BeGin is an easy and fool-proof framework for graph continual learning.
Our framework BeGin has the following advantages:
- BeGin is easy-to-use. It is easily extended since it is modularized with reusable modules for data processing, algorithm design, training, and evaluation.
- BeGin is fool-proof by completely separating the evaluation module from the learning part, where users implement their own graph CL methods, in order to eliminate potential mistakes in evaluation.
- BeGin provides 23 benchmark scenarios for graph from 14 real-world datasets, which cover 12 combinations of the incremental settings and the levels of problem. In addition, BeGin provides various basic evaluation metrics for measuring the performances and final evalution metrics designed for continual learning.
You can install BeGin with the following command:
pip install -e .Before running the command, we strongly recommend installing the proper version of PyTorch, DGL, and torch-scatter depending on your CUDA version.
torch>=1.8.1dgl>=0.6.1torch-scatter>=2.0.6torch-sparse>=0.6.9torch-geometric>=2.0.4ogb>=1.3.4dgl-lifesci>=0.2.9rdkit-pypi>=2022.9.1
For running some algorithms, you may need the following additional packages:
quadprogcvxpyqpth
The tutorial and documents of BeGin are available at Here.
We also provide some running examples in examples directory.
If you use this framework as part of any published research, please consider acknowledging our paper.
@article{kokang2022begin,
title={BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning},
author={Ko, Jihoon and Kang, Shinhwan and Shin, Kijung},
journal={arXiv preprint arXiv:2211.?????},
year={2022},
}