theislab / theislab/interscale

Re-mask input to transformer

Open
#18 0 comments 0 reactions 0 assignees View on GitHub

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

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 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.