Dynamic Graph Link Prediction by Semantic Evolution

Abstract

Dynamic graph link prediction has attracted increasing attention in various fields such as social networks, paper citation networks and knowledge graphs. Many models have been developed to predict the future graph structure. In this paper, we propose a link prediction model with semantic evolution (LISE), to predict links in a sequence of graph over time. Our approach is based on the discovery of non-random initialization dynamic word embedding which is a kind of method to study semantic evolution. It can help us train node embedding in the same space and introduce temporal context into the embedding training of nodes. Based on node embedding in the same space, LISE can unify historical behavior, graph snapshots structure information and dynamic attributes into a frame. We evaluate our proposed method and various comparing methods on two real-world datasets. The experimental results prove the effectiveness of the link prediction made by LISE model.