BriefGPT.xyz
Jul, 2022
KG-NSF: 无负样本的知识图谱补全方法
KG-NSF: Knowledge Graph Completion with a Negative-Sample-Free Approach
HTML
PDF
Adil Bahaj, Safae Lhazmir, Mounir Ghogho
TL;DR
通过交叉相关矩阵，提出一种克服负采样限制，能够快速学习知识图谱（KG）嵌入的负采样免费框架（KG-NSF），其具有与基于负采样的方法相当的链接预测性能，同时收敛更快。
Abstract
knowledge graph
(KG) completion is an important task that greatly benefits knowledge discovery in many fields (e.g. biomedical research). In recent years, learning
kg embeddings
to perform this task has received
→