基于实体多元编码的时序知识图谱推理

Reasoning Model for Temporal Knowledge Graph Based on Entity Multiple Unit Coding

【目的】解决时序知识图谱推理方法存在的实体信息获取片面和缺乏不同时间戳对于待推理事件重要性度量的问题。【方法】提出一种基于实体多元编码的时序知识图谱推理模型。实体多元编码旨在引入三种实体特征编码,包括当前时间戳的实体切片特征编码、融合时间戳嵌入和实体静态特征的实体动态特征编码以及历史时间步上相对稳定的实体片段特征编码。同时,设计时序注意力机制来学习不同时间戳内的局部结构信息对推理目标的重要性权重。【结果】该时序知识图推理模型在数据集ICEWS14上的实验结果为MRR:0.4704,Hits@1:40.31%,Hits@3:50.02%,Hits@10:59.98%;在ICEWS18上的实验结果为MRR:0.4385,Hits@1:37.55%,Hits@3:46.92%,Hits@10:56.85%;在YAGO上的实验结果为MRR:0.6564,Hits@1:63.07%,Hits@3:65.87%,Hits@10:68.37%,评估指标优于基线方法。【局限】在大规模数据集上运行速度较慢。【结论】本文方法捕获了时序知识图谱中包括实体切片特征、动态特征和片段特征的实体多元特征,所设计的时序注意力机制能够度量历史局部结构信息对推理的重要性,有效提升了时序知识图谱推理的性能。

[Objective] This paper tries to address the issues of incomplete entity information extraction and importance measurement of different timestamps for the events to be reasoned in temporal knowledge graph.[Methods] We proposed a new model based on entity multiple unit coding(EMUC). The EMUC introduces the entity slice feature encodings for the current timestamps, the entity dynamic feature encodings fusing timestamp embedding and entity static features, as well as entity segment feature encodings over historical steps. We also utilized a temporal attention mechanism to learn the importance weights of local structural information at different timestamps to the inference target. [Results] The experimental results of the proposed model on the ICEWS14 test set were MRR: 0.470 4, Hits@1: 40.31%, Hits@3: 50.02%, Hits@10: 59.98%, while on the ICEWS18 test set were MRR: 0.438 5, Hits@1: 37.55%, Hits@3: 46.92%, Hits@10: 56.85%, and on the YAGO test set are MRR:0.656 4, Hits@1: 63.07%, Hits@3 : 65.87%, Hits@10: 68.37%. Our model outperforms the existing methods on these evaluating metrics. [Limitations] EMUC has slow inference speed for large-scale datasets. [Conclusions]The newly temporal attention mechanism measures the importance of historical local structure information for reasoning, which effectively improves the reasoning performance of the temporal knowledge graph.