曲阜师范大学学报（自然科学版）2024，Vol.50Issue(2)：93-99,7.DOI:10.3969/j.issn.1001-5337.2024.2.093
基于多尺度卷积的胶囊网络知识图谱嵌入模型
Knowledge graph embedding model based on multi-scale convolution of capsule network
摘要
Abstract
This paper is based on the excellent dimensional information mining ability of capsule neural networks,and incorporates multi-scale convolution to further enhance their feature extraction and interac-tion capabilities.A capsule network knowledge graph embedding model based on multi-scale convolution is proposed.Firstly,the initialization embedding vectors for entities and relationships are trained using the TransE algorithm.Secondly,different feature maps are generated through multi-scale convolution,and the resulting feature maps are fused to form corresponding capsules.Finally,dynamic routing is used to speci-fy the connection from the first layer capsule to the second layer capsule.The second layer capsule obtained through routing is then used to obtain the final vector length using the squash function,which determines the confidence level of the triplet.Compared with the embedding models CapsE,the proposed model in this paper has a 1.8％improvement in Hit@10 and 1.4％improvement in MRR metrics on the WN18RR dataset,and a 2.2％improvement in Hit@10 and 4.8％improvement in MR on the FB15k-237 dataset.关键词
知识图谱/多尺度卷积/胶囊网络/知识图谱嵌入/神经网络Key words
knowledge graph/multi-scale convolution/capsule network/knowledge graph embed-ding/neural network分类
信息技术与安全科学引用本文复制引用
周淑霄,王艳娜,周子力,王妍,董兆安..基于多尺度卷积的胶囊网络知识图谱嵌入模型[J].曲阜师范大学学报（自然科学版）,2024,50(2):93-99,7.基金项目
山东省自然科学基金(ZR2020MF149) （ZR2020MF149）
山东省高校科技计划(J18KB161) （J18KB161）
教育部产学合作协同育人项目(202102291003). （202102291003）
