BriefGPT.xyz
Sep, 2018
基于生成对抗网络的图半监督学习
Semi-supervised Learning on Graphs with Generative Adversarial Nets
HTML
PDF
Ming Ding, Jie Tang, Jie Zhang
TL;DR
研究使用生成式对抗网络来帮助半监督图学习,提出GraphSGAN方法,在该方法中,生成器和分类器网络进行竞争性博弈,生成器通过在子图之间的低密度区域生成假样本来平衡,分类器通过隐式考虑子图密度属性来区分真实样本和假样本。实验结果表明,GraphSGAN显著优于几种现有方法。
Abstract
We investigate how
generative adversarial nets
(GANs) can help
semi-supervised learning
on
graphs
. We first provide insights on working pr
→