计算机科学
嵌入
知识图
可扩展性
采样(信号处理)
图形
理论计算机科学
任务(项目管理)
构造(python库)
分层数据库模型
约束(计算机辅助设计)
数据挖掘
人工智能
数学
数据库
滤波器(信号处理)
几何学
经济
管理
程序设计语言
计算机视觉
作者
Zhenzhou Lin,Zhiqiang Zhao,Jingyou Xie,Ying Shen
标识
DOI:10.1145/3539618.3591996
摘要
Knowledge graph embedding aims at modeling knowledge by projecting entities and relations into a low-dimensional semantic space. Most of the works on knowledge graph embedding construct negative samples by negative sampling as knowledge graphs typically only contain positive facts. Although substantial progress has been made by dynamic distribution based sampling methods, selecting plausible and prior information-engaged negative samples still poses many challenges. Inspired by type constraint methods, we propose Hierarchical Type Enhanced Negative Sampling (HTENS) which leverages hierarchical entity type information and entity-relation cooccurrence information to optimize the sampling probability distribution of negative samples. The experiments performed on the link prediction task demonstrate the effectiveness of HTENS. Additionally, HTENS shows its superiority in versatility and can be integrated into scalable systems with enhanced negative sampling.
科研通智能强力驱动
Strongly Powered by AbleSci AI