Self-supervised representation learning with tf-gnn
Open
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
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 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