摘要
知识图谱嵌入(KGE)将实体和关系映射到低维连续向量空间中,以利用机器学习方法实现关系数据的应用,如知识分析、推理、补全等。以ConvE为代表将卷积神经网络(CNN)应用于知识图谱嵌入中,以捕捉实体和关系的交互信息,但其标准卷积捕捉特征交互信息能力不足,特征表达能力低下。针对特征交互能力不足问题,提出了一种改进的Inception结构,在此基础上构建一个知识图谱嵌入模型InceE。首先,该结构使用混合空洞卷积替代标准卷积,以提高特征交互信息捕捉能力;其次,使用残差网络结构,以减少特征信息丢失。实验使用基准数据集Kinship、FB15k、WN18验证InceE链接预测有效性。在Kinship、FB15k数据集上,相较于ArcE和QuatRE模型,InceE的Hit@1分别提升了1.6和1.5个百分点;在三个数据集上,与ConvE对比,InceE的Hit@1分别提升了6.3、20.8和1.0个百分点。实验结果表明InceE具有更强的特征交互信息捕捉能力。
KGE(Knowledge Graph Embedding)maps entities and relationships into a low-dimensional continuous vector space,uses machine learning methods to implement relational data applications,such as knowledge analysis,reasoning,and completion.Taking ConvE(Convolution Embedding)as a representative,CNN(Convolutional Neural Network)is applied to knowledge graph embedding to capture the interactive information of entities and relationships,but the ability of the standard convolutional to capture feature interaction information is insufficient,and its feature expression ability is low.Aiming at the problem of insufficient feature interaction ability,an improved Inception structure was proposed,based on which a knowledge graph embedding model named InceE was constructed.Firstly,hybrid dilated convolution replaced standard convolution to improve the ability to capture feature interaction information.Secondly,the residual network structure was used to reduce the loss of feature information.The experiments were carried out on the datasets Kinship,FB15k,WN18 to verify the effectiveness of link prediction by InceE.Compared with ArcE and QuatRE models on the Kinship and FB15k datasets,the Hit@1 of InceE increased by 1.6 and 1.5 percentage points;compared with ConvE on the three datasets,the Hit@1 of InceE increased by 6.3,20.8,and 1.0 percentage points.The experimental results show that InceE has a stronger ability to capture feature interactive information.
作者
余晓鹏
何儒汉
黄晋
张俊杰
胡新荣
YU Xiaopeng;HE Ruhan;HUANG Jin;ZHANG Junjie;HU Xinrong(Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion(Wuhan Textile University),Wuhan Hubei 430200,China;School of Computer Science and Artificial Intelligence,Wuhan Textile University,Wuhan Hubei 430200,China;Engineering Research Center of Hubei Province for Clothing Information(Wuhan Textile University),Wuhan Hubei 430200,China)
出处
《计算机应用》
CSCD
北大核心
2022年第4期1065-1071,共7页
journal of Computer Applications
基金
湖北省教育厅科学技术研究计划重点项目(20141603)。