基于混合注意力机制的时间旋转知识图谱补全

Temporal rotation knowledge graph completion based on hybrid attention mechanism

针对现有时序知识图谱补全中捕捉动态关系模式,处理非对称、临时和自反关系方面的局限性,提出了一种新颖的融合混合注意力机制与时间旋转的模型。一方面,通过引入时间旋转,利用复数空间中的向量来表示随时间演化的实体与关系,特别是处理时间区间内的关系变化,采用双复数嵌入方案显著增强了对时态特性的表达能力;另一方面,通过对知识图谱引入空间注意力和通道注意力两个维度分析,能够更好地聚焦于时序序列中对预测最为关键的实体和关系特征,从而在复杂的时间序列中挖掘时序关联信息。通过在ICEWS14、ICEWS18、YAGO11k和WIKI12k数据集上的实验评估,模型在MRR、Hits@1、Hits@3和Hits@10上普遍优于基线模型,体现出算法的优越性和强鲁棒性。

A novel model that integrates a hybrid attention mechanism with temporal rotation is proposed to address the limitations of capturing dynamic relation patterns,handling asymmetric,temporary,and reflexive relations in existing temporal knowledge graph completion.On one hand,by introducing temporal rotation,we leverage vectors in complex spaces to represent entities and relations evolving over time,especially to handle relation changes within temporal intervals.The adoption of a dual-complex embedding scheme significantly enhances the expressive power for temporal characteristics.On the other hand,by introducing spatial attention and channel attention to analyze the knowledge graph from two dimensions,the model can better focus on the most crucial entity and relation features in the temporal sequence for prediction,thus mining temporal correlation information from complex time series.Through experimental evaluations on the ICEWS14,ICEWS18,YAGO11k,and WIKI12k datasets,the model outperforms baseline models in terms of MRR,Hits@1,Hits@3,and Hits@10,demonstrating the superiority and strong robustness of the proposed algorithm.