Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Jiaxing Zhang, Dongsheng Luo, Hua Wei• 2023

Related benchmarks

TaskDatasetResultRank
Graph ClassificationBA-2motifs SingleMotif (test)
AUC-ROC0.878
9
Graph ClassificationBA-HouseAndGrid MultipleMotif (test)
AUC-ROC80.4
9
Graph ClassificationBenzene MultipleMotif (test)
AUC-ROC79.6
9
Graph ClassificationBA-HouseGrid SingleMotif (test)
AUC-ROC0.811
9
Graph ClassificationSPMotif SingleMotif (test)
AUC-ROC63.1
9
Graph ClassificationAlkane-Carbonyl MultipleMotif (test)
AUC-ROC79.1
9
Graph ClassificationFluorid-Carbonyl MultipleMotif (test)
AUC-ROC68.6
9
Distribution-shift evaluationBENZENE
Cosine Similarity0.907
8
Distribution-shift evaluationBA-HouseGrid
Euclidean Distance0.973
8
Distribution-shift evaluationTRIANGLES
Cosine Similarity0.947
8
Showing 10 of 28 rows

Other info

Follow for update