JuliaGraphs / JuliaGraphs/GraphNeuralNetworks.jl

Pooling support for HeteroGraphs

Open
#388 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

heterographs
Dominant language
Julia
Stars
308
Forks
74
Avg merge
3d 6h
Merged PRs (30d)
2

Description

While browsing the codebase I noticed that there're some Convolution functions that support HeteroGraphs while there's none Pooling functions that support HeteroGraphs. So I thought it would be good to add this feature.

List of existing functions that need to be extended:

  • GlobalPool
  • GlobalAttentionPool
  • TopKPool
  • Set2Set

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 reading the existing HeteroGraph convolution support and the implementations of GlobalPool, GlobalAttentionPool, TopKPool, and Set2Set. Compare their current handling of graph inputs, then check that each listed pooling function supports HeteroGraphs and that the relevant existing tests pass or are extended to cover the new behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
julia
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.