Spectral-based Graph Convolutional Network for Directed Graphs
This work addresses a limitation in graph neural networks for directed graphs, which is important for domains like social networks or citation networks, but it is incremental as it builds on existing spectral-based GCNs.
The paper tackles the problem that spectral-based graph convolutional networks (GCNs) cannot directly handle directed graphs by proposing an improved model using redefined Laplacians, and it demonstrates state-of-the-art performance in semi-supervised node classification tasks on directed graph datasets.
Graph convolutional networks(GCNs) have become the most popular approaches for graph data in these days because of their powerful ability to extract features from graph. GCNs approaches are divided into two categories, spectral-based and spatial-based. As the earliest convolutional networks for graph data, spectral-based GCNs have achieved impressive results in many graph related analytics tasks. However, spectral-based models cannot directly work on directed graphs. In this paper, we propose an improved spectral-based GCN for the directed graph by leveraging redefined Laplacians to improve its propagation model. Our approach can work directly on directed graph data in semi-supervised nodes classification tasks. Experiments on a number of directed graph datasets demonstrate that our approach outperforms the state-of-the-art methods.