Graph Neural Networks for Massive MIMO Detection
This work addresses a domain-specific problem in wireless communication, offering an incremental improvement over existing methods like belief propagation and MMSE.
The paper tackles the problem of massive MIMO detection in wireless communication by using graph neural networks (GNNs) to learn a message-passing solution, resulting in performance that outperforms the MMSE baseline detector under a uniform prior assumption.
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.