A Graph Data Augmentation Strategy with Entropy Preserving

All of these domains and many more can be readily modeled as graphs, which contain information about connection between individual units. For instance, citation graph describes interactions among science research papers which are represented as nodes with labels to indicate category, and the citation links between papers are mapped into edges. Information from single node or local dense nodes propagates along edges, and this makes graphs be useful structured knowledge repositories for machine learning tasks like link prediction and node classification. Graph Convolutional Networks (GCNs) [4, 5, 6, 7, 8] draw support from convolutional operation on graph to aggregate neighbor nodes information from low-to high-order hierarchical structures to get central node representation. In the course of time, GCNs and subsequent variants have emerged as powerful approaches for a variety of tasks like semi-supervised node classification [4, 9], which is also the main focus of this paper. In order to enable GCNs with more expressivity to wider neighbors, one may stack more layers to the network. But unfortunately, deeper layer network model fails to achieve the expectation partly due to the phenomenon of over-smoothing [10], which is an inherent issue of graph convolutional calculation mechanism. It has been proven that graph convolution operation is a type of Laplacian smoothing, thus representations of nodes in same region converge to same values and tend to be indistinguishable across different classes in embedding space as model goes deeper [11]. An easy but effective way to tackle with over-smoothing is to generate perturbed graph data for training.