量要求。一个基站在上行链路 MU-MIMO 系统中为许多用户提供服务，从而导致大量的多用户干扰 (MUI)。设计用于处理强 MUI 的高性能检测器具有挑战性。本文分析了在存在高 MUI 的情况下，最先进的消息传递 (MP) 检测器中使用的后验分布近似导致的性能下降。我们开发了一个基于图神经网络的框架来微调 MP 检测器的腔分布，从而改进 MP 检测器中的后验分布近似。然后，我们提出了两种新的基于神经网络的检测器，它们依赖于期望传播 (EP) 和贝叶斯并行干扰消除 (BPIC)，分别称为 GEPNet 和 GPICNet 检测器。GEPNet 检测器最大限度地提高了检测性能，而 GPICNet 检测器平衡了性能和复杂性。我们提供了置换等方差性质的证明，即使在用户数量动态变化的系统中，也允许检测器只训练一次。仿真结果表明，所提出的 GEPNet 检测器性能在各种配置下都接近最大似然性能，并且 GPICNet 检测器使 BPIC 检测器的复用增益增加了一倍。而 GPICNet 检测器平衡了性能和复杂性。我们提供了置换等方差性质的证明，即使在用户数量动态变化的系统中，也允许检测器只训练一次。仿真结果表明，所提出的 GEPNet 检测器性能在各种配置下都接近最大似然性能，并且 GPICNet 检测器使 BPIC 检测器的复用增益增加了一倍。而 GPICNet 检测器平衡了性能和复杂性。我们提供了置换等方差性质的证明，即使在用户数量动态变化的系统中，也允许检测器只训练一次。仿真结果表明，所提出的 GEPNet 检测器性能在各种配置下都接近最大似然性能，并且 GPICNet 检测器使 BPIC 检测器的复用增益增加了一倍。