GRAPH NEURAL NETWORKS FOR LINK PREDICTION IN DYNAMIC KNOWLEDGE GRAPHS

Dynamic knowledge graphs, which capture evolving relationships among entities over time, are becoming increasingly important in various domains such as social networks, recommendation systems, finance domain and biomedical research. This research paper investigates the effectiveness of Graph Neural Networks (GNNs) for link prediction in dynamic knowledge graphs. By leveraging the temporal dynamics of the graph, we propose novel GNN architectures and evaluate their performance against state-of-the-art methods on real-world datasets. The results demonstrate the capability of GNNs to effectively capture evolving relationships and make accurate predictions in dynamic knowledge graphs, providing valuable insights for applications in various domains.