MHDNE: Network Embedding Based on Multivariate Hawkes Process

With the evolution of the network, the interactions among nodes in networks make networks exhibit dynamic properties. Mining the rich information behind dynamic networks is of great importance for network analysis. However, most of the existing network embedding methods focus on static networks which ignore the dynamic properties of networks. In this paper, we propose a novel approach MHDNE (Multivariate hawkes process network embedding) to learn the representations of nodes in dynamic networks. The key idea of our approach is to integrate the historical edge information as well as network evolution properties into the formation process of edges based on Hawkes process. By integrating the multivariate Hawkes process into network embedding, MHDNE resolves the issue that the existing methods cannot effectively capture both of the historical information and evolution process of dynamic networks. Extensive experiments demonstrate that the embeddings learned from the proposed MHDNE model can achieve better performance than the state-of-the-art methods in downstream tasks, such as node classification and network visualization.