Trustworthy Knowledge Base Embeddings: A Foundational Study of Box Semantics
Neurosymbolic Artificial Intelligence · 2026-07 · 2
DOI: 10.1177/29498732261469486 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurosymbolic Artificial Intelligence, online erschienen am 29.07.2026. Verfasst von Mena Leemhuis und 1 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Knowledge base embeddings are widely applied, used for instance to improve link prediction tasks on knowledge graphs by exploiting the geometric regularities occurring during learning. Techniques where ontological concepts are interpreted as boxes have shown to be particularly useful in this context, as they are both suitably expressive and of low computational cost allowing practical implementations. However, in order to use those regularities for learning reliably, it is necessary to determine and understand the possible biases in the approach: how do we distinguish what is learned due to regularities in the data from what is simply based on the representational limitations of the embedding? In this paper, we establish that there are some severe limitations in expressivity when modeling description logic ontologies with box embeddings in intended target languages such as E L H O ( ∘ ) ⊥ . We illustrate that, under some weak assumptions, box semantics always satisfy Helly’s Property, and is thus too weak to semantically capture E L H O ( ∘ ) ⊥ in an adequate way. We then characterize how so-called Helly-satisfiable E L H O ( ∘ ) ⊥ ontologies can be determined and discuss other restrictions of representability arising from Helly’s Property, namely the restricted faithfulness of the embeddings.
Zitieren
APA
Leemhuis, M., & Kutz, O. (2026). Trustworthy Knowledge Base Embeddings: A Foundational Study of Box Semantics. Neurosymbolic Artificial Intelligence, 2. https://doi.org/10.1177/29498732261469486
Vancouver
Leemhuis M, Kutz O. Trustworthy Knowledge Base Embeddings: A Foundational Study of Box Semantics. Neurosymbolic Artificial Intelligence. 2026;2. doi:10.1177/29498732261469486
BibTeX
@article{Leemhuis2026,
author = {Leemhuis, Mena and Kutz, Oliver},
title = {Trustworthy Knowledge Base Embeddings: A Foundational Study of Box Semantics},
journal = {Neurosymbolic Artificial Intelligence},
year = {2026},
volume = {2},
doi = {10.1177/29498732261469486}
}
EUVIMED