Unsupervised Dynamic Network Embedding Using Global Information

Network embedding has become a fascinating research subject in recent years owing to its ability to represent networks with rich relationships in the low-dimensional vector space, which inspires various downstream tasks, such as link prediction and node classification. Nevertheless, most existing network embedding methods focus on static networks where nodes and edges do not evolve with time. Although some methods consider the dynamics of networks, they pay little attention to the global information of networks, or have recourse to node labels for training. In this paper, we propose an unsupervised dynamic network embedding using the global information, called UDNGI. More specifically, we first maximize the mutual information between the local node embedding and the global network embedding based on a well-designed graph convolutional network for capturing the global information at a time-step specific snapshot network. Then, a temporal smoothness constraint is proposed to minimize the embedding deviation between two successive snapshots, and a modified long short-term memory is designed to update the weight parameters of the graph convolutional network, which enables the model to capture the global information across all time steps. Extensive experiments on node classification and link prediction demonstrate that UDNGI achieves a generally better performance than state-of-the-art methods.