Scaling Graph-based Deep Learning models to larger networks

TL;DR

This paper addresses the challenge of scaling Graph Neural Networks for larger networks, proposing a solution that maintains prediction accuracy as network size and complexity increase.

Contribution

It introduces a GNN-based approach specifically designed to scale effectively to larger, more complex networks with higher link capacities and aggregated traffic.

Findings

The proposed GNN approach scales to larger networks effectively.

It maintains prediction accuracy with increased network size.

The method demonstrates improved generalization to unseen, larger networks.

Abstract

Graph Neural Networks (GNN) have shown a strong potential to be integrated into commercial products for network control and management. Early works using GNN have demonstrated an unprecedented capability to learn from different network characteristics that are fundamentally represented as graphs, such as the topology, the routing configuration, or the traffic that flows along a series of nodes in the network. In contrast to previous solutions based on Machine Learning (ML), GNN enables to produce accurate predictions even in other networks unseen during the training phase. Nowadays, GNN is a hot topic in the Machine Learning field and, as such, we are witnessing great efforts to leverage its potential in many different fields (e.g., chemistry, physics, social networks). In this context, the Graph Neural Networking challenge 2021 brings a practical limitation of existing GNN-based solutions for networking: the lack of generalization to larger networks. This paper approaches the scalability problem by presenting a GNN-based solution that can effectively scale to larger networks including higher link capacities and aggregated traffic on links.