Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks

By Mark Eisen, Alejandro Ribeiro. IEEE Transactions on Signal Processing, 2019

317 citations recorded by the source corpus.

We consider the problem of optimally allocating resources across a set of transmitters and receivers in a wireless network. The resulting optimization problem takes the form of constrained statistical learning, in which solutions can be found in a model-free manner by parameterizing the resource allocation policy. Convolutional neural networks architectures are an attractive option for parameterization, as their dimensionality is small and does not scale with network size. We introduce the random edge graph neural network (REGNN), which performs convolutions over random graphs formed by the fading interference patterns in the wireless network. The REGNN-based allocation policies are shown to retain an important permutation equivariance property that makes them amenable to transference to different networks. We further present an unsupervised model-free primal-dual learning algorithm to train the weights of the REGNN. Through numerical simulations, we demonstrate the strong performance REGNNs obtain relative to heuristic benchmarks and their transference capabilities.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/daec3877d99e4183d74245571f07bff9ec3a15c7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Electrical and Electronic Engineering

Citations in the corpus

Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis (2020, methodology): “cannot be solved by existing methods in [10], [13], [14].”
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications (2021, background): “…been shown to be able to harness the beneﬁts of generalizability, interpretability, robustness, scalability, superior performance, real-time and distributed implementation for learning to optimize nonconvex problems, including power control [270], beamforming [23], and phase shift design [25].”
A Tutorial on Ultrareliable and Low-Latency Communications in 6G: Integrating Domain Knowledge Into Deep Learning (2021, methodology): “The details on the model-free unsupervised deep learning method can be found in [63], [232], [233], and [242].”
Optimal Power Flow Using Graph Neural Networks (2019, background): “In particular, we focus on graph neural networks (GNNs) [13–15] to exploit their stability properties [21] that guarantee scalability [22, 23].”