DensE: An Enhanced Non-Abelian Group Representation for Knowledge Graph Embedding

08/11/2020
by   Haonan Lu, et al.
0

Capturing the composition patterns of relations is a vital task in knowledge graph completion. It also serves as a fundamental step towards multi-hop reasoning over learned knowledge. Previously, rotation-based translational methods, e.g., RotatE, have been developed to model composite relations using the product of a series of complex-valued diagonal matrices. However, RotatE makes several oversimplified assumptions on the composition patterns, forcing the relations to be commutative, independent from entities and fixed in scale. To tackle this problem, we have developed a novel knowledge graph embedding method, named DensE, to provide sufficient modeling capacity for complex composition patterns. In particular, our method decomposes each relation into an SO(3) group-based rotation operator and a scaling operator in the three dimensional (3-D) Euclidean space. The advantages of our method are twofold: (1) For composite relations, the corresponding diagonal relation matrices can be non-commutative and related with entity embeddings; (2) It extends the concept of RotatE to a more expressive setting with lower model complexity and preserves the direct geometrical interpretations, which reveals how relations with distinct patterns (i.e., symmetry/anti-symmetry, inversion and composition) are modeled. Experimental results on multiple benchmark knowledge graphs show that DensE outperforms the current state-of-the-art models for missing link prediction, especially on composite relations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2022

SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Space

Translation distance based knowledge graph embedding (KGE) methods, such...
research
09/04/2019

A Non-commutative Bilinear Model for Answering Path Queries in Knowledge Graphs

Bilinear diagonal models for knowledge graph embedding (KGE), such as Di...
research
04/23/2019

Quaternion Knowledge Graph Embedding

Complex-valued representations have demonstrated promising results on mo...
research
06/08/2022

ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion

Knowledge graphs are inherently incomplete. Therefore substantial resear...
research
05/22/2023

3D Rotation and Translation for Hyperbolic Knowledge Graph Embedding

The main objective of Knowledge Graph (KG) embeddings is to learn low-di...
research
02/15/2022

STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation

The bilinear method is mainstream in Knowledge Graph Embedding (KGE), ai...
research
04/01/2023

Knowledge Graph Embedding with 3D Compound Geometric Transformations

The cascade of 2D geometric transformations were exploited to model rela...

Please sign up or login with your details

Forgot password? Click here to reset