Fig. 7.

Unfaithfulness scores across five GNN explainers that produce node feature explanations. Every GNN explainer is evaluated on three datasets whose network topology is equivalent to SG-Base and by varying the ratio between informative and redundant node features: most informative node features, control node features, and least informative node features. Results show that across all explainers, unfaithfulness decreases as the proportion of informative to redundant features increases, with explainers trained on the graph with the most informative node features having consistently lower unfaithfulness scores than explainers trained on graphs with the least informative node features.