Classification of vertices on social networks by multiple approaches

TL;DR

This paper compares multiple approaches for classifying vertices in social networks, emphasizing the effectiveness of graph neural networks versus traditional methods and analyzing their computational trade-offs.

Contribution

It evaluates the performance of graph neural networks against non-neural approaches for vertex classification using various social network datasets.

Findings

Graph neural networks outperform traditional methods in accuracy.

Non-neural approaches are faster and more cost-effective.

Graph neural networks have potential for further improvement.

Abstract

Due to the advent of the expressions of data other than tabular formats, the topological compositions which make samples interrelated came into prominence. Analogically, those networks can be interpreted as social connections, dataflow maps, citation influence graphs, protein bindings, etc. However, in the case of social networks, it is highly crucial to evaluate the labels of discrete communities. The reason underneath for such a study is the non-negligible importance of analyzing graph networks to partition the vertices by using the topological features of network graphs, solely. For each of these interaction-based entities, a social graph, a mailing dataset, and two citation sets are selected as the testbench repositories. This paper, it was not only assessed the most valuable method but also determined how graph neural networks work and the need to improve against non-neural network approaches which are faster and computationally cost-effective. Also, this paper showed a limit to be excesses by prospective graph neural network variations by using the topological features of networks trialed.