JuliaGraphs / JuliaGraphs/GraphNeuralNetworks.jl

Spatial Graph Convolutional Networks

Open
#503 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi, many thanks for your work on this amazing package.

There is a paper called "Spatial Graph Convolutional Networks", with accompanying PyTorch code. You may be familiar with this work already but, from my understanding, the premise of this architecture is that it is a proper generalisation of CNNs from gridded spatial data to irregular spatial data; see Figure 3 and Theorem 1 in the paper.

Do you think it would be worthwhile to include this architecture in your package, perhaps as one of the convolutional 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

Read the linked paper, especially Figure 3 and Theorem 1, then compare its architecture with the convolutional layers listed in the package API. Review the linked PyTorch implementation and determine the expected scope and acceptance criteria before attempting work; the issue does not currently define what completion would look like.

Written by the indexing model from the issue text.

Assessment

Tech stack
julia
Domain
machine-learning
Issue type
Feature
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.