arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.02150cs.AI
收藏

时间感知图神经网络在时态知识图谱实体对齐中的应用

Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs

University of Bonn(波恩大学);Fraunhofer IAIS(弗劳恩霍夫智能分析与信息系统研究所)

Chengjin Xu, Fenglong Su, Jens Lehmann

摘要:

实体对齐旨在识别不同知识图谱之间的等价实体对。最近,包含时间信息的时态知识库(TKG)的可用性产生了在这样的TKG中进行时间推理的需要。现有的基于嵌入的实体对齐方法忽略了大规模知识库中普遍存在的时间信息,存在很大的改进空间。针对TKG之间的实体对齐问题,提出了一种基于图神经网络的时间感知实体对齐方法(TEA-GNN)。我们将不同KG的实体,关系和时间戳嵌入到向量空间中,并使用GNN来学习实体表示。为了将关系和时间信息结合到我们模型的GNN结构中,我们使用了一种时间感知的注意力机制,该机制为不同的节点分配不同的权重,并使用从邻域中相关关系和时间戳的嵌入计算的正交变换矩阵。多个真实世界的TKG数据集上的实验结果表明,由于包含时间信息,我们的方法显着优于最先进的方法。

英文摘要:

Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs). Recently, the availability of temporal KGs (TKGs) that contain time information created the need for reasoning over time in such TKGs. Existing embedding-based entity alignment approaches disregard time information that commonly exists in many large-scale KGs, leaving much room for improvement. In this paper, we focus on the task of aligning entity pairs between TKGs and propose a novel Time-aware Entity Alignment approach based on Graph Neural Networks (TEA-GNN). We embed entities, relations and timestamps of different KGs into a vector space and use GNNs to learn entity representations. To incorporate both relation and time information into the GNN structure of our model, we use a time-aware attention mechanism which assigns different weights to different nodes with orthogonal transformation matrices computed from embeddings of the relevant relations and timestamps in a neighborhood. Experimental results on multiple real-world TKG datasets show that our method significantly outperforms the state-of-the-art methods due to the inclusion of time information.

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。

↑