Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion

TL;DR

This paper introduces GeomE, a novel geometric algebra based embedding method for static and temporal knowledge graphs, achieving state-of-the-art link prediction performance by modeling entities, relations, and temporal dynamics effectively.

Contribution

The paper proposes GeomE, a geometric algebra based embedding approach that unifies static and temporal knowledge graph representations, extending it to TGeomE with temporal regularization and tensor factorization.

Findings

GeomE subsumes several state-of-the-art models.

TGeomE effectively models temporal dynamics in knowledge graphs.

Proposed models outperform existing methods on multiple datasets.

Abstract

Recent years, Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a Knowledge Graph (KG) into a geometric space and thus have gained increasing attentions. In addition, many recent Knowledge Graphs involve evolving data, e.g., the fact (\textit{Obama}, \textit{PresidentOf}, \textit{USA}) is valid only from 2009 to 2017. This introduces important challenges for knowledge representation learning since such temporal KGs change over time. In this work, we strive to move beyond the complex or hypercomplex space for KGE and propose a novel geometric algebra based embedding approach, GeomE, which uses multivector representations and the geometric product to model entities and relations. GeomE subsumes several state-of-the-art KGE models and is able to model diverse relations patterns. On top of this, we extend GeomE to TGeomE for temporal KGE, which performs 4th-order tensor factorization of a temporal KG and devises a new linear temporal regularization for time representation learning. Moreover, we study the effect of time granularity on the performance of TGeomE models. Experimental results show that our proposed models achieve the state-of-the-art performances on link prediction over four commonly-used static KG datasets and four well-established temporal KG datasets across various metrics.