Quaternion Knowledge Graph Embeddings (2019)

View PDF. Abstract:In this work, we move beyond the traditional complex-valued representations, introducing more expressive hypercomplex representations to model entities and relations for knowledge graph embeddings. More specifically, quaternion embeddings, hypercomplex-valued embeddings with three imaginary components, are utilized to represent entities. Relations are modelled as rotations in the quaternion space. The advantages of the proposed approach are: Latent inter-dependencies are aptly captured with Hamilton product, encouraging a more compact interaction between entities and relations; Quaternions enable expressive rotation in four-dimensional space and have more degree of freedom than rotation in complex plane; The proposed framework is a generalization of ComplEx on hypercomplex space while offering better geometrical interpretations, concurrently satisfying the key desiderata of relational representation learning. Experimental results demonstrate that our method achieves state-of-the-art performance on four well-established knowledge graph completion benchmarks.