Group Representation Theory for Knowledge Graph Embedding

2019/09/11 by Chen Cai, Cai, Chen
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Complex Network Analysis Techniques #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Representation Theory (math.RT) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1909.05100

openalex publication_date 2019/09/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Knowledge graph embedding has recently become a popular way to model relations and infer missing links. In this paper, we present a group theoretical perspective of knowledge graph embedding, connecting previous methods with different group actions. Furthermore, by utilizing Schur's lemma from group representation theory, we show that the state of the art embedding method RotatE can model relations from any finite Abelian group.

Citations

• On the Equivalence of Holographic and Complex Embeddings for Link Prediction
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex\n Space
• Compositional Vector Space Models for Knowledge Base Completion

Related

• ModulE: Module Embedding for Knowledge Graphs
• Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces
• Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex\n Space
• TorusE: Knowledge Graph Embedding on a Lie Group