NVIDIA-Merlin / NVIDIA-Merlin/Transformers4Rec

[FEA] Support recurrence mechanism for Transformer architectures to deal with longer sequences

Open
#266 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status/needs-triage
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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.