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

Loss_MIT wrong? #32

Closed
lcnnnn opened this issue Jan 19, 2024 · 8 comments
Closed

Loss_MIT wrong? #32

lcnnnn opened this issue Jan 19, 2024 · 8 comments

Comments

@lcnnnn
Copy link

lcnnnn commented Jan 19, 2024

I saw that the loss of MIT computaion in core.py was
'MIT_loss = self.customized_loss_func(
X_tilde_3, inputs["X_ori"], inputs["indicating_mask"]
)'
,which computed the MAE between M~3 and X_ori and differed to the paper.

@WenjieDu
Copy link
Owner

Hi there,

Thank you so much for your attention to SAITS! If you find SAITS is helpful to your work, please star⭐️ this repository. Your star is your recognition, which can let others notice SAITS. It matters and is definitely a kind of contribution.

I have received your message and will respond ASAP. Thank you again for your patience! 😃

Best,
Wenjie

@WenjieDu
Copy link
Owner

The imputation values for X are from X_tilde_3, hence it is fine.

@lcnnnn
Copy link
Author

lcnnnn commented Jan 19, 2024

Thank you for your reply , I know that the imputation values for X are from X_tilde_3, just as the code shows:

combine X_tilde_1 and X_tilde_2

    X_tilde_3 = (1 - combining_weights) * X_tilde_2 + combining_weights * X_tilde_1
    # replace non-missing part with original data
    X_c = masks * X + (1 - masks) * X_tilde_3

but the equation in paper is L_MIT=MAE(X_c,X,I)

@WenjieDu
Copy link
Owner

Yes, but as I said, the code logic here is right. The parts for loss calculation in L_MIT=MAE(X_c,X,I) and
MIT_loss = self.customized_loss_func(X_tilde_3, inputs["X_ori"], inputs["indicating_mask"]) both determined by indicating_mask, i.e., the term I, and they are the same. You can try to replace X_tilde_3 with X_c, the MIT_loss result will not change.

@lcnnnn
Copy link
Author

lcnnnn commented Jan 19, 2024 via email

@WenjieDu
Copy link
Owner

My pleasure. If you're working on time series imputation, our recent survey work https://github.com/WenjieDu/Awesome_Imputation may be helpful to you. The benchmark code has been open source, and the preprint paper will be released soon.

@lcnnnn
Copy link
Author

lcnnnn commented Jan 19, 2024 via email

@WenjieDu
Copy link
Owner

I am closing this issue because the proposed questions have been solved. If you have further concerns, reopening it will be welcome.

BTW, you can also join our PyPOTS community to discuss research related to partially-observed time series data.

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