Fast Sequence Based Embedding with Diffusion Graphs

A graph embedding is a representation of the vertices of a graph in a low dimensional space, which approximately preserves properties such as distances between nodes. Vertex sequence based embedding procedures use features extracted from linear sequences of vertices to create embeddings using a neural network. In this paper, we propose diusion graphs as a method to rapidly generate vertex sequences for network embedding. Its computational eciency is superior to previous methods due to simpler sequence generation, and it produces more accurate results. In experiments, we found that the performance relative to other methods improves with increasing edge density in the graph. In a community detection task, clustering nodes in the embedding space produces better results compared to other sequence based embedding methods.