图神经网络应该使用特征、边或两者皆有？

Mar, 2021

Should Graph Neural Networks Use Features, Edges, Or Both?

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)