SDGNN: Learning Node Representation for Signed Directed Networks

Abstract

Network embedding is aimed at mapping nodes in a network into low-dimensional vector representations. Graph Neural Networks (GNNs) have received widespread attention and lead to state-of-the-art performance in learning node representations. However, most GNNs only work in unsigned networks, where only positive links exist. It is not trivial to transfer these models to signed directed networks, which are widely observed in the real world yet less studied. In this paper, we first review two fundamental sociological theories (i.e., status theory and balance theory) and conduct empirical studies on real-world datasets to analyze the social mechanism in signed directed networks. Guided by related sociological theories, we propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks. The proposed model simultaneously reconstructs link signs, link directions, and signed directed triangles. We validate our model's effectiveness on five real-world datasets, which are commonly used as the benchmark for signed network embedding. Experiments demonstrate the proposed model outperforms existing models, including feature-based methods, network embedding methods, and several GNN methods.

arXiv commentAccepted and to appear at AAAI2021

References in corpus (8)

• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Community detection in networks with positive and negative links
• Community Interaction and Conflict on the Web
• Graph Wavelet Neural Network
• Distributed Representations of Signed Networks
• Signed Graph Convolutional Network
• Computing Lens for Exploring the Historical People's Social Network