基于关系注意网络的时间感知知识图谱推理分析  

Analysis of Time Aware Knowledge Graph Reasoning Based on Relationship Attention Network

作　　者：廖洪 李黔黔 李志文 喻梓瑞 LIAO Hong;LI Qianqian;LI Zhiwen;YU Zirui(College of Big Data and Information Engineering,Guizhou University,Guizhou 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵州550025

出　　处：《集成电路应用》2024年第12期6-7,共2页Application of IC

摘　　要：阐述基于关系注意网络的感知时间知识图谱推理,它在每个时间节点内利用关系图注意网络,差异性地捕获知识图谱的结构性和高阶联系,递归地从节点的邻居传播嵌入,以优化节点的嵌入。通过门控组件动态地对历史知识图谱系列进行自回归地建模,以捕获所有历史事实。This paper describes perceptual temporal knowledge graph inference based on relational attention networks.It utilizes relational graph attention networks to capture the structural and higherorder connections of the knowledge graph differentially at each time node,recursively propagating embeddings from the neighbors of nodes to optimize node embeddings.It dynamically models the historical knowledge graph series through a gating component to capture all historical facts through autoregressive modeling.

关 键 词：智能技术 门控组件 优化节点的嵌入 知识图谱推理 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]