Fast Power Control Adaptation via Meta-Learning for Random Edge Graph Neural Networks

TL;DR

This paper introduces a meta-learning approach to enable rapid adaptation of power control policies in decentralized wireless networks using graph neural networks, specifically REGNN, to handle time-varying topologies efficiently.

Contribution

It proposes a meta-learning framework for fast adaptation of REGNN-based power control policies across different network topologies, improving flexibility and responsiveness.

Findings

Meta-learning enhances quick adaptation to new network configurations.

REGNN effectively models power control in arbitrary interference graphs.

The approach reduces the need for extensive retraining in dynamic environments.

Abstract

Power control in decentralized wireless networks poses a complex stochastic optimization problem when formulated as the maximization of the average sum rate for arbitrary interference graphs. Recent work has introduced data-driven design methods that leverage graph neural network (GNN) to efficiently parametrize the power control policy mapping channel state information (CSI) to the power vector. The specific GNN architecture, known as random edge GNN (REGNN), defines a non-linear graph convolutional architecture whose spatial weights are tied to the channel coefficients, enabling a direct adaption to channel conditions. This paper studies the higher-level problem of enabling fast adaption of the power control policy to time-varying topologies. To this end, we apply first-order meta-learning on data from multiple topologies with the aim of optimizing for a few-shot adaptation to new network configurations.