Adaptive Personalized Knowledge Graph Summarization

Lukas Faber, Tara Safavi, Davide Mottin, Danai Koutra, Emmanuel Müller

MLG Workshop @ KDD 2018

Can we compress a graph based on user queries?


Knowledge graphs, which are rich networks of entities and concepts connected via multiple types of relationships, have gained traction as powerful structures for natural language understanding and question answering. Although recent research efforts have started to address efficient querying and storage of knowledge graphs, such methods are neither user-driven nor flexible to changes in the data, both of which are important in the real world. We thus introduce and motivate adaptive knowledge graph summarization to create small, personalized knowledge graphs that contain only the information most relevant to an individual user’s interests. Such concise summaries may be stored locally on mobile devices, allowing for fast interactive querying, and constantly updated to serve changing user needs and data evolution. In this position paper, we make a case for adaptive knowledge graph summarization, outlining promising approaches toward efficient, personalized knowledge graph management