arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.08641cs.AI
收藏

多关系投影的知识图谱嵌入

Knowledge Graph Embedding with Multiple Relation Projections

Applied AI Institute, Deakin University(迪肯大学应用人工智能研究所)

Kien Do, Truyen Tran, Svetha Venkatesh

摘要:

知识图谱包含世界的丰富关系结构,从而补充异构数据中的数据驱动机器学习。表示知识图谱的最有效方法之一是将符号关系和实体嵌入到连续空间中,其中关系是关系空间中实体的投影图像之间的近似线性平移。然而,诸如TransR、TransD或TransSparse的现有技术的关系投影方法不对关系之间的相关性进行建模,并且因此在计算需求和统计鲁棒性方面都不能扩展到具有数千个关系的复杂知识图谱。为此,我们引入transF,一种新的基于投影的方法,通过明确建模的投影矩阵的基础子空间,减轻了关系投影的负担。因此,TransF比现有的投影方法要轻得多,并且在面对大量关系时是鲁棒的。在典型的链接预测任务上的实验结果表明,我们提出的模型在很大程度上优于竞争对手,达到了最先进的性能。特别是,TransF在N对1/1对N关系的头/尾实体预测任务中比性能最好的基于简化的方法提高了9%/5%。

英文摘要:

Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data. One of the most effective methods in representing knowledge graphs is to embed symbolic relations and entities into continuous spaces, where relations are approximately linear translation between projected images of entities in the relation space. However, state-of-the-art relation projection methods such as TransR, TransD or TransSparse do not model the correlation between relations, and thus are not scalable to complex knowledge graphs with thousands of relations, both in computational demand and in statistical robustness. To this end we introduce TransF, a novel translation-based method which mitigates the burden of relation projection by explicitly modeling the basis subspaces of projection matrices. As a result, TransF is far more light weight than the existing projection methods, and is robust when facing a high number of relations. Experimental results on the canonical link prediction task show that our proposed model outperforms competing rivals by a large margin and achieves state-of-the-art performance. Especially, TransF improves by 9%/5% in the head/tail entity prediction task for N-to-1/1-to-N relations over the best performing translation-based method.

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。

↑