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

关于损失函数 #18

Open
ChenyuxinXMU opened this issue Feb 8, 2023 · 5 comments
Open

关于损失函数 #18

ChenyuxinXMU opened this issue Feb 8, 2023 · 5 comments

Comments

@ChenyuxinXMU
Copy link

您好,
我尝试用您的模型跑自己的数据集(两个视图),但是出现了对比损失为负数,且聚类指标越来越低的情况。这可能是什么原因呢?

@Lin-Yijie
Copy link
Collaborator

您好,对比损失代码实现时为最小化负的互信息,所以负值是正常情况。
聚类指标低可能需要调整超参数,比如loss.py中的lamb,可以设为0试试。同时可以调整重建和预测损失的权重。上述超参数均在configure.py中配置。

@ChenyuxinXMU
Copy link
Author

ChenyuxinXMU commented Feb 8, 2023 via email

@Lin-Yijie
Copy link
Collaborator

@ChenyuxinXMU 感谢您的关注!

  1. 设置了missing_rate后代码会自动将数据集进行缺失处理,加上mask。如果设置为0则不会进行处理。
  2. 我们在期刊版本中提供了多个视图的扩展方案,目前提供了3个view的代码实现。请见Dual Contrastive Prediction for Incomplete Multi-View Representation Learning

@ChenyuxinXMU
Copy link
Author

@ChenyuxinXMU 感谢您的关注!

  1. 设置了missing_rate后代码会自动将数据集进行缺失处理,加上mask。如果设置为0则不会进行处理。
  2. 我们在期刊版本中提供了多个视图的扩展方案,目前提供了3个view的代码实现。请见Dual Contrastive Prediction for Incomplete Multi-View Representation Learning

十分感谢您的解答!

@ChenyuxinXMU
Copy link
Author

ChenyuxinXMU commented Mar 22, 2023 via email

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