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

请教用MMOE解决回归和分类任务 #1

Open
zoe218 opened this issue Jul 6, 2021 · 5 comments
Open

请教用MMOE解决回归和分类任务 #1

zoe218 opened this issue Jul 6, 2021 · 5 comments

Comments

@zoe218
Copy link

zoe218 commented Jul 6, 2021

Hello~
最近遇到多目标学习的问题,用一个模型学习回归和分类任务,但是用MMOE结果很异常。
要是想适应回归和分类任务,你对如何修改MMOE有什么建议么?

@huangjunheng
Copy link
Owner

我的理解 多任务学习需要确保2个任务最起码是有一定相关性的 完全无关的任务 不适合用多任务学习

@lixingyuan1998
Copy link

您好请问数据是有的train_data, train_label, validation_data, validation_label, test_data, test_label直接跑会报错
raise ValueError("{0} format is not supported".format(y_type))
ValueError: unknown format is not supported

@lixingyuan1998
Copy link

解决了 roc_auc_score 不支持tensor需要转化一下 还是谢谢啦~

@IrvingZJU
Copy link

Hello~ 最近遇到多目标学习的问题,用一个模型学习回归和分类任务,但是用MMOE结果很异常。 要是想适应回归和分类任务,你对如何修改MMOE有什么建议么?

首先任务要有一定的相关性,回归和分类是可以多任务的,就是一个Tower多一个sigmoid或softmax,然后损失函数不同罢了,需要注意两个loss的量级要尽量接近。

@Wsy002
Copy link

Wsy002 commented Mar 26, 2022

解决了 roc_auc_score 不支持tensor需要转化一下 还是谢谢啦~

你好想请问下要怎么更改呢 一样遇到这个问题

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