NVIDIA-Merlin / NVIDIA-Merlin/Transformers4Rec
[FEA] Support recurrence mechanism for Transformer architectures to deal with longer sequences
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.3k
- Forks
- 165
- Avg merge
- 1m
- Merged PRs (30d)
- 2
Description
🚀 Feature request
Some HF Transformer architectures support the recurrence mechanism, which allow for processing segments of a sequence and leveraging learnings from past segments, like XLNET and Transformer-XL.
This new feature is about making it possible to use recurrence mechanism with long sequences of user interactions.
P.s. it need to be investigated if there are data loading requirements to work with the sequence segments
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
The issue does not name files, tests, or an entry point. Begin by investigating how supported Hugging Face architectures represent recurrence and whether data loading must expose sequence segments; done means recurrence can process long user-interaction sequences with the required data-loading behavior defined.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, 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