Knowledge Graph Completion Based on GCN of Multi-Information Fusion and High-Dimensional Structure Analysis Weight  

作　　者：NIU Haoran HE Haitao FENG Jianzhou NIE Junlan ZHANG Yangsen REN Jiadong 

机构地区：[1]Yanshan University,Qinhuangdao 066004,China [2]Beijing Information Science and Technology University,Beijing 100096,China

出　　处：《Chinese Journal of Electronics》2022年第2期387-396,共10页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(61602401,61772449);Scientific and Technological Research Projects of Colleges and Universities in Hebei Province(QN2018074);Nature Scientist Fund of Hebei Province(F2019203157)。

摘　　要：Knowledge graph completion(KGC)can solve the problem of data sparsity in the knowledge graph.A large number of models for the KGC task have been proposed in recent years.However,the underutilisation of the structure information around nodes is one of the main problems of the previous KGC model,which leads to relatively single encoding information.To this end,a new KGC model that encodes and decodes the feature information is proposed.First,we adopt the subgraph sampling method to extract node structure.Moreover,the graph convolutional network(GCN)introduced the channel attention convolution encode node structure features and represent them in matrix form to fully mine the node feature information.Eventually,the high-dimensional structure analysis weight decodes the encoded matrix embeddings and then constructs the scoring function.The experimental results show that the model performs well on the datasets used.

关 键 词：Knowledge graph completion Graph convolutional network Channel attention convolution High-dimensional structure analysis weight 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] O157.5[自动化与计算机技术—控制科学与工程]