Topological based classification using graph convolutional networks

TL;DR

This paper explores how topological features of nodes in graphs can enhance graph convolutional networks (GCN) performance, showing that incorporating topology improves accuracy beyond existing methods, especially with distant node connections.

Contribution

The study demonstrates that explicitly adding topological features and distant node connections to GCNs significantly boosts classification accuracy, surpassing current state-of-the-art methods.

Findings

Topological features alone can predict node classes with high accuracy.

Adding distant node connections based on topology improves GCN performance.

Topology-based methods outperform existing state-of-the-art in multiple datasets.

Abstract

In colored graphs, node classes are often associated with either their neighbors class or with information not incorporated in the graph associated with each node. We here propose that node classes are also associated with topological features of the nodes. We use this association to improve Graph machine learning in general and specifically, Graph Convolutional Networks (GCN). First, we show that even in the absence of any external information on nodes, a good accuracy can be obtained on the prediction of the node class using either topological features, or using the neighbors class as an input to a GCN. This accuracy is slightly less than the one that can be obtained using content based GCN. Secondly, we show that explicitly adding the topology as an input to the GCN does not improve the accuracy when combined with external information on nodes. However, adding an additional adjacency matrix with edges between distant nodes with similar topology to the GCN does significantly improve its accuracy, leading to results better than all state of the art methods in multiple datasets.