A Additive feature attribution methods unify existing explainers for GNNs In this section, we analyze the vanilla gradient-based explainers and GNNExplainer [ 24

GNN and assign important scores on explained features. Here, we consider the simplest gradient-based explanation method in which the score of each feature is associated with the gradient of the GNN's loss function with respect to that feature. The proof that this explanation method falls into the class of additive feature attribution methods is quite straight-forward. S is a good explanation for the target prediction. This experiment setup is the same as that in experiment of Figure 1.