IntSE:特征增强的知识图谱补全方法

IntSE:Feature Enhanced Knowledge Graph Completion Method

知识图谱补全旨在发现充分表达实体和关系语义关联的模型,从而依据已知实体和关系预测三元组中的缺失部分.InteractE是一种基于卷积神经网络的嵌入模型,通过棋盘结构重组实体和关系嵌入元素,增加实体和关系之间的特征交互信息从而表达实体和关系间更丰富的语义,提升知识图谱补全效果.然而棋盘结构增强特征交互的同时打乱实体和关系嵌入的空间结构信息,针对该问题,提出了一种改进InteractE的知识图谱补全方法——IntSE.IntSE采用SENet筛选InteractE特征映射中对知识图谱补全有益的特征通道信息,并抑制无用的特征通道信息,从而提升知识图谱补全效果.为了使得SENet更适用知识图谱补全任务,进一步改进SENet的门机制.在公开数据集FB15k-237和WN18RR上进行知识图谱补全实验,结果表明IntSE的性能较InteractE有一定提升,IntSE优于主流基于卷积神经网络的嵌入模型.

The purpose of knowledge graph completion is to find models that fully express the semantic associations between entities and relations,so as to predict the missing parts in the triad based on known entities and relations.InteractE model reconstructs the elements of entity and relation embedding through checkered structure,increases the characteristic interaction information between entities and relations,so as to expresses richer semantics between them,it achieves the best effect in the knowledge graph completion method based on convolutional neural network.However,the checkered structure enhances the interaction of features and at the same time disrupts the spatial structure information embedded in entities and relations.To solve this problem,this paper proposes an improved knowledge graph completion method of InteractE—IntSE.IntSE uses SENet to screen useful feature channel information for knowledge graph completion in InteractE feature mapping and suppress useless feature channel information,so as to improve the knowledge graph completion effect,so as to improve the completion effect of knowledge graph.In order to make SENet more suitable for the task of knowledge graph completion,the gate mechanism of SENet was further improved.The results of knowledge graph completion experiment on public datasets FB15k-237 and WN18RR show that the performance of IntSE is significantly improved compared with that of InteractE,and IntSE is superior to the mainstream embedded model based on convolution neural network.