tensorflow / tensorflow/gnn

Implement SE3 Transformers

Open
#17 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
1.5k
Forks
204
Avg merge
13m
Merged PRs (30d)
1

Description

Hi, I'm really excited for this library. I think some of the scalability tricks you have promised under the hood look exceptionally nice.

Building off of the GATv2 example, I'd really like to implement SE3 Transformers (https://arxiv.org/pdf/2006.10503.pdf)

I understand you have a roadmap, and this is an alpha, but I haven't found a SE3 implementation in tensorflow I like and this seems the most promising starting point.

I am able to compile and run tests (from my own branch). I can either try and hack something together for myself, or potentially layout a spec with someone from the team to do this.

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

Read the SE3 Transformers paper and the repository's GATv2 example first. Work with the team to define a specification, including the intended TensorFlow GNN integration and validation criteria; the issue is complete when that agreed implementation and its tests are in place.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
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.