Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis

TL;DR

This paper introduces a highly efficient KGE framework using Orthogonal Procrustes Analysis, significantly reducing training time and environmental impact while maintaining competitive performance and interpretability.

Contribution

It presents a novel KGE method with full batch learning, closed-form solutions, and interpretable embeddings, outperforming existing approaches in efficiency.

Findings

Reduces training time and carbon footprint by orders of magnitude.

Achieves competitive performance on standard datasets.

Provides highly interpretable entity embeddings with rich semantic information.

Abstract

Knowledge Graph Embeddings (KGEs) have been intensively explored in recent years due to their promise for a wide range of applications. However, existing studies focus on improving the final model performance without acknowledging the computational cost of the proposed approaches, in terms of execution time and environmental impact. This paper proposes a simple yet effective KGE framework which can reduce the training time and carbon footprint by orders of magnitudes compared with state-of-the-art approaches, while producing competitive performance. We highlight three technical innovations: full batch learning via relational matrices, closed-form Orthogonal Procrustes Analysis for KGEs, and non-negative-sampling training. In addition, as the first KGE method whose entity embeddings also store full relation information, our trained models encode rich semantics and are highly interpretable. Comprehensive experiments and ablation studies involving 13 strong baselines and two standard datasets verify the effectiveness and efficiency of our algorithm.