Towards Fair Class-wise Robustness: Class Optimal Distribution Adversarial Training.

The identical distribution hypothesis is equivalent to the parameter discrepancy hypothesis: Adversarial attacks on graph neural networks.

Graph convolutional networks-based robustness optimization for scale-free Internet of Things.

SmartTRO: Optimizing topology robustness for Internet of Things via deep reinforcement learning with graph convolutional networks.

Parameter discrepancy hypothesis: adversarial attack for graph data.

USI-AUC: An evaluation criterion of community detection based on a novel link-prediction method.