Data, Intelligence & Graphs

• Knowledge Graphs
• Machine/Deep Learning
• Language/Foundational Models
• Natural Language Processing
• Logic and Algorithms
• Graph mining
• Stream Mining
• Application Domains: Healthcare, Legal Domain

Research Projects

Industry Collaborations

Algorithms:

• AMIE: AMIE is a project to learn patterns and rules in ontologies. We conduct this project together with the Database department of the Max Planck Institute for Informatics in Germany.

Knowledge Graphs:

• YAGO: YAGO is a large ontology constructed from WordNet, Wikipedia, and other sources. We develop YAGO together with the Database department of the Max Planck Institute for Informatics in Germany.

Softwares:

• scikit-network: scikit-network is a Python package for the analysis of large graphs (clustering, embedding, classification, ranking).

• We investigate how to do machine learning in real time, contributing to new open source tools:

  • River: a Python library for online MachineLearning
  • MOA: Massive Online Analytics, a framework for mining data streams (in Java). 
  • Apache SAMOA: Scalable Advanced Massive Online
  • Analytics, an open source framework for data stream mining on the Hadoop Ecosystem

Language and Relevance

Computer science is not just about computers. In this area of research, we investigate how humans reason, and what this implies for machines.

• Simplicity theory seeks to explain the relevance of situations or events to human minds.
• Relevance in natural language: The point is to retro-engineer methods to achieve meaningful and relevant speech from our understanding of human performance.
• We apply game theory and social simulation to explore conditions in which providing valuable (i.e. relevant) information is a profitable strategy. Read this paper.

Four articles have been accepted at ICLR 2026
1. Query-Level Uncertainty in Large Language Models, Lihu Chen, Fabian M. Suchanek, Gaël Varoquaux, Gerard de Melo.
2. Efficient Resource Constrained Training of Vision Transformers via Subspace Optimization, Le-Trung Nguyen Enzo Tartaglione Van-Tam Nguyen.
3. Study of Training Dynamics for Memory-Constrained Fine-tuning. Aël Quélennec, Nour Hezbri, Pavlo Mozharovskyi, Van-Tam Nguyen, Enzo Tartaglione.
4. INSTANT: Compressing Gradients and Activations for Resource-Efficient Training.

Our article “It’s All About the Confidence: An Unsupervised Approach for Multilingual Historical Entity Linking using Large Language Models” by Cristian Santini, Marieke van Erp, Mehwish Alam has been accepted at EACL 2026.

Yiwen Peng, Thomas Bonald and Fabian Suchanek received the best paper award at ISWC 2025 for their paper on FLORA: Unsupervised Knowledge Graph Alignment by Fuzzy Logic.

Two demo articles Enriching Taxonomies using Large Language Models and T-REX: Table Refute or Entail Explainer by Zeinab Ghamlouch, Tim Luka Horstmann, Beptiste Geisenberger, and Mehwish Alam were presented at ECAI 2025 and ECML/PKDD 2025.

Berenice Jaulmes attended the 36th European Summer School in Logic, Language, and Information (ESSLLI2025) in Bochum, Germany.

Nils Holzenberger attended the International Seminars on the New Institutional Economics 2025.