Graph Convolutional Networks: analysis, improvements and results

TL;DR

This paper enhances graph convolutional networks with four improvements, leading to better performance and efficiency on benchmark datasets, including state-of-the-art results on one dataset.

Contribution

The paper introduces four novel enhancements to existing graph convolutional networks, improving their accuracy and computational efficiency.

Findings

Achieved state-of-the-art results on one benchmark dataset.

Reduced computational cost compared to competitors.

Provided competitive results on three other datasets.

Abstract

In the current era of neural networks and big data, higher dimensional data is processed for automation of different application areas. Graphs represent a complex data organization in which dependencies between more than one object or activity occur. Due to the high dimensionality, this data creates challenges for machine learning algorithms. Graph convolutional networks were introduced to utilize the convolutional models concepts that shows good results. In this context, we enhanced two of the existing Graph convolutional network models by proposing four enhancements. These changes includes: hyper parameters optimization, convex combination of activation functions, topological information enrichment through clustering coefficients measure, and structural redesign of the network through addition of dense layers. We present extensive results on four state-of-art benchmark datasets. The performance is notable not only in terms of lesser computational cost compared to competitors, but also achieved competitive results for three of the datasets and state-of-the-art for the fourth dataset.