LARS-research/CLGNN

Model

Code for the technical report [Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks].

Quick Start

Here, we provide a quick start guide on how to reproduce the results.

Download the project and install the required dependencies.

git clone https://github.com/LARS-research/CLGNN.git
cd CLGNN
pip install -r requirements.txt

Run the Code

To reproduce the results on the OGB Leaderboards, execute the script: sh scripts/run_leaderboard_OGBN-MAG.sh

License

CLGNN is released under the MIT license. Further details can be found here.