超网络知识图谱嵌入

Aug, 2018

Hypernetwork Knowledge Graph Embeddings

Ivana Balazevic, Carl Allen, Timothy M. Hospedales

TL;DR本文提出一种基于超网络结构的张量分解方法，用于实现知识图谱中链接预测任务，取得了比ConvE和所有以前的方法更好的性能表现，同时能够作为张量分解模型的一种简化（相比较于卷积神经网络方法）而得到推广。

Abstract

knowledge graphs are large graph-structured databases of facts, which typically suffer from incompleteness. link prediction is the task of inferring missing relations (links) between entities (nodes) in a knowled