Semantic, Symbolic and Interpretable Machine Learning

This program concerns machine learning (ML) approaches which operate at the human abstraction level, where the world is described by entities, concepts, and their mutual relationships.  Among other topics, we cover multi-relational learning, learning with (temporal) knowledge graphs, and the extraction of statistical and logical regularities from data.  Methods include, e.g., embedding approaches, graph neural networks, scene graph analysis, neuro-symbolic programming, and inductive logic programming.

The goal is that our program becomes a cumulation point of like-minded researchers and we expect fruitful interactions with closely related programs covering, e.g., NLP, vision, and geometric deep learning.

 


Workshops organized by the program

14 - 16 February 2024: ELLIS Workshop on Semantic, Symbolic and Interpretable Machine Learning

Hosted at the Oberwolfach Research Institute for Mathematics (MFO) in southern Germany, the workshop focused on machine learning approaches which operate at the human abstraction level, where the world is described by entities, concepts, and their mutual relationships. Among other topics, the event in the Black Forest covered multi-relational learning, learning with (temporal) knowledge graphs, and the extraction of statistical and logical regularities from data. It served as an important platform to connect scientists in this field and to foster new research collaborations in Europe. The workshop was funded by the state of Baden-Württemberg (Germany) and organized in collaboration with the ELLIS Institute Tübingen and the Max-Planck-Institut für Intelligente Systeme.