tensorflow / tensorflow/recommenders
Loss function does not decrease and weights are not ben updated
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 300
- PR merge metrics
- No merged PRs in 30d
Description
I tried the retrieval model as in the tutorial with another dataset and loss function does not decrease and weights are not updated with each epoch, also after training with several epochs I found that all embeddings are identical. Someone can help me to know why is this happening? How can I fix it?
I'm training only with ids of users and items as in tutorial.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the retrieval model from the tutorial with the alternate dataset and user/item IDs described in the issue. Compare the loss, weight updates, and resulting embeddings across epochs. Done means the cause of the unchanged loss and identical embeddings is identified and a verified fix or reproduction result is documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100