NVIDIA-Merlin / NVIDIA-Merlin/Transformers4Rec
Support to incremental training
Open
Nobody has claimed this yet.
Incremental training
- Dominant language
- Python
- Stars
- 1.3k
- Forks
- 165
- Avg merge
- 1m
- Merged PRs (30d)
- 2
Description
Extending the embedding tables of categorical features for new values seen on incremental training.
P.s. requires incremental preprocessing ( https://github.com/NVIDIA/NVTabular/issues/798 )
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 reading the linked NVTabular issue #798 about incremental preprocessing, then trace how categorical embedding tables are created and used during training. No source files or tests are named in this issue. Done means new categorical values can be handled during incremental training without breaking existing embeddings.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100