NVIDIA-Merlin / NVIDIA-Merlin/Merlin

[QST] Can I use customer embeddings and the item embeddings generated using Merlin two tower model for other downstream tasks ?

Open
#910 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Python
Stars
907
Forks
129
PR merge metrics
No merged PRs in 30d

Description

❓ Questions & Help

Details

  1. Once I train the merlin two tower model with sufficient data , Can I use the customer embeddings and the item embeddings generated during this process for other machine learning downstream tasks ?

  2. I have just started exploring Merlin Models. Currently working with DLRM models
    https://github.com/NVIDIA-Merlin/models/blob/main/examples/02-Merlin-Models-and-NVTabular-integration.ipynb

I wanted to check if there a way to retrieve/extract embeddings of users and movies once DLRM model is trained ?

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

Start with the linked Merlin Models and NVTabular integration notebook, then inspect the documented DLRM and two-tower model usage. Determine whether trained user and item embeddings are exposed for downstream tasks, and document the supported extraction path or limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.