Topological Regularization for Graph Neural Networks Augmentation

Abstract

The complexity and non-Euclidean structure of graph data hinder the development of data augmentation methods similar to those in computer vision. In this paper, we propose a feature augmentation method for graph nodes based on topological regularization, in which topological structure information is introduced into end-to-end model. Specifically, we first obtain topology embedding of nodes through unsupervised representation learning method based on random walk. Then, the topological embedding as additional features and the original node features are input into a dual graph neural network for propagation, and two different high-order neighborhood representations of nodes are obtained. On this basis, we propose a regularization technique to bridge the differences between the two different node representations, eliminate the adverse effects caused by the topological features of graphs directly used, and greatly improve the performance. We have carried out extensive experiments on a large number of datasets to prove the effectiveness of our model.

arXiv comment20 pages, 5 figures

References in corpus (7)

• Unsupervised Data Augmentation for Consistency Training
• DeepInf: Social Influence Prediction with Deep Learning
• Towards Deeper Graph Neural Networks
• Simple and Deep Graph Convolutional Networks
• Efficient Probabilistic Logic Reasoning with Graph Neural Networks
• AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
• Topological based classification using graph convolutional networks