tensorflow / tensorflow/recommenders
[Question] How to use Attention to aggregate history?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 300
- PR merge metrics
- No merged PRs in 30d
Description
@OmarMAmin mentioned Exploring Heterogeneous Metadata for Video Recommendation with
Two-tower Model paper in this discussion.
I read through the paper multiple times and a few resources about existing Attention mechanisms, but I haven't figured out the following questions:
- Which Attention should be used from TF, Luong-style attention or Bahdanau-style attention.?
- What should be exactly the query and value inputs to the Attention layer? They trained a User-Item recommender and it looks like that for the Attention layers in both the Query and Candidate Towers either User or Item features were used.
From the paper:
Maybe @patrickorlando do you have an idea related to this?
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 with the linked paper, the tf.keras.layers.Attention and AdditiveAttention API documentation, and discussion #633. Determine whether either attention mechanism and its query/value roles can be recommended from the paper, then document a clear usage explanation or example; done means both questions have an unambiguous, project-supported answer.
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
- 20/100