Fig. 5
From: Complex network effects on the robustness of graph convolutional networks
Performance using an adaptive attack for global poisoning with all three training schemes. Results are shown in terms of overall classifier accuracy using a GCN, an SVD-based GCN, and GNNGuard on the CiteSeer and Cora datasets. Bars showing accuracy before poisoning are desaturated, while accuracy after poisoning is solid. Higher accuracy is better for the defender. In all cases, selecting training data using GreedyCover results in better post-attack accuracy