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.

Sign up for GitHub

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

Jump to bottom

PaddlePaddle中使用GBDT、FM的疑问 #3971

Closed
buptwds opened this issue Sep 8, 2017 · 4 comments
Closed

PaddlePaddle中使用GBDT、FM的疑问 #3971

buptwds opened this issue Sep 8, 2017 · 4 comments
Assignees
@lcy-seso
Labels
question

Comments

@buptwds
Copy link

buptwds commented Sep 8, 2017

在ctr预估中，现在使用的是LR，然后尝试了Wide&Deep，效果并没有提升。现在想做一些特征的组合，网上查阅资料说GBDT、FM的效果比较好，想问一下在PaddlePaddle中应该如何使用，或者PaddlePaddle中是否有可替代的模型？或者对于ctr预估还有其他什么建议吗？注：目前的训练集是01稀疏矩阵
@lcy-seso
Copy link
Contributor

lcy-seso commented Sep 8, 2017 •
edited
Loading

GBDT 完全是树模型那一套，和神经网络不是一套方法。
FM paddle 现在不支持，没有完成FM运算的层。

@buptwds
Copy link
Author

buptwds commented Sep 8, 2017

那像我现在这种情况（01稀疏矩阵的ctr预估），有什么好的建议吗

@lcy-seso
Copy link
Contributor

其它用户也提出过关于 FM 层的问题 #3664 ， Paddle暂时不支持，我们会考虑添加，计划待定。

@lcy-seso lcy-seso self-assigned this Sep 29, 2017
@will-am will-am mentioned this issue Nov 27, 2017
Merged
@jacquesqiao
Copy link
Member

FM is supported, and GBDT will not be supported by PaddlePaddle.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@lcy-seso lcy-seso

Labels
question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@jacquesqiao @lcy-seso @buptwds @chengduoZH