EL Embeddings: Geometric construction of models for the Description Logic EL ++
An embedding is a function that maps entities from one algebraic structure into another while preserving certain characteristics. Embeddings are being used successfully for mapping relational data or text into vector spaces where they can be used for machine learning, similarity search, or similar tasks. We address the problem of finding vector space embeddings for theories in the Description Logic $\mathcal{EL}^{++}$ that are also models of the TBox. To find such embeddings, we define an optimization problem that characterizes the model-theoretic semantics of the operators in $\mathcal{EL}^{++}$ within $\Re^n$, thereby solving the problem of finding an interpretation function for an $\mathcal{EL}^{++}$ theory given a particular domain $\Delta$. Our approach is mainly relevant to large $\mathcal{EL}^{++}$ theories and knowledge bases such as the ontologies and knowledge graphs used in the life sciences. We demonstrate that our method can be used for improved prediction of protein--protein interactions when compared to semantic similarity measures or knowledge graph embedding
Code (1)
Tasks
Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsSemantic SimilaritySemantic Textual SimilaritySimilar Papers 제목 키워드 기반
Geometric Models for (Temporally) Attributed Description Logics
In the search for knowledge graph embeddings that could capture ontological knowledge, geometric models of existential rules have been recently introduced. It has been shown that convex geometric regions capture the so-c…
Knowledge Graph EmbeddingsKnowledge GraphsOn a geometric description of time dependent singular Lagrangians with applications to biological systems
We consider certain analytical features of a stochastic model that can explain among other things competition among species and simultaneous predation on the competing species from a geometric perspective which allows fo…
Description Logic EL++ Embeddings with Intersectional Closure
Many ontologies, in particular in the biomedical domain, are based on the Description Logic EL++. Several efforts have been made to interpret and exploit EL++ ontologies by distributed representation learning. Specifical…
Representation LearningWhat Do Language Priors Contribute to Darcy-Flow Inversion? A Mechanistic Audit
In ill-posed inverse problems, the recovered solution depends as much on the prior as on the data, yet much of the engineering knowledge that could serve as that prior is recorded qualitatively rather than in formal math…
Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations
Geometric embedding methods have shown to be useful for multi-hop reasoning on knowledge graphs by mapping entities and logical operations to geometric regions and geometric transformations, respectively. Geometric embed…
Knowledge Graphs