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

Question on influence computation #30

Open
yushundong opened this issue Dec 20, 2021 · 1 comment
Open

Question on influence computation #30

yushundong opened this issue Dec 20, 2021 · 1 comment

Comments

@yushundong
Copy link

Hi, thanks for your amazing contribution of this Pytorch implementation!

Question on influence computation: as mentioned in function calc_s_test_single: s_test = invHessian * nabla(Loss(test_img, model params). However, as in Eq. (2) in the paper Understanding Black-box Predictions via Influence Functions, we should compute invHessian * nabla(Loss(train_img, model params). It seems that the positions of train and test image in Eq. (2) is switched.

Did I get anything wrong? Could you please provide more clue on that? Thanks so much for your information!
@lange-martin
Copy link

Have a look at chapter 3 in the paper: "Efficiently calculating influence". Here, s_test is definied as invHessian * nabla(Loss(test_img, params)).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@lange-martin @yushundong