SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations
Published in
Neural Information Processing Systems(2022)External Links:
TL
TL;DR
This work proposes Structure-Aware Shapley-based Multipiece Explanation (SAME), a method to address the structure-aware feature interactions challenges for GNNs explanation that has the potential to be as explainable as the theoretically optimal explanation obtained by the Shapley value within polynomial time.