QuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding

2025-04-18

AI Summary

Existing quaternion-based knowledge graph embedding models rely on inner-product scoring functions, limiting their flexibility and interpretability in modeling relational patterns. To address this, we propose QDist—the first Euclidean distance-based quaternion embedding framework. QDist abandons the conventional inner-product mechanism and instead defines the triple scoring function via Euclidean distances in the quaternion vector space, explicitly capturing the geometric structure of entities and relations. Theoretically, QDist unifies distance-based metric learning with hypercomplex algebraic properties. Empirically, it achieves significantly lower Mean Rank than state-of-the-art quaternion models (e.g., QuatE) on standard benchmarks including FB15k-237 and WN18RR, reduces parameter count by approximately 30%, and maintains efficient inference—demonstrating the effectiveness and generalizability of distance-driven modeling in hypercomplex embeddings.

Technology Category

• Machine Learning: Quantum Machine Learning
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Knowledge graph embedding (KGE) methods aim to represent entities and relations in a continuous space while preserving their structural and semantic properties. Quaternion-based KGEs have demonstrated strong potential in capturing complex relational patterns. In this work, we propose QuatE-D, a novel quaternion-based model that employs a distance-based scoring function instead of traditional inner-product approaches. By leveraging Euclidean distance, QuatE-D enhances interpretability and provides a more flexible representation of relational structures. Experimental results demonstrate that QuatE-D achieves competitive performance while maintaining an efficient parameterization, particularly excelling in Mean Rank reduction. These findings highlight the effectiveness of distance-based scoring in quaternion embeddings, offering a promising direction for knowledge graph completion.

Problem

• Develops a distance-based quaternion model for knowledge graph embedding
• Improves interpretability and flexibility in representing relational structures
• Enhances performance in knowledge graph completion tasks

Innovation

• Quaternion-based model with distance scoring
• Euclidean distance enhances interpretability
• Efficient parameterization improves Mean Rank