Anytime Bottom-Up Rule Learning for Knowledge Graph Completion

doi:10.24963/ijcai.2019/435

Anytime Bottom-Up Rule Learning for Knowledge Graph Completion

2019-08-01

0

OA

AI

DOI：10.24963/ijcai.2019/435

原文链接

原文求助

摘要

En 中文

We propose an anytime bottom-up technique for learning logical rules from large knowledge graphs. We apply the learned rules to predict candidates in the context of knowledge graph completion. Our approach outperforms other rule-based approaches and it is competitive with current state of the art, which is based on latent representations. Besides, our approach is significantly faster, requires less computational resources, and yields an explanation in terms of the rules that propose a candidate.

Anytime Bottom-Up Rule Learning for Knowledge Graph Completion

摘要

期刊

机构

引用论文