Knowledge Graph Embedding with 3D Compound Geometric Transformations
This work addresses knowledge graph completion for AI applications, but it is incremental, building on existing 2D and 3D transformation methods.
The authors tackled the problem of knowledge graph embedding by proposing CompoundE3D, a family of models using 3D compound geometric transformations, which achieved superior performance on link prediction across four datasets.
The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as a new KGE model, Rotate3D, by leveraging its non-commutative property. Inspired by CompoundE and Rotate3D, we leverage 3D compound geometric transformations, including translation, rotation, scaling, reflection, and shear and propose a family of KGE models, named CompoundE3D, in this work. CompoundE3D allows multiple design variants to match rich underlying characteristics of a KG. Since each variant has its own advantages on a subset of relations, an ensemble of multiple variants can yield superior performance. The effectiveness and flexibility of CompoundE3D are experimentally verified on four popular link prediction datasets.