bugfix: Second GNNExplainer with custom config overwrites first #10257
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
rusty1s
approved these changes
May 20, 2025
chrisn-pik
pushed a commit
to chrisn-pik/pytorch_geometric
that referenced
this pull request
Jun 30, 2025
…team#10257) Here's an example test program ``` python from torch_geometric.explain.algorithm.gnn_explainer import GNNExplainer summing_explainer = GNNExplainer(edge_reduction='sum') multiplying_explainer = GNNExplainer(edge_reduction='prod') print(summing_explainer.coeffs['edge_reduction']) ``` Without the bugfix, this prints "prod" even though it's printing the edge_reduction for the **summing_explainer**. This is because `GNNExplainer.coeffs` is a class-level variable. When we instantiate multiplying_explainer, it overwrites GNNExplainer.coeffs['edge_reduction'] which is the same dictionary item summing_explainer uses. The bugfix renames GNNExplainer.coeffs to GNNExplainer.default_coeffs, and each GNNExplainer instance gets its own copy of the coeffs dict, so they don't step on one another.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Here's an example test program
Without the bugfix, this prints "prod" even though it's printing the edge_reduction for the summing_explainer. This is because
GNNExplainer.coeffsis a class-level variable. When we instantiate multiplying_explainer, it overwrites GNNExplainer.coeffs['edge_reduction'] which is the same dictionary item summing_explainer uses.The bugfix renames GNNExplainer.coeffs to GNNExplainer.default_coeffs, and each GNNExplainer instance gets its own copy of the coeffs dict, so they don't step on one another.