-
Notifications
You must be signed in to change notification settings - Fork 3.6k
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
CaptumExplainer
forward method
#6387
Conversation
Codecov Report
@@ Coverage Diff @@
## master #6387 +/- ##
==========================================
- Coverage 84.73% 84.70% -0.04%
==========================================
Files 395 395
Lines 21624 21666 +42
==========================================
+ Hits 18324 18353 +29
- Misses 3300 3313 +13
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
node_mask_type = self.explainer_config.node_mask_type | ||
edge_mask_type = self.explainer_config.edge_mask_type | ||
if node_mask_type is not None and edge_mask_type is not None: | ||
mask_type = 'node_and_edge' |
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.
Could we introduce these three mask types as an Enum? Also in captum.py
, possibly as a follow-up PR.
…h_geometric into captum_explainer_forward
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.
Looks good.
Lets add an issue to update https://pytorch-geometric.readthedocs.io/en/latest/notes/explain.html, to show HeteroExplanation
.
…h_geometric into captum_explainer_forward
CaptumExplainer
forward method
Defines Explainer.call for homogeneous/heterogeneous graphs (#6375)