曲阜师范大学学报（自然科学版）2024，Vol.50Issue(1)：72-76,5.DOI:10.3969/j.issn.1001-5337.2024.1.072
基于图注意力网络的小样本知识图谱补全
Graph attention network for few-shot knowledge graph completion
摘要
Abstract
In this paper,we propose a few-shot knowledge graph completion method based on Graph Attention Network(GAT),which gives different weights to neighbors through the attention mechanism of GAT to generate a more powerful feature representation.By matching the query set and reference set through the matching network,the candidate entity with the highest similarity score is selected as the com-pleted tail entity.The experimental results show that the graph attention network can effectively predict the missing links in the few-shot knowledge graph.关键词
知识图谱补全/链接预测/小样本学习/图注意力网络Key words
knowledge graph completion/link prediction/few-shot learning/graph attention network分类
信息技术与安全科学引用本文复制引用
闵雪洁,王艳娜,周子力,王妍,董兆安..基于图注意力网络的小样本知识图谱补全[J].曲阜师范大学学报（自然科学版）,2024,50(1):72-76,5.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）
