English

A*Net and NBFNet Learn Negative Patterns on Knowledge Graphs

Artificial Intelligence 2024-12-09 v1

Abstract

In this technical report, we investigate the predictive performance differences of a rule-based approach and the GNN architectures NBFNet and A*Net with respect to knowledge graph completion. For the two most common benchmarks, we find that a substantial fraction of the performance difference can be explained by one unique negative pattern on each dataset that is hidden from the rule-based approach. Our findings add a unique perspective on the performance difference of different model classes for knowledge graph completion: Models can achieve a predictive performance advantage by penalizing scores of incorrect facts opposed to providing high scores for correct facts.

Keywords

Cite

@article{arxiv.2412.05114,
  title  = {A*Net and NBFNet Learn Negative Patterns on Knowledge Graphs},
  author = {Patrick Betz and Nathanael Stelzner and Christian Meilicke and Heiner Stuckenschmidt and Christian Bartelt},
  journal= {arXiv preprint arXiv:2412.05114},
  year   = {2024}
}
R2 v1 2026-06-28T20:25:45.059Z