Semantic, Symbolic and Interpretable Machine Learning

This workshop concerns machine learning (ML) approaches that 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, interpretable and revisable AI via symbolic representations, and extracting logical programs from data. Methods include, e.g., embedding approaches, graph neural networks, scene graph analysis, neuro-symbolic programming, and inductive logic programming. We also expect fruitful interactions with closely related programs covering, e.g., NLP, vision, and geometric deep learning.

Organized by:

Volker Tresp and Team
LMU / MCML

Kristian Kersting and Team
TU Darmstadt