theislab / theislab/interscale
Re-mask input to transformer
Open
Nobody has claimed this yet.
backlog
enhancement
- Dominant language
- Python
- Stars
- 12
- Forks
- 1
- Avg merge
- 12h 51m
- Merged PRs (30d)
- 1
Description
Description of feature
Re-masking described in GraphMAE.
Forces the transformer to learn expression from node through long-range interactions solely. Otherwise, can also already use its own local information.
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 by reading the transformer's implementation and the GraphMAE description of re-masking. Determine where the transformer input is masked and how long-range interactions are isolated from a node's local information. Done means the transformer applies the requested re-masking behavior and its existing validation still passes.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100