BriefGPT.xyz
Jun, 2022
测量和优化图神经网络中图形信息的使用
Measuring and Improving the Use of Graph Information in Graph Neural Networks
HTML
PDF
Yifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma...
TL;DR
本文介绍了一种上下文环境下的图神经网络框架，提出了两个平滑度度量标准来衡量从图形数据中获得的信息的数量和质量，并设计了一种新的 GNN 模型 CS-GNN 来改善基于图形的信息的利用。结果表明，在不同类型的真实图中，CS-GNN 的性能优于现有模型。
Abstract
graph neural networks
(GNNs) have been widely used for
representation learning
on graph data. However, there is limited understanding on how much performance GNNs actually gain from graph data. This paper introdu
→