Quadratic GCN for Graph Classification
This work addresses the accuracy limitations in graph classification for machine learning applications, presenting an incremental improvement over existing GCN-based methods.
The authors tackled the problem of limited accuracy in graph classification tasks (GCT) using Graph Convolutional Networks (GCNs) by proposing Quadratic GCN (QGCN), which combines GCN with knowledge graph methods and a self-regularized activation function, resulting in outperforming state-of-the-art methods across all tested tasks.
Graph Convolutional Networks (GCNs) have been extensively used to classify vertices in graphs and have been shown to outperform other vertex classification methods. GCNs have been extended to graph classification tasks (GCT). In GCT, graphs with different numbers of edges and vertices belong to different classes, and one attempts to predict the graph class. GCN based GCT have mostly used pooling and attention-based models. The accuracy of existing GCT methods is still limited. We here propose a novel solution combining GCN, methods from knowledge graphs, and a new self-regularized activation function to significantly improve the accuracy of the GCN based GCT. We present quadratic GCN (QGCN) - A GCN formalism with a quadratic layer. Such a layer produces an output with fixed dimensions, independent of the graph vertex number. We applied this method to a wide range of graph classification problems, and show that when using a self regularized activation function, QGCN outperforms the state of the art methods for all graph classification tasks tested with or without external input on each graph. The code for QGCN is available at: https://github.com/Unknown-Data/QGCN .