BriefGPT.xyz
Feb, 2018
GraphVAE: 使用变分自编码器生成小图
GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
HTML
PDF
Martin Simonovsky, Nikos Komodakis
TL;DR
本文提出一种基于变分自编码器的方法，通过直接输出预先定义大小的概率性的全连接图来解决学习图嵌入任务中的线性化困境，并在分子生成任务中进行了评估。
Abstract
deep learning
on
graphs
has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks, which is in contrast with advances in
→