Online Dynamic Network Embedding
This work addresses the challenge of dynamic network embedding for researchers and practitioners dealing with evolving or temporal graph data, representing an incremental improvement over existing static methods.
The authors tackled the problem of embedding dynamic networks, which change over time, by proposing the Recurrent Neural Network Embedding (RNNE) algorithm that uses virtual nodes to handle varying network sizes and incorporates both local and global structural information. The results show that RNNE outperforms state-of-the-art methods in reconstruction, classification, and link prediction tasks on five networks.
Network embedding is a very important method for network data. However, most of the algorithms can only deal with static networks. In this paper, we propose an algorithm Recurrent Neural Network Embedding (RNNE) to deal with dynamic network, which can be typically divided into two categories: a) topologically evolving graphs whose nodes and edges will increase (decrease) over time; b) temporal graphs whose edges contain time information. In order to handle the changing size of dynamic networks, RNNE adds virtual node, which is not connected to any other nodes, to the networks and replaces it when new node arrives, so that the network size can be unified at different time. On the one hand, RNNE pays attention to the direct links between nodes and the similarity between the neighborhood structures of two nodes, trying to preserve the local and global network structure. On the other hand, RNNE reduces the influence of noise by transferring the previous embedding information. Therefore, RNNE can take into account both static and dynamic characteristics of the network.We evaluate RNNE on five networks and compare with several state-of-the-art algorithms. The results demonstrate that RNNE has advantages over other algorithms in reconstruction, classification and link predictions.