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

论文中的Figure2里提到的Siamese encoder具体的内容是什么呢?分别是AE 和IGAE嘛? #14

Open
maymayuo opened this issue Oct 25, 2023 · 3 comments

Comments

@maymayuo
Copy link

FIgure2

@maymayuo maymayuo changed the title 论文中的Figure2里提到的Siamese encoder具体的内容是什么呢?分别是是AE 和IGAE嘛? 论文中的Figure2里提到的Siamese encoder具体的内容是什么呢?分别是AE 和IGAE嘛? Oct 25, 2023
@yueliu1999
Copy link
Owner

您好,感谢关注。是的,是AE和IGAE的孪生编码器。具体的代码可以在这里找到:
https://github.com/yueliu1999/DCRN/blob/main/DCRN.py#L47C3-L47C4
https://github.com/yueliu1999/DCRN/blob/main/DCRN.py#L131

@maymayuo
Copy link
Author

谢谢作者的回复!我现在对预训练模型中的结果z_tilde的含义和应用上产生了一些疑问,期待您的回答:
1)z_tidle应该是论文里框架图中的 Z吧?
2)如果是Z,而后在Z后进行Kmeans,我应该如何知道cite数据集中的3327个节点的哪些节点是属于类别1,哪些属于类别2,依次类推哪些节点属于类别6呢?

@yueliu1999
Copy link
Owner

1)嗯嗯,Z应该是框架图中的Z。
https://github.com/yueliu1999/DCRN/blob/main/DCRN.py#L259

2)这里cluster_id是每个样本的簇id。
https://github.com/yueliu1999/DCRN/blob/main/utils.py#L454

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