TransINT: Embedding Implication Rules in Knowledge Graphs with Isomorphic Intersections of Linear Subspaces

TL;DR

TransINT is a novel knowledge graph embedding method that preserves implication relations among relations in an interpretable, isomorphic manner, enabling improved link prediction and rule mining.

Contribution

It introduces a new embedding approach that isomorphically encodes relation implications and allows automatic training on implied facts without explicit rule grounding.

Findings

Outperforms state-of-the-art rule integration methods in link prediction.

Achieves significant improvements in triple classification.

Provides an interpretable geometric measure for semantic relatedness.

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) $\in$ 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.