Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis

Abstract

Deep learning has recently emerged as a disruptive technology to solve challenging radio resource management problems in wireless networks. However, the neural network architectures adopted by existing works suffer from poor scalability, generalization, and lack of interpretability. A long-standing approach to improve scalability and generalization is to incorporate the structures of the target task into the neural network architecture. In this paper, we propose to apply graph neural networks (GNNs) to solve large-scale radio resource management problems, supported by effective neural network architecture design and theoretical analysis. Specifically, we first demonstrate that radio resource management problems can be formulated as graph optimization problems that enjoy a universal permutation equivariance property. We then identify a class of neural networks, named \emph{message passing graph neural networks} (MPGNNs). It is demonstrated that they not only satisfy the permutation equivariance property, but also can generalize to large-scale problems while enjoying a high computational efficiency. For interpretablity and theoretical guarantees, we prove the equivalence between MPGNNs and a class of distributed optimization algorithms, which is then used to analyze the performance and generalization of MPGNN-based methods. Extensive simulations, with power control and beamforming as two examples, will demonstrate that the proposed method, trained in an unsupervised manner with unlabeled samples, matches or even outperforms classic optimization-based algorithms without domain-specific knowledge. Remarkably, the proposed method is highly scalable and can solve the beamforming problem in an interference channel with $1000$ transceiver pairs within $6$ milliseconds on a single GPU.

Accepted by IEEE Journal on Selected Areas in Communications - Series on Machine Learning for Communications and Networks

References in corpus (12)

• Fast Graph Representation Learning with PyTorch Geometric
• Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
• Optimal Multiuser Transmit Beamforming: A Difficult Problem with a Simple Solution Structure
• A Deep Learning Framework for Optimization of MISO Downlink Beamforming
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
• Spatial Deep Learning for Wireless Scheduling
• Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
• Differentiable Convex Optimization Layers
• Equivariance Through Parameter-Sharing
• What Can Neural Networks Reason About?
• RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection