基于属性嵌入与图注意力网络的实体对齐算法  

Entity Alignment Algorithm Based on Attribute Embedding and Graph Attention Network

作　　者：苏谟[2,3] 步格格 范秋枫 刘凡力 SU Mo;BU Ge-Ge;FAN Qiu-Feng;LIU Fan-Li(University of Chinese Academy of Sciences,Beijing 100049,China;Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang 110168,China;Shenyang Ligong University,Shenyang 110159,China)

机构地区：[1]中国科学院大学,北京100049 [2]中国科学院沈阳计算技术研究所,沈阳110168 [3]沈阳理工大学,沈阳110159

出　　处：《计算机系统应用》2023年第3期202-208,共7页Computer Systems & Applications

基　　金：沈阳市中青年科技创新人才(RC210393);辽宁省“百千万人才工程”项目(2021921015)。

摘　　要：实体对齐旨在找到位于不同知识图谱中的等效实体,是实现知识融合的重要步骤.当前主流的方法是基于图神经网络的实体对齐方法,这些方法往往过于依赖图的结构信息,导致在特定图结构上训练得到的模型不能拓展应用于其他图结构中.同时,大多数方法未能充分利用辅助信息,例如属性信息.为此,本文提出了一种基于图注意力网络和属性嵌入的实体对齐方法,该方法使用图注意力网络对不同的知识图谱进行编码,引入注意力机制从实体应用到属性,在对齐阶段将结构嵌入和属性嵌入进行结合实现实体对齐效果的提升.在现实世界的3个真实数据集上对本文模型进行了验证,实验结果表明提出的方法在很大程度上优于基准的实体对齐方法.Entity alignment aims to find equivalent entities located in different knowledge graphs and is an important step for knowledge fusion. Currently, mainstream entity alignment methods are those based on graph neural networks.However, they often rely too much on the structural information of graphs, as a result of which models trained on specific graph structures cannot be applied to other graph structures. Meanwhile, most methods fail to fully utilize auxiliary information, such as attribute information. In response, this study proposes an entity alignment method based on a graph attention network and attribute embedding. The method uses the graph attention network to encode different knowledge graphs, introduces an attention mechanism from entity application to attribute, and combines structure embedding and attribute embedding in the alignment stage to improve the effect of entity alignment. The proposed model is verified on three real-world datasets, and the experimental results show that the proposed method outperforms the benchmark methods for entity alignment by a large margin.

关 键 词：实体对齐 图注意力网络 知识图谱 属性嵌入 对齐预测 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]