BriefGPT.xyz
Sep, 2019
图卷积神经网络中节点汇聚的非负因式分解方法
A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks
HTML
PDF
Davide Bacciu, Luigi Di Sotto
TL;DR
该论文讨论了一种在图形结构数据中引入池化机制的方法，并将其作为图形卷积神经网络的组成部分。研究表明，这种粗化过程显著提高了模型的预测性能。
Abstract
The paper discusses a pooling mechanism to induce subsampling in graph structured data and introduces it as a component of a
graph convolutional neural network
. The pooling mechanism builds on the
non-negative matrix fa
→