Skip to content

关于源域和辅域权重的问题 #7

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

Open
zhangjiantianyasmile opened this issue Mar 4, 2018 · 4 comments
Open

关于源域和辅域权重的问题 #7

zhangjiantianyasmile opened this issue Mar 4, 2018 · 4 comments

Comments

@zhangjiantianyasmile
Copy link

你好,很抱歉,又来打扰。
看到你把源域和辅域权重的更新又修改为戴文渊paper中提到的更新方式,我想冒昧的问一下,你是在哪些数据集上做的验证证明戴的方法是可以收敛的?
我怎么是在你之前提到的权重更新方式下才能收敛,戴的方法不能收敛呢?

@yuliang-liang
Copy link

我也是这个问题,两种权重我都实验了,第一次迭代就error rate就等于0,实际test并不好,求教该什么原因,负迁移么?

@MrDavidG
Copy link

@vilin777 @zhangjiantianyasmile 我也遇到了这个问题, 按照icml 2007上面tradaboost的权重更新方法复现了只有数值型特征的mushroom数据集上的实验,是无法收敛的,加权错误率始终在0.5左右。而按照作者更改之前的tradaboost更新方法(即beta_t是1,beta是-1),实验反而收敛了。。很奇怪

@leiseraiesecqd
Copy link

第一次迭代error rate就等于0是因为决策树函数的问题,希望能对大家有帮助,需要设置max_depth, min_samples_leaf这两个参数哈,具体见最新的那个issue。

@SAwxl
Copy link

SAwxl commented Apr 16, 2019

@MrDavidG 你好,请问 作者更改之前的tradaboost更新方法(即beta_t是1,beta是-1) 具体是怎么更新的呢?我目前也在使用tradaboost做训练。谢谢

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

5 participants