Topological based classification of paper domains using graph convolutional networks
This addresses the problem of classifying academic papers in citation networks without relying on text, which could benefit domains with limited content data.
The paper tackles node classification in graphs by combining topological features with information propagation using Graph Convolutional Networks, achieving results nearly as good as text-based methods on CiteSeer and Cora datasets without using textual content.
The main approaches for node classification in graphs are information propagation and the association of the class of the node with external information. State of the art methods merge these approaches through Graph Convolutional Networks. We here use the association of topological features of the nodes with their class to predict this class. Moreover, combining topological information with information propagation improves classification accuracy on the standard CiteSeer and Cora paper classification task. Topological features and information propagation produce results almost as good as text-based classification, without no textual or content information. We propose to represent the topology and information propagation through a GCN with the neighboring training node classification as an input and the current node classification as output. Such a formalism outperforms state of the art methods.