Xander Wilcke

Linked Data, Knowledge Graphs, and other graph-shaped expressions of knowledge, information, and data are becoming popular means to store, share, and query datasets in a large variety of domains. As a post-doc in the Learning and Reasoning group at the Vrije University Amsterdam I am particularly interested in how we can employ novel machine learning techniques, including graph neural networks, inductive logic programming, and neuro-symbolic methods, to learn more from these data structures and such techniques can support domain experts in their research. This last facet is especially important for my work in WP4, in which I'm investigating how deep learning can be used to infer potentially interesting hypotheses from social-historical Linked Data.