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

--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. NOWLEDGE GRAPHS (KGs) are structured representations of real-world knowledge, expressed as triples (head, relation, tail) that denote relationships between entities. These graphs encapsulate factual information about entities, such as objects, events, or abstract concepts, and their interconnections. KGs have emerged as foundational tools in a wide range of applications, including question-answering [1]-[3], natural language processing [4], and recommendation systems [5], [6]. Their ability to represent and infer complex relationships makes them indispensable for semantic reasoning and downstream AI applications.