Certifiable Robustness and Robust Training for Graph Convolutional Networks

28 Jun 2019Daniel ZügnerStephan Günnemann

Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outcomes unreliable. We propose the first method for certifiable (non-)robustness of graph convolutional networks with respect to perturbations of the node attributes... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Node Classification Citeseer GNN RH-U Accuracy 68% # 26
Node Classification Cora GNN RH-U Accuracy 83% # 19
Node Classification Pubmed GNN RH-U Accuracy 86% # 1