Multidimensional graph neural networks for wireless communications
Graph neural networks (GNNs) can improve the efficiency of learning wireless policies by
leveraging their permutation properties and topology prior. While mismatched permutation …
leveraging their permutation properties and topology prior. While mismatched permutation …
Meta-Learning for Wireless Communications: A Survey and a Comparison to GNNs
Deep learning has been used for optimizing a multitude of wireless problems. Yet most
existing works assume that training and test samples are drawn from the same distribution …
existing works assume that training and test samples are drawn from the same distribution …
Learning resource allocation policy: Vertex-GNN or edge-GNN?
Y Peng, J Guo, C Yang - IEEE Transactions on Machine …, 2024 - ieeexplore.ieee.org
Graph neural networks (GNNs) update the hidden representations of vertices (called Vertex-
GNNs) or hidden representations of edges (called Edge-GNNs) by processing and pooling …
GNNs) or hidden representations of edges (called Edge-GNNs) by processing and pooling …
Understanding the performance of learning precoding policy with GNN and CNNs
Learning-based precoding has been shown able to be implemented in real-time, jointly
optimized with channel acquisition, and robust to imperfect channels. Yet previous works …
optimized with channel acquisition, and robust to imperfect channels. Yet previous works …
Deep neural networks with data rate model: Learning power allocation efficiently
J Guo, C Yang - IEEE Transactions on Communications, 2023 - ieeexplore.ieee.org
Learning-based resource allocation can be implemented in real-time, but deep neural
networks (DNNs) developed in other fields such as computer vision are with high training …
networks (DNNs) developed in other fields such as computer vision are with high training …
How to improve learning efficiency of GNN for precoding?
J Guo, C Yang - 2023 IEEE 97th Vehicular Technology …, 2023 - ieeexplore.ieee.org
Learning precoding with deep neural networks (DNNs) enables real-time implementation
and robustness to imperfect channels. However, existing DNNs for learning precoding suffer …
and robustness to imperfect channels. However, existing DNNs for learning precoding suffer …
On the size generalizibility of graph neural networks for learning resource allocation
J Wu, C Sun, C Yang - Science China Information Sciences, 2024 - Springer
Size generalization is important for learning resource allocation policies in wireless systems
with time-varying scales. If a neural network for learning a wireless policy is not …
with time-varying scales. If a neural network for learning a wireless policy is not …
Learning hybrid precoding efficiently for mmWave systems with mathematical properties
Hybrid precoding in millimeter wave systems can support high spectral efficiency with
affordable cost. With deep learning, fairly good solutions that are robust to imperfect chan …
affordable cost. With deep learning, fairly good solutions that are robust to imperfect chan …
Understanding the Performance of Learning Precoding Policies with Graph and Convolutional Neural Networks
Learning-based precoding has been shown able to be implemented in real-time, jointly
optimized with channel acquisition, and robust to imperfect channels. Nonetheless, existing …
optimized with channel acquisition, and robust to imperfect channels. Nonetheless, existing …
Self-supervised learning of linear precoders under non-linear PA distortion for energy-efficient massive MIMO systems
Massive multiple input multiple output (MIMO) systems are typically designed under the
assumption of linear power amplifiers (PAs). However, PAs are typically most energy …
assumption of linear power amplifiers (PAs). However, PAs are typically most energy …