2024/05/14 by Rui Li, Li, Rui, Chaozhuo Li +7 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Cognitive Computing and Networks #FOS: Computer and information sciences #Machine Learning (cs.LG) #Rough Sets and Fuzzy Logic
paper · pdf · doi:10.48550/arxiv.2405.08540
openalex publication_date 2024/05/14 · openalex created_date 2024/05/16 · openalex updated_date 2026/07/28
Recent advances in knowledge graph embedding (KGE) rely on Euclidean/hyperbolic orthogonal relation transformations to model intrinsic logical patterns and topological structures. However, existing approaches are confined to rigid relational orthogonalization with restricted dimension and homogeneous geometry, leading to deficient modeling capability. In this work, we move beyond these approaches in terms of both dimension and geometry by introducing a powerful framework named GoldE, which features a universal orthogonal parameterization based on a generalized form of Householder reflection. Such parameterization can naturally achieve dimensional extension and geometric unification with theoretical guarantees, enabling our framework to simultaneously capture crucial logical patterns and inherent topological heterogeneity of knowledge graphs. Empirically, GoldE achieves state-of-the-art performance on three standard benchmarks. Codes are available at https://github.com/xxrep/GoldE.