Directed Graph Convolutional Network

Abstract

Graph Convolutional Networks (GCNs) have been widely used due to their outstanding performance in processing graph-structured data. However, the undirected graphs limit their application scope. In this paper, we extend spectral-based graph convolution to directed graphs by using first- and second-order proximity, which can not only retain the connection properties of the directed graph, but also expand the receptive field of the convolution operation. A new GCN model, called DGCN, is then designed to learn representations on the directed graph, leveraging both the first- and second-order proximity information. We empirically show the fact that GCNs working only with DGCNs can encode more useful information from graph and help achieve better performance when generalized to other models. Moreover, extensive experiments on citation networks and co-purchase datasets demonstrate the superiority of our model against the state-of-the-art methods.

References in corpus (11)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Simplifying Graph Convolutional Networks
• Pitfalls of Graph Neural Network Evaluation
• How Powerful are Graph Neural Networks?
• Attention-based Graph Neural Network for Semi-supervised Learning
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Adaptive Graph Convolutional Neural Networks
• N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification
• Label Efficient Semi-Supervised Learning via Graph Filtering

Cited by in corpus (7)

• RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data
• Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction
• MagNet: A Neural Network for Directed Graphs
• A Network Science perspective of Graph Convolutional Networks: A survey
• Graph Neural Networks with Feature and Structure Aware Random Walk
• Asymmetric Graph Representation Learning
• Space-Time-Separable Graph Convolutional Network for Pose Forecasting