@inproceedings{97b5233e10a1411c891101778010cbba,
title = "Scalable Multi-User Precoding and Pilot Optimization with Graph Neural Networks",
abstract = "We consider the problem of sum rate maximization in frequency division duplex (FDD) systems when only imperfect channel state information (CSI) is available. Inspired by the low complexity and generalization ability offered by graph neural networks (GNNs), we propose an end-to-end (E2E) framework for both, precoding and downlink (DL) pilot sequences optimization based on the novel Edge-graph attention network (GAT). The simulation results confirm the potential of the proposed E2E approach to optimize sum rates and its scalability in scenarios with varying numbers of users. Additionally, the superiority of the learned pilot matrix compared to the conventionally employed sub-discrete Fourier transform (DFT) matrix is highlighted.",
keywords = "Attention mechanism, FDD systems, graph neural networks, multi-user precoding, pilot optimization",
author = "Valentina Rizzello and Amor, \{Donia Ben\} and Michael Joham and Wolfgang Utschick",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 59th Annual IEEE International Conference on Communications, ICC 2024 ; Conference date: 09-06-2024 Through 13-06-2024",
year = "2024",
doi = "10.1109/ICC51166.2024.10622529",
language = "English",
series = "IEEE International Conference on Communications",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2956--2961",
editor = "Matthew Valenti and David Reed and Melissa Torres",
booktitle = "ICC 2024 - IEEE International Conference on Communications",
}