[目的]通过调研和梳理文献,总结基于图神经网络的知识图谱补全方法.[文献范围]以"Knowledge Graph Completion"、"知识图谱补全"作为检索词在Web of Science、DBLP和CNKI数据库中进行检索,共筛选出79篇文献.[方法]分别归纳总结图卷积神经网络、图注意力网络、图自动编码网络三种基于图神经网络的知识图谱补全方法类别,并对每种类别的技术脉络、典型方法、模型框架优缺点等进行对比论述.[结果]运用知识图谱补全任务的常用数据集和评价指标,从MRR、MR、Hit@k等性能评价角度对各类模型的效果进行对比分析,并对未来研究提出展望.[局限]在实验结果对比中,只讨论了FB15K-237和WN18RR数据集上部分应用较广的模型的评估结果,缺乏全部模型在同一数据集上的对比.[结论]相比基于表示学习模型和基于神经网络模型,基于图神经网络模型具有更好的图谱补全性能,但模型关系复杂性高、过平滑、可扩展性通用性差,这也是未来研究要解决的问题.
An Overview of Research on Knowledge Graph Completion Based on Graph Neural Network
[Objective]This paper summarizes the knowledge graph completion methods based on graph neural network through research and literature review.[Coverage]With"knowledge graph completion"as search terms to retrieve literature from the Web of Science,DBLP and CNKI,a total of 79 representative literature were screened out for review.[Methods]Based on the model structure,three knowledge graph completion methods based on graph neural networks were summarized,including graph convolutional neural networks,graph attention networks,and graph auto encoder.[Results]Using common data sets and evaluation indicators for knowledge graph completion tasks,the effects of various models were comparatively analyzed in terms of MRR,MR,Hit@k and other performance evaluations,and prospects for future research were suggested.[Limitations]In the comparison of experimental results,only the evaluation results of some widely used models on the FB15K-237 and WN18RR datasets are discussed,the comparison of all models on the same dataset is lacking.[Conclusions]Compared with the representation learning model and the neural network model,the graph neural network model has better performance,but it still faces difficulties such as high complexity of model relationships,over-smoothness,and poor scalability and universality.
NETL
NSTL
万方数据
