tensorflow / tensorflow/gnn

Self-supervised representation learning with tf-gnn

Open
#809 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi TF-GNN users!

Could anyone share example code demonstrating the use of contrastive losses/DGI module, or suggest an alternative method to set up a basic self-supervised representation learning task? Additionally, if you could point me to a repository that utilizes tf-gnn in this context, that would also be great.

Thanks,
Szabolcs

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 tf-gnn's contrastive losses/DGI module and look for existing self-supervised examples or repositories using tf-gnn. Done means providing a working basic self-supervised representation-learning example or clearly pointing users to a suitable implementation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
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.