融合多层次卷积神经网络的知识图谱嵌入模型  

Knowledge Graph Embedding Model Incorporating Multi-Level Convolutional Neural Networks

作　　者：李敏 李学俊[1] 廖竞[1] LI Min;LI Xuejun;LIAO Jing(School of Computer Science and Technology,Southwest University of Science and Technology,Mianyang,Sichuan 621010,China)

机构地区：[1]西南科技大学计算机科学与技术学院,四川绵阳621010

出　　处：《计算机工程与应用》2025年第6期192-198,共7页Computer Engineering and Applications

基　　金：国家自然科学基金(61872304)。

摘　　要：知识图谱嵌入将实体和关系投影到连续的低维嵌入空间中来学习三元组特征。基于翻译类的模型无法提取深层知识且特征表达能力有限,基于神经网络的模型虽然能提取出深层知识但容易丢失浅层知识,并且对于实体和关系间的特征交互能力较弱。为了在基于神经网络的模型中充分提取三元组浅层与深层特征,提出一种融合多层次卷积神经网络的知识图谱嵌入模型(ConvM),该模型使用头实体与关系交叉排列的重组嵌入方式来加强实体关系间的特征交互,并采用空洞卷积与一维、三维卷积核并列结合的特征提取模块来捕获实体关系间的多尺度交互特征,除此之外引入残差连接以改善原始信息遗忘问题。在五个公开数据集上对ConvM模型进行链接预测实验,实验结果表明,ConvM模型在FB15k、FB15k-237和Kinship数据集上的MRR指标相比ConvE模型分别提升了23.3%、10.8%、12.2%,体现了ConvM模型优秀的特征表达能力,有效提升了链接预测性能。Knowledge graph embedding projects entities and relations into a continuous low-dimensional embedding space to learn the triple features.The model based on translation cannot extract deep knowledge and has limited feature expression ability.Although the model based on neural network can extract deep knowledge,it is easy to lose shallow knowledge,and has weak feature interaction ability between entities and relations.In order to fully extract the shallow and deep features of triple in the model based on neural network,this paper introduces a knowledge graph embedding model incorporating multi-level convolutional neural networks called ConvM.ConvM model uses the recombination embedding method of cross-arrangement of head entities and relations to enhance the feature interaction between them.It also adopts the feature extraction module that combines dilated convolution with one-dimensional and three-dimensional convolution kernels to capture multiscale interaction features between entities and relations.In addition,ConvM model introduces a residual connection to improve the forgetting problem of original information.Five public datasets serve as the basis for conducting link prediction experiments.Experimental results demonstrate that ConvM model outperforms ConvE model,with MRR metric improved by 23.3%,10.8%,and 12.2%on FB15k,FB15k-237,and Kinship datasets,respectively.These findings highlight the outstanding feature expression capability of ConvM model and its effective enhancement of link prediction performance.

关 键 词：知识图谱嵌入 残差学习 卷积神经网络 链接预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]