Tiny Graph Neural Networks for Radio Resource Management

TL;DR

This paper introduces a low-rank approximation-based Graph Neural Network architecture for radio resource management, achieving significant reductions in model size and parameters with minimal performance loss.

Contribution

The novel Low Rank Message Passing Graph Neural Network (LR-MPGNN) architecture reduces model size and parameters using low-rank techniques, maintaining robustness in radio resource management tasks.

Findings

60-fold decrease in model size

Up to 98% reduction in parameters

Only 2% performance decrease in weighted sum rate

Abstract

The surge in demand for efficient radio resource management has necessitated the development of sophisticated yet compact neural network architectures. In this paper, we introduce a novel approach to Graph Neural Networks (GNNs) tailored for radio resource management by presenting a new architecture: the Low Rank Message Passing Graph Neural Network (LR-MPGNN). The cornerstone of LR-MPGNN is the implementation of a low-rank approximation technique that substitutes the conventional linear layers with their low-rank counterparts. This innovative design significantly reduces the model size and the number of parameters. We evaluate the performance of the proposed LR-MPGNN model based on several key metrics: model size, number of parameters, weighted sum rate of the communication system, and the distribution of eigenvalues of weight matrices. Our extensive evaluations demonstrate that the LR-MPGNN model achieves a sixtyfold decrease in model size, and the number of model parameters can be reduced by up to 98%. Performance-wise, the LR-MPGNN demonstrates robustness with a marginal 2% reduction in the best-case scenario in the normalized weighted sum rate compared to the original MPGNN model. Additionally, the distribution of eigenvalues of the weight matrices in the LR-MPGNN model is more uniform and spans a wider range, suggesting a strategic redistribution of weights.