DeepAI AI Chat
Log In Sign Up

A Group-Theoretic Framework for Knowledge Graph Embedding

by   Tong Yang, et al.

We demonstrated the existence of a group algebraic structure hidden in relational knowledge embedding problems, which suggests that a group-based embedding framework is essential for designing embedding models. Our theoretical analysis explores merely the intrinsic property of the embedding problem itself hence is model-independent. Motivated by the theoretical analysis, we have proposed a group theory-based knowledge graph embedding framework, in which relations are embedded as group elements, and entities are represented by vectors in group action spaces. We provide a generic recipe to construct embedding models associated with two instantiating examples: SO3E and SU2E, both of which apply a continuous non-Abelian group as the relation embedding. Empirical experiments using these two exampling models have shown state-of-the-art results on benchmark datasets.


page 1

page 2

page 3

page 4


Group Representation Theory for Knowledge Graph Embedding

Knowledge graph embedding has recently become a popular way to model rel...

ModulE: Module Embedding for Knowledge Graphs

Knowledge graph embedding (KGE) has been shown to be a powerful tool for...

Relational Memory-based Knowledge Graph Embedding

Knowledge graph embedding models often suffer from a limitation of remem...

RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding

Embedding entities and relations of a knowledge graph in a low-dimension...

HousE: Knowledge Graph Embedding with Householder Parameterization

The effectiveness of knowledge graph embedding (KGE) largely depends on ...

LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding

Knowledge graph embedding (KGE) models learn to project symbolic entitie...

Tiling of Constellations

Motivated by applications in reliable and secure communication, we addre...