Continuous-Time Dynamic Network Embeddings

TLDR

Networks evolve continuously, yet most network representation learning focuses on static snapshots and ignores temporal dynamics. The authors propose a general framework to incorporate temporal information into network embedding methods. The framework yields methods for learning time‑respecting embeddings from continuous‑time dynamic networks. Experiments show the framework improves performance by an average of 11.9% across methods and graphs, confirming that modeling temporal dependencies yields more meaningful representations.

Abstract

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Although many networks contain this type of temporal information, the majority of research in network representation learning has focused on static snapshots of the graph and has largely ignored the temporal dynamics of the network. In this work, we describe a general framework for incorporating temporal information into network embedding methods. The framework gives rise to methods for learning time-respecting embeddings from continuous-time dynamic networks. Overall, the experiments demonstrate the effectiveness of the proposed framework and dynamic network embedding approach as it achieves an average gain of 11.9% across all methods and graphs. The results indicate that modeling temporal dependencies in graphs is important for learning appropriate and meaningful network representations.