Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings

TL;DR

This paper introduces DURA, a novel regularizer that leverages duality in knowledge graph embedding models to improve semantic similarity representation, significantly enhancing performance on static and temporal benchmarks.

Contribution

The paper proposes DURA, a duality-induced regularizer that enforces semantic similarity in embeddings by utilizing associated dual models, improving existing semantic matching models.

Findings

DURA improves state-of-the-art models on static knowledge graph benchmarks.

DURA enhances temporal knowledge graph embedding performance.

Experimental results show consistent and significant gains with DURA.

Abstract

Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE). Many existing semantic matching models use inner products in embedding spaces to measure the plausibility of triples and quadruples in static and temporal knowledge graphs. However, vectors that have the same inner products with another vector can still be orthogonal to each other, which implies that entities with similar semantics may have dissimilar embeddings. This property of inner products significantly limits the performance of semantic matching models. To address this challenge, we propose a novel regularizer -- namely, DUality-induced RegulArizer (DURA) -- which effectively encourages the entities with similar semantics to have similar embeddings. The major novelty of DURA is based on the observation that, for an existing semantic matching KGE model (primal), there is often another distance based KGE model (dual) closely associated with it, which can be used as effective constraints for entity embeddings. Experiments demonstrate that DURA consistently and significantly improves the performance of state-of-the-art semantic matching models on both static and temporal knowledge graph benchmarks.