-
Notifications
You must be signed in to change notification settings - Fork 471
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
Feature attribution for darts model #1235
Comments
Hi there 👋 I am also interested in this question |
+1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
❓ Questions and Help
Hi, I've been working on FeatureExplainer for probabilistic TiDE model and eventually came up with this solution:
Basically, it's feature ablation approach with additional darts-to-torch transformations.
My question is: is there any way to apply gradient-based attribution method to a model with output of shape
(batch_size, n_timestamps, n_targets)
? If not, is a perturbation/permutation method the only option for a forecasting model?The text was updated successfully, but these errors were encountered: