Graph Neural Network-based End-to-End Learning for Multi-User MIMO Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Hao, Vo, Hoang Triet, Kosasih, Alva, Vucetic, Branka, Hardjawana, Wibowo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911455725486080
author Chang, Hao
Vo, Hoang Triet
Kosasih, Alva
Vucetic, Branka
Hardjawana, Wibowo
author_facet Chang, Hao
Vo, Hoang Triet
Kosasih, Alva
Vucetic, Branka
Hardjawana, Wibowo
contents End-to-end (E2E) learning has recently been proposed to jointly design the modulator and symbol detector by using deep neural networks (DNNs). However, existing schemes lack sufficient capability to cancel multi-user interference (MUI) in uplink multi-user multiple-input multiple-output (MU-MIMO) systems. In this paper, we propose a graph neural network (GNN)-based E2E learning scheme that employs a GNN-based modulator to generate learned constellation points, and a GNN-based detector to cancel MUI. They are jointly optimized to minimize the symbol error rate (SER) performance loss. Simulation results demonstrate that the proposed E2E outperforms existing schemes with a predefined modulator. Specifically, it achieves an approximate 2 dB gain in a high MUI environment and surpasses even the maximum-likelihood (ML) detector in a low MUI condition.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16112
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Neural Network-based End-to-End Learning for Multi-User MIMO Systems
Chang, Hao
Vo, Hoang Triet
Kosasih, Alva
Vucetic, Branka
Hardjawana, Wibowo
Signal Processing
End-to-end (E2E) learning has recently been proposed to jointly design the modulator and symbol detector by using deep neural networks (DNNs). However, existing schemes lack sufficient capability to cancel multi-user interference (MUI) in uplink multi-user multiple-input multiple-output (MU-MIMO) systems. In this paper, we propose a graph neural network (GNN)-based E2E learning scheme that employs a GNN-based modulator to generate learned constellation points, and a GNN-based detector to cancel MUI. They are jointly optimized to minimize the symbol error rate (SER) performance loss. Simulation results demonstrate that the proposed E2E outperforms existing schemes with a predefined modulator. Specifically, it achieves an approximate 2 dB gain in a high MUI environment and surpasses even the maximum-likelihood (ML) detector in a low MUI condition.
title Graph Neural Network-based End-to-End Learning for Multi-User MIMO Systems
topic Signal Processing
url https://arxiv.org/abs/2411.16112