计算机科学与探索 ›› 2024, Vol. 18 ›› Issue (3): 646-658.DOI: 10.3778/j.issn.1673-9418.2212076

• 理论·算法 • 上一篇    下一篇

融合选择注意力的小样本知识图谱补全模型

林穗,卢超海,姜文超,林晓珊,周蔚林   

  1. 1. 广东工业大学 计算机学院,广州 510006
    2. 数安时代科技股份有限公司,广东 佛山 510100
  • 出版日期:2024-03-01 发布日期:2024-03-01

Few-Shot Knowledge Graph Completion Based on Selective Attention

LIN Sui, LU Chaohai, JIANG Wenchao, LIN Xiaoshan, ZHOU Weilin   

  1. 1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
    2. Global Digital Cybersecurity Authority Co., Ltd., Foshan, Guangdong 510100, China
  • Online:2024-03-01 Published:2024-03-01

摘要: 在面对实体对关系复杂或目标邻域稀疏等情况时,现有的小样本知识图谱补全模型普遍存在关系表示学习能力不足以及忽略实体对相对位置和交互作用的问题。基于此,提出一种基于选择注意力机制和交互感知的小样本知识图谱补全模型(SAIA)。首先,通过在聚合邻域信息过程中引入选择注意机制,帮助邻域编码器聚焦更重要的邻居以减少噪声邻居的不良影响;其次,在关系表示学习阶段,利用背景知识图谱中与任务关系相关的信息学习更加准确的关系表示;最后,为了挖掘知识图谱实体之间的交互信息和位置信息,设计了一个实体对公共交互率指标(CIR)来衡量实体对三阶路径内的关联程度,然后结合实体语义信息共同预测新的事实。实验结果表明该方法优于目前最先进的小样本知识图谱补全模型。与基准模型最优的结果相比,SAIA在NELL-one和Wiki-one数据集上的5-shot链接预测中,平均倒数排名(MRR)、Hits@10、Hits@5以及Hits@1等性能评价指标分别提高了0.038、0.011、0.028和0.052以及0.034、0.037、0.029和0.027,验证了所提模型的有效性和可行性。

关键词: 知识图谱, 知识图谱补全, 表示学习, 小样本关系, 注意力机制

Abstract: Most few-shot knowledge graph completion models have some problems, such as low ability to learn relation representation and rarely attaching importance to the relative location and interaction between query entity pair when the relation between entities is complex or triples’ neighborhood is sparse. A selective attention mechanism and interaction awareness (SAIA) based few-shot knowledge graph completion algorithm is proposed. Firstly, by introducing selective attention mechanism in the process of aggregating neighbor information, the neighbor encoder pays more attention to important neighbors to reduce adverse effects of noise neighbors. Secondly, SAIA utilizes the information related to task relation in the background knowledge graph to learn more accurate relation embedding in the process of relationship representation learning. Finally, in order to mine the interaction information and location information between entities in knowledge graph, a common interaction rate index (CIR) of entity pair is designed to measure the degree of association between entities in 3-hop path. Then, SAIA combines entity pair semantic information to predict new fact. Experimental results show that SAIA outperforms the state-of-the-art few-shot knowledge graph completion methods. Compared with the optimal results of baseline models, the proposed method achieves 5-shot link prediction performance improvement of 0.038, 0.011, 0.028 and 0.052 on NELL-one dataset and 0.034,0.037,0.029 and 0.027 on Wiki-one dataset by the metric MRR, Hits@10, Hits@5 as well as Hits@1, which verifies the effectiveness and feasibility of SAIA.

Key words: knowledge graph, knowledge graph completion, representation learning, few-shot relation, attention mechanism