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

超图如何采集负样本? #28

Open
yw155 opened this issue Dec 27, 2022 · 4 comments
Open

超图如何采集负样本? #28

yw155 opened this issue Dec 27, 2022 · 4 comments
Assignees
Labels
question Further information is requested

Comments

@yw155
Copy link

yw155 commented Dec 27, 2022

您好,有个问题想向您请教下。

对于超图的监督学习,当采用二值化交叉熵损失函数,负样本空间中的组合情况特别多,这时负的超边该如何采样呢?

谢谢!

@yifanfeng97
Copy link
Member

请问,您的任务是要做超边的链路预测吗?

@yw155
Copy link
Author

yw155 commented Dec 27, 2022

@yifanfeng97 嗯嗯,是的,想对超边进行预测,而且正边的样本是稀疏的,可以怎么处理呢?

谢谢!

@yifanfeng97
Copy link
Member

@yw155
确实,超边可以连接超过两个点,有更高的建模自由度,但是也整个预测空间也指数级增长。我建议加一些约束,最简单就是只预测三个点的超边,或者你把正样本的超边中一个点替换成随机其他点,来构造负样本试试。

@yifanfeng97 yifanfeng97 added the question Further information is requested label Dec 27, 2022
@yw155
Copy link
Author

yw155 commented Dec 27, 2022

好的,谢谢回复!

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

No branches or pull requests

3 participants