2019/04/23 by Shuai Zhang, Yi Tay, Zhang, Shuai +5 · 2 voices · 16 citations
Computer Science · #Advanced Graph Neural Networks #Cognitive Computing and Networks #Graph Theory and Algorithms #cs.CL #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1904.10281
openalex publication_date 2019/04/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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: (1) Latent inter-dependencies (between all components) are aptly captured with Hamilton product, encouraging a more compact interaction between entities and relations; (2) Quaternions enable expressive rotation in four-dimensional space and have more degree of freedom than rotation in complex plane; (3) 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 (i.e., modeling symmetry, anti-symmetry and inversion). Experimental results demonstrate that our method achieves state-of-the-art performance on four well-established knowledge graph completion benchmarks.