BriefGPT.xyz
Feb, 2023
基于嵌入式知识图谱补全的度偏置研究
Toward Degree Bias in Embedding-Based Knowledge Graph Completion
HTML
PDF
Harry Shomer, Wei Jin, Wentao Wang, Jiliang Tang
TL;DR
本文讨论如何应对知识图谱补全中存在的度量偏差，提出了一种新的数据增强方法KG-Mixup，并进行了广泛的实验验证。
Abstract
A fundamental task for
knowledge graphs
(KGs) is knowledge graph
completion
(KGC). It aims to predict unseen edges by learning representations for all the entities and relations in a KG. A common concern when lea
→