Graph-based data analysis and learning has received a lot of attention recently, but still requires much more research. We are building open-source prototypes for scalable management and analysis of based on either the property graph model or RDF. A cornerstone of this is graph representation learning, which allows graphs to be used directly in a wide range of machine learning and machine learning approaches and natural language understanding techniques. These representations thus form a bridge between knowledge representation and Machine Learning.

Research Focus

We significantly extend the research on graph analytics and the development of the distributed open-source system GRADOOP. We develop new indexing and graph summarization techniques and apply selectivity-enhancing mechanisms known from graph databases. Advanced representation learning in Knowledge Graphs will be integrated into the PyKEEN framework, and we explore knowledge-based methods for rich graph models.

Aims

• Analysis and ML on dynamic graphs:
• Scalable RDF graph queries
• Representation learning in knowledge graphs
• Graph-based reasoning and ontology languages