Learning State-Augmented Policies for Information Routing in Communication Networks

TL;DR

This paper introduces a novel state augmentation strategy using graph neural networks to optimize information routing in large-scale communication networks, leveraging local information and unsupervised learning for improved performance.

Contribution

The paper proposes a new state augmentation approach with GNNs for efficient, local-information-based routing in communication networks, validated on real network topologies.

Findings

Enhanced routing performance compared to baseline algorithms

Effective use of local information for global routing optimization

Successful validation on real-time network topologies

Abstract

This paper examines the problem of information routing in a large-scale communication network, which can be formulated as a constrained statistical learning problem having access to only local information. We delineate a novel State Augmentation (SA) strategy to maximize the aggregate information at source nodes using graph neural network (GNN) architectures, by deploying graph convolutions over the topological links of the communication network. The proposed technique leverages only the local information available at each node and efficiently routes desired information to the destination nodes. We leverage an unsupervised learning procedure to convert the output of the GNN architecture to optimal information routing strategies. In the experiments, we perform the evaluation on real-time network topologies to validate our algorithms. Numerical simulations depict the improved performance of the proposed method in training a GNN parameterization as compared to baseline algorithms.