microsoft / microsoft/Graphormer

Graphormer module

Open
#133 10 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.5k
Forks
374
PR merge metrics
No merged PRs in 30d

Description

How can I use the graphormer model with custom dataloader and training scripts (not the fairseq commands)?
My data consists of DGL graphs and my setup uses DGL GraphConv layers. I want to use Graphormer as a torch.nn.Module (like any other GNN layer) and encode DGL graphs in my setup. How can I use Graphormer model alone and replace DGL GraphConv layers with Graphormer layers?

Contributor guide

No contributing guide indexed for this repository

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 reviewing the Graphormer model entry points and the fairseq command-based path referenced in the issue, then compare them with the custom DGL dataloader and training setup described. Done would be a documented, supported path for using Graphormer as a torch.nn.Module with DGL graphs, or a clear statement of the required integration boundary.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
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.