Miguel Romero Orth — accepted AI-conference papers

2025

How Expressive are Knowledge Graph Foundation Models?

Xingyue Huang, Pablo Barcelo, Michael M. Bronstein, Ismail Ilkan Ceylan, Mikhail Galkin, Juan L Reutter +1

ICML 2025poster

Knowledge Graph Foundation Models (KGFMs) are at the frontier for deep learning on knowledge graphs (KGs), as they can generalize to completely novel knowledge graphs with different relational vocabularies. Despite their empirical success, our theoretical understanding of KGFMs remains very limited.…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs

Xingyue Huang, Miguel Romero Orth, Ismail Ilkan Ceylan, Pablo Barcelo

NeurIPS 2023poster

Graph neural networks are prominent models for representation learning over graph-structured data. While the capabilities and limitations of these models are well-understood for simple graphs, our understanding remains incomplete in the context of knowledge graphs. Our goal is to provide a systemati…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗

2022

On Computing Probabilistic Explanations for Decision Trees

Marcelo Arenas, Pablo Barcelo, Miguel Romero Orth, Bernardo Subercaseaux

NeurIPS 2022accept

Formal XAI (explainable AI) is a growing area that focuses on computing explanations with mathematical guarantees for the decisions made by ML models. Inside formal XAI, one of the most studied cases is that of explaining the choices taken by decision trees, as they are traditionally deemed as one o…

Cited by 55 Source ↗PDF ↗Scholar ↗