English

Faithiful Embeddings for EL++ Knowledge Bases

Artificial Intelligence 2022-09-23 v2 Machine Learning Logic in Computer Science

Abstract

Recently, increasing efforts are put into learning continual representations for symbolic knowledge bases (KBs). However, these approaches either only embed the data-level knowledge (ABox) or suffer from inherent limitations when dealing with concept-level knowledge (TBox), i.e., they cannot faithfully model the logical structure present in the KBs. We present BoxEL, a geometric KB embedding approach that allows for better capturing the logical structure (i.e., ABox and TBox axioms) in the description logic EL++. BoxEL models concepts in a KB as axis-parallel boxes that are suitable for modeling concept intersection, entities as points inside boxes, and relations between concepts/entities as affine transformations. We show theoretical guarantees (soundness) of BoxEL for preserving logical structure. Namely, the learned model of BoxEL embedding with loss 0 is a (logical) model of the KB. Experimental results on (plausible) subsumption reasonings and a real-world application for protein-protein prediction show that BoxEL outperforms traditional knowledge graph embedding methods as well as state-of-the-art EL++ embedding approaches.

Keywords

Cite

@article{arxiv.2201.09919,
  title  = {Faithiful Embeddings for EL++ Knowledge Bases},
  author = {Bo Xiong and Nico Potyka and Trung-Kien Tran and Mojtaba Nayyeri and Steffen Staab},
  journal= {arXiv preprint arXiv:2201.09919},
  year   = {2022}
}

Comments

Published in ISWC'22

R2 v1 2026-06-24T09:00:54.883Z