Online adversarial knowledge distillation for graph neural networks

Can Wang, Zhe Wang, Defang Chen, Sheng Zhou, Yan Feng, Chun Chen

Abstract: Highlights•We propose an Online Adversarial Knowledge Distillation framework for GNNs.•OAD trains a group of GNN models to capture structure updates in GNNs.•OAD extracts both local and global knowledge in graph structured data.•Extensive experiments demonstrate the effectiveness of OAD.