MetaP: Meta Pattern Learning for One-Shot Knowledge Graph Completion

1 code implementation • SIGIR 2021 2021 • Zhiyi Jiang, Jianliang Gao, Xinqi Lv

In this paper, we propose a meta pattern learning framework (MetaP) to predict new facts of relations under a challenging setting where there is only one reference for each relation.

Information Retrieval Relation +1