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.

Sign up for GitHub

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

Jump to bottom

邻接矩阵A的扩散步骤 #8

Open
zjucaoyz opened this issue Dec 26, 2023 · 7 comments
Open

邻接矩阵A的扩散步骤 #8

zjucaoyz opened this issue Dec 26, 2023 · 7 comments

Comments

@zjucaoyz
Copy link

您好，我想请问下原文中的邻接矩阵A在代码中是怎么体现迭代的？
@Steve-syd
Copy link

同问+1

@wangshanhu
Copy link

wangshanhu commented Dec 27, 2023 •
edited
Loading

同问+1, 并没有看见邻接矩阵的输入，这与论文中的FourierGNN(X,A)不相符啊

@aikunyi
Copy link
Owner

aikunyi commented Dec 27, 2023

Note that the hypervairate graph is a fully-connected graph.

@zjucaoyz
Copy link
Author

Note that the hypervairate graph is a fully-connected graph.

十分感谢回答。A初始化的时候确实都是1，但是第二次迭代是A1(A0XW0)W1，此时A1也都是1吗？论文中似乎提到diffusion step。代码中显示了不同的参数矩阵W，但A似乎一直都是1。

@aikunyi
Copy link
Owner

aikunyi commented Dec 30, 2023 •
edited
Loading

因为我们是在hypervariate graph上做的运算，所以A一直是1

@Steve-syd
Copy link

因为我们是在hypervariate graph上做的运算，所以A一直是1

请问您这里说的“一直是1”，意思是A一直是单位矩阵还是A一直是全1的邻接矩阵呢？

@lqf0624
Copy link

lqf0624 commented Sep 5, 2024

因为我们是在hypervariate graph上做的运算，所以A一直是1

如果A一直是1，为什么论文里说邻接矩阵是通过FourierGNN学到的？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
5 participants
@lqf0624 @aikunyi @Steve-syd @zjucaoyz @wangshanhu