arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.04676cs.LGcs.AIcs.CLstat.ML
收藏

基于正交Procrustes分析的高效知识图谱嵌入学习

Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis

The University of Sheffield(谢菲尔德大学);Utrecht University(乌得勒支大学)

Xutan Peng, Guanyi Chen, Chenghua Lin, Mark Stevenson

摘要:

由于知识图谱嵌入具有广泛的应用前景,近年来得到了广泛的研究。然而,现有的研究集中在提高最终的模型性能,而不承认所提出的方法的计算成本,在执行时间和环境影响方面。本文提出了一种简单而有效的KGE框架,与最先进的方法相比,它可以减少训练时间和碳足迹的数量级,同时产生有竞争力的性能。我们强调了三项技术创新:通过关系矩阵进行全批学习,KGE的封闭形式正交Procrustes分析和非负采样训练。此外,作为第一个实体嵌入也存储完整关系信息的KGE方法,我们训练的模型编码了丰富的语义,并且具有高度的可解释性。在13个强基线和两个标准数据集上进行的实验和消融研究验证了算法的有效性和效率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑