This is the official repo for the paper FLAG: Adversarial Data Augmentation for Graph Neural Networks.
TL;DR: FLAG augments node features to generalize GNNs on both node and graph classification tasks.
- Simple, adding just a dozen lines of code
- General, applicable to any GNN baseline
- Versatile, working on both node and graph classification tasks
- Scalable, minimum memory overhead, working on the original infrastructure
To reproduce experimental results for DeeperGCN, visit here.
Other baselines including GCN, GraphSAGE, GAT, GIN, MLP, etc. are available here.
To view the empirical performance of FLAG, please visit the Open Graph Benchmark Node and Graph classification leaderboards.
- ogb>=1.2.3
- torch-geometric>=1.6.1
- torch>=1.5.0
If you find FLAG useful, please cite our paper.
@misc{kong2020flag,
title={FLAG: Adversarial Data Augmentation for Graph Neural Networks},
author={Kezhi Kong and Guohao Li and Mucong Ding and Zuxuan Wu and Chen Zhu and Bernard Ghanem and Gavin Taylor and Tom Goldstein},
year={2020},
eprint={2010.09891},
archivePrefix={arXiv},
primaryClass={cs.LG}
}