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 2103.10379cs.LGcs.SC
收藏

ChronoR:基于旋转的时态知识图谱嵌入

ChronoR: Rotation Based Temporal Knowledge Graph Embedding

University of Florida(佛罗里达大学);Texas A&M University(德克萨斯A&M大学)

Ali Sadeghian, Mohammadreza Armandpour, Anthony Colas, Daisy Zhe Wang

摘要:

尽管时态知识图谱的重要性和丰富性,目前的研究主要集中在静态图上的推理。本文研究时态知识图谱上的推理问题。特别是时间链接预测的任务。一般来说,这是一个困难的任务,由于数据的非平稳性,数据异构性,及其复杂的时间依赖性。我们提出了时序旋转嵌入(ChronoR),这是一种用于学习实体,关系和时间表示的新模型。学习密集表示经常被用作在知识图谱上执行推理的有效且通用的方法。所提出的模型学习由关系和时间参数化的k维旋转变换,使得在使用旋转变换每个事实的头部实体之后,它落在其对应的尾部实体附近。通过使用高维旋转作为其变换算子,ChronoR捕获了时态知识图谱的时态和多关系特征之间的丰富交互。实验表明,ChronoR能够在时间知识图谱链接预测的基准数据集上胜过许多最先进的方法。

英文摘要:

Despite the importance and abundance of temporal knowledge graphs, most of the current research has been focused on reasoning on static graphs. In this paper, we study the challenging problem of inference over temporal knowledge graphs. In particular, the task of temporal link prediction. In general, this is a difficult task due to data non-stationarity, data heterogeneity, and its complex temporal dependencies. We propose Chronological Rotation embedding (ChronoR), a novel model for learning representations for entities, relations, and time. Learning dense representations is frequently used as an efficient and versatile method to perform reasoning on knowledge graphs. The proposed model learns a k-dimensional rotation transformation parametrized by relation and time, such that after each fact's head entity is transformed using the rotation, it falls near its corresponding tail entity. By using high dimensional rotation as its transformation operator, ChronoR captures rich interaction between the temporal and multi-relational characteristics of a Temporal Knowledge Graph. Experimentally, we show that ChronoR is able to outperform many of the state-of-the-art methods on the benchmark datasets for temporal knowledge graph link prediction.

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。

↑