APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 1

Knowledge Graph Embedding with 3D Compound Geometric Transformations

Xiou Ge, University of Southern California, USA, xiouge@usc.edu , Yun Cheng Wang, University of Southern California, USA, Bin Wang, Institute for Infocomm Research (I2R), A*STAR, Singapore, C.-C. Jay Kuo, University of Southern California, USA
 
Suggested Citation
Xiou Ge, Yun Cheng Wang, Bin Wang and C.-C. Jay Kuo (2024), "Knowledge Graph Embedding with 3D Compound Geometric Transformations", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 1, e4. http://dx.doi.org/10.1561/116.00000177

Publication Date: 14 Feb 2024
© 2024 X. Ge, Y. C. Wang, B. Wang and C. C. J. Kuo
 
Subjects
 
Keywords
Knowledge graph embeddingLink predictionGeometric transformation
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 701 times

In this article:
Introduction 
Related Work 
Proposed Method 
Experiments 
Conclusion and Future Work 
Acknowledgments 
References 

Abstract

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Inspired by the recent trend in KGE designs that leverage multiple transformation from SO(3) instead of SE(2), we leverage 3D compound geometric transformations, including translation, rotation, scaling, reflection, and shear and propose a family of KGE models, named CompoundE3D, in this work. CompoundE3D allows multiple design variants to match rich underlying characteristics of a KG. We propose a beam search-based algorithm to locate the near-optimal embedding scoring function designs for different datasets in the vast search space resulted from different combinations of operator components. Since each variant has its own advantages on a subset of relations, an ensemble of multiple variants can yield superior performance. The effectiveness and flexibility of CompoundE3D are experimentally verified on four popular link prediction datasets.

DOI:10.1561/116.00000177