pyg-team/pytorch_geometric

Add `IBMBNodeLoader` example

Open

#8,313 opened on Nov 2, 2023

View on GitHub
聽(2 comments)聽(0 reactions)聽(0 assignees)Python聽(19,985 stars)聽(3,514 forks)batch import
examplehelp wantedloader

Description

馃殌 The feature, motivation and pitch

As a follow-up of #6230 and redo of #8027 (cc @chendiqian as its PR author), we should add an example using the data loader.

paper: Influence-Based Mini-Batching for Graph Neural Networks

Alternatives

No response

Additional context

No response

Contributor guide

Tech stack
pythonpytorch
Domain
datamachine learningdocumentation
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
PythonPyTorchPyTorch Geometric basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
55
Research direction
Review the previous PR #8027 and issue #6230 for context on the IBMBNodeLoader implementation. Implement an example script that demonstrates using the IBMBNodeLoader to load a graph dataset and train a simple GNN model. Refer to the paper 'Influence Based Mini Batching for Graph Neural Networks' for the algorithm details.
Add `IBMBNodeLoader` example 路 pyg-team/pytorch_geometric#8313 | Good First Issue