Joint learning based on multi-shaped filters for knowledge graph completion

• 来源期刊: 高技术通讯（英文版）
• 年，卷（期）: 2021,（1）
• 页码范围: 43-52
• 页数: 10页
• 语种: 英文
• DOI: 10.3772/j.issn.1006-6748.2021.01.006

摘要

To solve the problem of missing many valid triples in knowledge graphs(KGs),a novel model based on a convolutional neural network(CNN)called ConvKG is proposed,which employs a joint learning strategy for knowledge graph completion(KGC).Related research work has shown the su-periority of convolutional neural networks(CNNs)in extracting semantic features of triple embed-dings.However,these researches use only one single-shaped filter and fail to extract semantic fea-tures of different granularity.To solve this problem,ConvKG exploits multi-shaped filters to co-con-volute on the triple embeddings,joint learning semantic features of different granularity.Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of dif-ferent granularity among triple elements.Experimental results confirm the strength of joint learning,and compared with state-of-the-art CNN-based KGC models,ConvKG achieves the better mean rank(MR)and Hits@10 metrics on dataset WN18RR,and the better MR on dataset FB15k-237.