Faithiful Embeddings for EL++ Knowledge Bases
This work addresses the challenge of embedding both data-level and concept-level knowledge in symbolic knowledge bases for applications like protein-protein prediction, representing an incremental improvement over existing methods.
The paper tackles the problem of learning faithful embeddings for EL++ knowledge bases by proposing BoxEL, a geometric approach that models concepts as axis-parallel boxes and entities as points, which theoretically guarantees soundness for preserving logical structure. Experimental results show that BoxEL outperforms traditional knowledge graph embedding methods and state-of-the-art EL++ embedding approaches in subsumption reasoning and protein-protein prediction tasks.
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.