arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.10353cs.AI
收藏

基于进化表示学习的时态知识图谱推理

Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning

University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc.(百度公司)

Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, Huawei Shen, Yuanzhuo Wang, Xueqi Cheng

摘要:

知识图谱(KG)推理可以预测不完整KG中缺失的事实,已经得到了广泛的研究。然而,推理时间KG(TKG),预测未来的事实仍然远远没有解决。预测未来事实的关键在于彻底了解历史事实。TKG实际上是对应于不同时间戳的KG序列,其中每个KG中的所有并发事实表现出结构依赖性,并且时间上相邻的事实携带信息序列模式。为了有效地捕捉这些属性,我们提出了一种新的递归进化网络的基础上图卷积网络(GCN),称为RE-GCN,它学习的进化表示的实体和关系在每个时间戳通过建模KG序列递归。具体而言,对于演化单元,利用关系感知的GCN来捕获KG内每个时间戳处的结构依赖性。为了并行地捕获所有事实的序列模式,历史KG序列由门递归分量自回归地建模。此外,实体的静态属性,如实体类型,也通过一个静态图约束组件,以获得更好的实体表示。基于演化实体和关系表示,可以实现未来时间戳的事实预测。大量的实验表明,RE-GCN模型在六个基准数据集上的时间推理任务获得了显着的性能和效率的改善。特别是,它实现了高达11.46%的改进MRR实体预测与高达82倍的加速比相比,最先进的基线。

英文摘要:

Knowledge Graph (KG) reasoning that predicts missing facts for incomplete KGs has been widely explored. However, reasoning over Temporal KG (TKG) that predicts facts in the future is still far from resolved. The key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps, where all concurrent facts in each KG exhibit structural dependencies and temporally adjacent facts carry informative sequential patterns. To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently. Specifically, for the evolution unit, a relation-aware GCN is leveraged to capture the structural dependencies within the KG at each timestamp. In order to capture the sequential patterns of all facts in parallel, the historical KG sequence is modeled auto-regressively by the gate recurrent components. Moreover, the static properties of entities such as entity types, are also incorporated via a static graph constraint component to obtain better entity representations. Fact prediction at future timestamps can then be realized based on the evolutional entity and relation representations. Extensive experiments demonstrate that the RE-GCN model obtains substantial performance and efficiency improvement for the temporal reasoning tasks on six benchmark datasets. Especially, it achieves up to 11.46\% improvement in MRR for entity prediction with up to 82 times speedup comparing to the state-of-the-art baseline.

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。

↑