Fixed dropout instantiation in NGCF and GRU4RecKG forward. Moved dropout_prob in config for SimpleX. #1946
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
…out_prob in config for SimpleX.
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Outdated suggestions cannot be applied.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.
Some models were directly instantiating a dropout object in the forward function, such as NGCF. Calling model.eval() does not turn off dropout in these scenarios, leading to potential issues in the case a direct access to the forward function is done for whatever use.
For one of my projects, I indeed needed to regenerate the user and item embeddings by keeping constant the trained weights, but the predictions were inconsistent due to this issue.
I found this issue in NGCF and GRU4RecKG. While checking all the models, I also noticed that the dropout probability for SimpleX was hard-coded as 0.1, and I moved it to its config file.