We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
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?
The text was updated successfully, but these errors were encountered:
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。
Sorry, something went wrong.
No branches or pull requests
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?
The text was updated successfully, but these errors were encountered: