Power Grid Knowledge Graph Completion with Complex Structure Learning.

In recent years, the knowledge graph has become a commonly used storage way for large-scale knowledge in the power grid. It has proved to have an excellent performance which helps people get specialized knowledge easier. However, generating new knowledge automatically in the incomplete knowledge graph is still an urgent problem to be resolved, which name is knowledge graph completion. Previous works do not pay enough attention to the structural information in the power grid knowledge graph, resulting in poor performance. In this paper, we propose a novel framework called Complex Structure Entropy Network (CSEN) to conduct multi-hop reasoning over a power grid knowledge graph with novel two-stage cognitive theory and von Neumann graph entropy. The paper evaluates the model on the power grid defects dataset in the link prediction task and shows the effectiveness of the proposed method compared to a variety of baselines.