- Keywords: Knowledge Graph Embedding, Isomorphism, Rules, Common Sense, Implication Rules, Knowledge Graph, Isomorphic Embedding, Semantics Mining, Rule Mining, TransH
- TL;DR: We propose TransINT, a novel and interpretable KG embedding method that isomorphically preserves the implication ordering among relations in the embedding space in an explainable, robust, and geometrically coherent way.
- Subject Areas: Knowledge Representation, Semantic Web and Search, Applications, Relational AI
- Archival Status: Archival
- Abstract: Knowledge Graphs (KG), composed of entities and relations, provide a structured representation of knowledge. For easy access to statistical approaches on relational data, multiple methods to embed a KG into f(KG) ∈ R^d have been introduced. We propose TransINT, a novel and interpretable KG embedding method that isomorphically preserves the implication ordering among relations in the embedding space. Given implication rules, TransINT maps set of entities (tied by a relation) to continuous sets of vectors that are inclusion-ordered isomorphically to relation implications. With a novel parameter sharing scheme, TransINT enables automatic training on missing but implied facts without rule grounding. On a benchmark dataset, we outperform the best existing state-of-the-art rule integration embedding methods with significant margins in link Prediction and triple Classification. The angles between the continuous sets embedded by TransINT provide an interpretable way to mine semantic relatedness and implication rules among relations.