Minor improvement to FakeDataset #4065
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
|
Seems I need to update the tests and also some bugs in this PR. |
arunppsg
force-pushed
the
fakedataset
branch
from
2840bc1
to
76946ad
Compare
|
Some tests are failing at an assertion for I am not sure how to handle it here. Can you help me here @rusty1s to get this merged in? Thanks! |
|
How about we only offset node features? |
Sounds good. In the last update I made offset to only node features and it passes the test case. Thanks! |
|
Super :) |
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Outdated suggestions cannot be applied.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.
I have made a small improvement to
FakeDatasetclass.The node features and edge features generated have same distribution across different labels. I made a small fix to make them have different mean across different labels. This will help when the fake dataset is used for training and testing models. Earlier, since distributions of node features and edge features where same across different labels, a model could not learn effectively.