Graph Convolutional Networks: analysis, improvements and results
This work addresses the problem of efficiently learning from complex graph data for applications in machine learning, though it is incremental as it builds on existing models.
The authors tackled the challenge of processing high-dimensional graph data by enhancing two existing Graph Convolutional Network models with four improvements, achieving competitive results on three benchmark datasets and state-of-the-art performance on a fourth dataset with reduced computational cost.
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.