tensorflow / tensorflow/recommenders
[Question] Support for other loss functions.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 300
- PR merge metrics
- No merged PRs in 30d
Description
This question is very broad and theoretical so apologies for that!
I would love to learn more about various loss functions which could be implemented in tfrs - when looking at other libs such lightfm, most will support a few loss functions.
I feel a tutorial on alternative loss functions would be excellent for example: https://github.com/tensorflow/addons/blob/master/tensorflow_addons/losses/triplet.py Using this function naively does not work - due to a data mismatch.
Thanks in advance!
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 reviewing the question and the linked TensorFlow Addons triplet loss implementation. Investigate why using that loss naively causes a data mismatch in TFRS, then determine which alternative loss functions and tutorial scope are appropriate. Done means a decided, working tutorial with an example that demonstrates the supported data flow.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100