Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization.

This repository is the official implementation of GRAIN.

Requirements

To install requirements:

pip install -r requirements.txt

Training

To train the model(s) in the paper:

cd the “example” data

run the python file GRAIN(ball-D).py or GRAIN(NN-D).py

Results

1. Accuracy comparison:

2. Active learning comparison:

3. Core-set selection comparison:

4. Efficiency comparison on GPU:

5. Efficiency comparison on CPU:

6. Interpretability:

7. Ablation study:

8. Generalization:

Cite

If you use Grain in a scientific publication, we would appreciate citations to the following paper:

@article{zhang2021grain,
  title={GRAIN: improving data efficiency of gra ph neural networks via diversified in fluence maximization},
  author={Zhang, Wentao and Yang, Zhi and Wang, Yexin and Shen, Yu and Li, Yang and Wang, Liang and Cui, Bin},
  journal={Proceedings of the VLDB Endowment},
  volume={14},
  number={11},
  pages={2473--2482},
  year={2021},
  publisher={VLDB Endowment}
}