Spectral-based Graph Convolutional Network for Directed Graphs

TL;DR

This paper introduces an improved spectral-based graph convolutional network that effectively handles directed graphs by redefining Laplacians, enabling better semi-supervised node classification performance.

Contribution

The paper proposes a novel spectral-based GCN model that directly operates on directed graphs using redefined Laplacians, advancing graph neural network capabilities.

Findings

Outperforms state-of-the-art methods on directed graph datasets

Effective for semi-supervised node classification

Works directly on directed graphs without modifications

Abstract

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.