Jiaqi Wei's paper VISION-KG: Topic-centric Visualization System for Summarizing Knowledge Graph was accepted by WSDM 2020.

　　Large scale knowledge graph (KG) has attracted wide attentions in both academia and industry recently. However, due to the complexity of SPARQL syntax and massive volume of real KG, it remains difficult for ordinary users to access KG. In this demo, we present VISION-KG, a topic-centric visualization system to help users navigate KG easily via entity summarization and entity clustering. Given a query entity, VISION-KG summarizes the induced subgraph of v’s neighbor nodes via our proposed facts ranking method that measures importance, relatedness and diversity. Moreover, to achieve conciseness, we split the summarized graph into several topic-centric summarized subgraph according to semantic and structural similarities among entities.Because of the incompleteness of KG, we measure the entity similarities by embedding vectors. Due to the NP-completeness of the problem, we propose a lightweight algorithm with bounded approximation. To address the online processing requirement, we adopt locality-sensitive hashing techniques to reduce the computation cost of accurate vector distances.