Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

无特征节点 #59

Open
mao1207 opened this issue Feb 18, 2024 · 1 comment
Open

无特征节点 #59

mao1207 opened this issue Feb 18, 2024 · 1 comment

Comments

@mao1207
Copy link

mao1207 commented Feb 18, 2024

在异构图中,节点往往缺乏自然属性,常见的做法是采用one-hot编码或随机向量作为节点特征。我对于这种人为定义特征的影响感到困惑,不确定它们对最终结果的影响程度。特别是在复现论文或者和将自己的方法与其他baseline比较时,由于实验设置的不同,比如对数据集无特征节点处理方法的不同,自己复现的方法往往和原论文有一些出入,请问您怎么看待这种差异呢?

@1049451037
Copy link
Member

1049451037 commented Feb 19, 2024

one-hot和随机初始化是等价的,可以认为随机初始化就是one-hot接了一个nn.Linear。虽然每个节点都是one-hot特征,但是由于GNN的邻居聚合特性,可以将相邻的节点随着层数堆叠变得相近。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants