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

互信息上界交流 #1

Open
junkangwu opened this issue Dec 22, 2020 · 0 comments
Open

互信息上界交流 #1

junkangwu opened this issue Dec 22, 2020 · 0 comments

Comments

@junkangwu
Copy link

抱歉打扰您~
我是在CLUB模型的issue中看到您和我有类似的训练问题,请问能否添加一个联系方向交流一下最小化互信息上界实现disentangle的思想?我训练自己模型中也出现了无法收敛的问题,具体情况为:

  1. 按照club论文及其中例子所示,第一步训练log likehood �q(y|x),此时应当将encoder模型参数固定,而开放CLUB互信息学习模型参数;而第二部计算分类生成损失以及互信息上界时,此时CLUB参数应当固定,更新encoder参数。我一开始并没有对训练过程中参数进行固定或者开放,出现的情况为,upbound_loss从正逐渐降低,并且变为负数一直无法收敛;而今天意识到参数学习次序,即有选择性释放或者固定相应模型参数时,lld_loss维持在很高的水平(50左右)而互信息上界则由正数变为负数到-4慢慢从负数方向靠近0值附近。
  2. 请问您目前相关研究进展怎样,如果有相同类似的目的,希望能够一起交流学习学习!感谢!

如有打扰,请多包涵!

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

1 participant