Added the GraphMaskExplainer algorithm
#6284
Merged
Conversation
This file contains 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
for more information, see https://pre-commit.ci
Codecov Report
@@ Coverage Diff @@
## master #6284 +/- ##
==========================================
+ Coverage 85.51% 85.57% +0.06%
==========================================
Files 403 404 +1
Lines 22024 22313 +289
==========================================
+ Hits 18834 19095 +261
- Misses 3190 3218 +28
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
Closed
|
Hi @rusty1s , I am still seeking your attention on this. May I get some review comments on this PR, please?? Thank you... |
|
Yes, we discussed how to deal with this PR and have plans to move this to |
|
Yes, it will. Please move this PR to |
|
Hi @rusty1s, Any updates?? Can we do something to review and merge this PR ASAP?? |
rusty1s
changed the title
GraphMaskExplainer algorithm
rusty1s
approved these changes
Jan 21, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This PR contains implementation of how to compute
layer-wise weightsfor eachedgein order to produceexplanationsfornode-level,edge-level, andgraph-leveltasks. Furthermore, this implementation is different from authors' original implementation and is fast and more memory efficient than theirs. Have addedTestsandExamplesof the proposed implementation in order to make the overall approach understandable.