Patrick Betz


University of Mannheim
B6, 26
D-68159 Mannheim

Email: patrick (at)

Research group:  Artificial Intelligence

Research Interests

  • Neuro-Symbolic AI
  • Knowledge representations


PyClause - A library for symbolic rule handling for knowledge graphs


  • P. Betz, L. Galarraga, S. Ott, C. Meilicke, F. Suchanek,  H. Stuckenschmidt
    PyClause – Simple and Efficient Rule Handling for Knowledge Graphs
    In: IJCAI (demo track, forthcoming), 2024
  • S. Ott, P. Betz, D. Stepanova, M. H. Gad-Elrab, C. Meilicke, H. Stuckenschmidt
    Rule-based knowledge graph completion with canonical models
    In: CIKM, 2023
  • P. Betz,  S. Lüdtke, C. Meilicke, H. Stuckenschmidt
    On the aggregation of rules for knowledge graph completion
    In: Knowledge and Logical Reasoning in the Era of Data-driven Learning Workshop@ICML 2023
  • C. Meilicke, M. W. Chekol, P. Betz, M. Fink, H Stuckenschmidt.
    Anytime bottom-up rule learning for large scale knowledge graph completion
    In: The VLDB Journal, 2023
  • P. Betz, C. Meilicke, H. Stuckenschmidt
    Adversarial explanations for knowledge graph embeddings
    In: IJCAI, 2022
  • P. Betz, C. Meilicke, H. Stuckenschmidt
    Supervised knowledge aggregation for knowledge graph completion
    In: ESWC, 2022
  • P. Betz, M. Niepert, P. Minervini, H. Stuckenschmidt
    Backpropagating through markov logic networks
    In: Proceedings of 15th International Workshop on Neural-Symbolic Learning and Reasoning, 2021
  • C. Meilicke, P. Betz, H. Stuckenschmidt
    Why a naive way to combine latent and symbolic knowledge base completion works surprisingly well
    In: 3rd Conference on Automated Knowledge Base Construction, 2021
  • S. Broscheit, D. Ruffinelli, A. Kochsiek, P. Betz, R. Gemulla
    LibKGE – A knowledge graph embedding library for reproducible research
    In: EMNLP (demo), 2020