LightGCN bug fixes
#7384
Merged
LightGCN bug fixes
#7384
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
1. In BPRLoss(_Loss)::forward, log_prob is divided by n_pairs twice. Changed the return clause to: return -log_prob + regularization / n_pairs 2. In LightGCN()::recommendation_loss, it calls BPRLoss::forward and passes in the embeddings of all nodes. It should pass in only the embeddings of the nodes in the mini-batch.
2. Fix LightGCN()::forward return type
Codecov Report
@@ Coverage Diff @@
## master #7384 +/- ##
==========================================
- Coverage 91.71% 91.32% -0.40%
==========================================
Files 440 440
Lines 24561 24560 -1
==========================================
- Hits 22526 22429 -97
- Misses 2035 2131 +96
... and 20 files with indirect coverage changes 📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
rusty1s
approved these changes
May 19, 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Outdated suggestions cannot be applied.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.
In BPRLoss(_Loss)::forward, log_prob is divided by n_pairs twice. Changed the return clause to: return -log_prob + regularization / n_pairs
In LightGCN()::recommendation_loss, it calls BPRLoss::forward and passes in the embeddings of all nodes. It should pass in only the embeddings of the nodes in the mini-batch.