SDGNN: Learning Node Representation for Signed Directed Networks

Authors

  • Junjie Huang Institute of Computing Technology, Chinese Academy of Sciences
  • Huawei Shen Institute of Computing Technology, Chinese Academy of Sciences
  • Liang Hou Institute of Computing Technology, Chinese Academy of Sciences
  • Xueqi Cheng Institute of Computing Technology, Chinese Academy of Sciences

Keywords:

Social Networks, Applications

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 socio- logical 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 embeddings. Experiments demonstrate the proposed model outperforms existing models, including feature-based methods, network embedding methods, and several GNN methods.

Downloads

Published

2021-05-18

How to Cite

Huang, J., Shen, H., Hou, L., & Cheng, X. (2021). SDGNN: Learning Node Representation for Signed Directed Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 196-203. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16093

Issue

Section

AAAI Technical Track on Application Domains