BriefGPT.xyz
Mar, 2021
图神经网络应该使用特征、边或两者皆有?
Should Graph Neural Networks Use Features, Edges, Or Both?
HTML
PDF
Lukas Faber, Yifan Lu, Roger Wattenhofer
TL;DR
本文研究了图形分类问题中图神经网络是否必要,发现对于图分类来说,GNN不仅仅是其部分之和。同时,我们还发现,与特征不同,仅使用边进行预测的模型并不总是能够转换为GNN。
Abstract
graph neural networks
(GNNs) are the first choice for learning algorithms on graph data. GNNs promise to integrate (i)
node features
as well as (ii)
→