Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis

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.

arXiv commentTo appear at NAACL 2021

References in corpus (9)

• Distributed Representations of Words and Phrases and their Compositionality
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Knowledge Graph Embedding for Link Prediction: A Comparative Analysis
• Quaternion Knowledge Graph Embeddings
• Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
• Fast Linear Model for Knowledge Graph Embeddings
• Towards Understanding the Importance of Noise in Training Neural Networks
• Measuring Social Bias in Knowledge Graph Embeddings