-
Notifications
You must be signed in to change notification settings - Fork 21
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
[MRG] Add SPA method #276
[MRG] Add SPA method #276
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #276 +/- ##
===========================================
- Coverage 97.10% 77.12% -19.98%
===========================================
Files 61 52 -9
Lines 6382 5924 -458
===========================================
- Hits 6197 4569 -1628
- Misses 185 1355 +1170
|
skada/deep/_graph_alignment.py
Outdated
loss_adv = self.domain_criterion_( | ||
domain_pred_s, domain_label | ||
) + self.domain_criterion_(domain_pred_t, domain_label_target) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
in eq (1) of the paper, they use both the cross entropy and the modified cross entropy loss (log(1-prob))
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we should also use label smoothing as the code of the paper: https://github.com/CrownX/SPA/blob/main/code/loss.py#L65-L84
Nice results with SPA, lets merge this now! |
https://arxiv.org/pdf/2310.17594