We are very proud to announce the creation of a new ELLIS program, called ‘Semantic, Symbolic and Interpretable Machine Learning’. This program will be headed by Volker Tresp, of the ELLIS Munich unit, Kristian Kersting and Paolo Frasconi.
The focus of the new program is on the approaches to machine learning (ML) that operate at the level of human abstraction, where the world is described in terms of entities, concepts, and the relationships between them. Topics of research include multi-relational learning with (temporal) knowledge graphs and the extraction of statistical and logical regularities from data. Methods include embedding approaches, graph neural networks, scene graph analysis, neuro-symbolic programming, and inductive logic programming.