CompoundE: Knowledge Graph Embedding with Translation, Rotation and Scaling Compound Operations

TL;DR

CompoundE introduces a novel knowledge graph embedding model that combines translation, rotation, and scaling operations, achieving state-of-the-art results across multiple datasets by unifying existing models within a group-theoretic framework.

Contribution

It proposes a new KGE model that integrates multiple geometric operations and unifies existing models under a group-theoretic framework, enhancing embedding expressiveness.

Findings

Achieves state-of-the-art performance on three KG datasets

Unifies existing KGE models within a compound operation framework

Demonstrates the effectiveness of combining multiple geometric transformations

Abstract

Translation, rotation, and scaling are three commonly used geometric manipulation operations in image processing. Besides, some of them are successfully used in developing effective knowledge graph embedding (KGE) models such as TransE and RotatE. Inspired by the synergy, we propose a new KGE model by leveraging all three operations in this work. Since translation, rotation, and scaling operations are cascaded to form a compound one, the new model is named CompoundE. By casting CompoundE in the framework of group theory, we show that quite a few scoring-function-based KGE models are special cases of CompoundE. CompoundE extends the simple distance-based relation to relation-dependent compound operations on head and/or tail entities. To demonstrate the effectiveness of CompoundE, we conduct experiments on three popular KG completion datasets. Experimental results show that CompoundE consistently achieves the state of-the-art performance.