BriefGPT.xyz
Dec, 2019
元图: 元学习的少样本链接预测
Meta-Graph: Few shot Link Prediction via Meta Learning
HTML
PDF
Avishek Joey Bose, Ankit Jain, Piero Molino, William L. Hamilton
TL;DR
本文提出了一种基于元学习的Meta-Graph框架，该框架使用高阶梯度以及一个条件生成图神经网络初始化的学习图签名函数，可以在少量训练数据的情况下快速适应新图，并在收敛时获得更好的结果。
Abstract
Fast
adaptation
to new data is one key facet of human intelligence and is an unexplored problem on graph-structured data. Few-Shot Link Prediction is a challenging task representative of real world data with evolving sub-
→