QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion
This addresses knowledge base completion for AI applications, offering an incremental improvement over existing quaternion-based methods.
The paper tackles knowledge graph completion by proposing QuatDE, a model that dynamically adjusts entity embeddings in quaternion space to capture relational patterns and entity semantics, achieving state-of-the-art results with MR improvements of 26% on WN18 and 15% on WN18RR.
Knowledge graph embedding has been an active research topic for knowledge base completion (KGC), with progressive improvement from the initial TransE, TransH, RotatE et al to the current state-of-the-art QuatE. However, QuatE ignores the multi-faceted nature of the entity and the complexity of the relation, only using rigorous operation on quaternion space to capture the interaction between entitiy pair and relation, leaving opportunities for better knowledge representation which will finally help KGC. In this paper, we propose a novel model, QuatDE, with a dynamic mapping strategy to explicitly capture the variety of relational patterns and separate different semantic information of the entity, using transition vectors to adjust the point position of the entity embedding vectors in the quaternion space via Hamilton product, enhancing the feature interaction capability between elements of the triplet. Experiment results show QuatDE achieves state-of-the-art performance on three well-established knowledge graph completion benchmarks. In particular, the MR evaluation has relatively increased by 26% on WN18 and 15% on WN18RR, which proves the generalization of QuatDE.