SDGNN: Learning Node Representation for Signed Directed Networks
This work provides a novel GNN model for learning node representations in signed directed networks, which are common in real-world scenarios but less studied, offering improved performance for researchers and practitioners working with such complex network structures.
This paper addresses the challenge of learning node representations in signed directed networks, which contain both positive and negative links with directions. The authors propose SDGNN, a novel Graph Neural Network model, which reconstructs link signs, link directions, and signed directed triangles, outperforming existing models on five real-world benchmark datasets.
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.