MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation
About
Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. However, their predictions are often not interpretable. Post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we shed light on the existence of the distribution shifting issue in existing methods, which affects explanation quality, particularly in applications on real-life datasets with tight decision boundaries. To address this issue, we introduce a generalized Graph Information Bottleneck (GIB) form that includes a label-independent graph variable, which is equivalent to the vanilla GIB. Driven by the generalized GIB, we propose a graph mixup method, MixupExplainer, with a theoretical guarantee to resolve the distribution shifting issue. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed mixup approach over existing approaches. We also provide a detailed analysis of how our proposed approach alleviates the distribution shifting issue.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Graph Classification | BA-2motifs SingleMotif (test) | AUC-ROC0.878 | 9 | |
| Graph Classification | BA-HouseAndGrid MultipleMotif (test) | AUC-ROC80.4 | 9 | |
| Graph Classification | Benzene MultipleMotif (test) | AUC-ROC79.6 | 9 | |
| Graph Classification | BA-HouseGrid SingleMotif (test) | AUC-ROC0.811 | 9 | |
| Graph Classification | SPMotif SingleMotif (test) | AUC-ROC63.1 | 9 | |
| Graph Classification | Alkane-Carbonyl MultipleMotif (test) | AUC-ROC79.1 | 9 | |
| Graph Classification | Fluorid-Carbonyl MultipleMotif (test) | AUC-ROC68.6 | 9 | |
| Distribution-shift evaluation | BENZENE | Cosine Similarity0.907 | 8 | |
| Distribution-shift evaluation | BA-HouseGrid | Euclidean Distance0.973 | 8 | |
| Distribution-shift evaluation | TRIANGLES | Cosine Similarity0.947 | 8 |