Fixed dropout instantiation in NGCF and GRU4RecKG forward. Moved dropout_prob in config for SimpleX. #1946
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Outdated suggestions cannot be applied.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.