MEGA: Explaining Graph Neural Networks with Network Motifs
Lists
Only you see this
Abstract
Graph Neural Networks (GNNs) are powerful tools for graph representation. However, GNNs have remained black boxes, leading to the lack of explainability. As a consequence, the application of GNNs has been severely limited. Existing methods focus on generating an explanation with important nodes and edges but pay less attention to high-order structures (e.g., network motif), which are more intuitive and important for graph data. The explanations generated by the explainer will thus ignore the high-order information contained in multi-node neighbours, resulting in a decrease in the human comprehensibility of the explanation subgraph. In this paper, we propose a motif-aware GNNs explainer (MEGA), wherein a motif-aware subgraph generation module and a counterfactual optimization layer are employed. MEGA can provide high-quality counterfactual explanations for GNNs while focusing on high-order features of graph data. We justify the effectiveness of the proposed MEGA on both synthetic and real-world datasets. Experimental results show that MEGA outperforms state-of-the-art baselines while keeping explanations at a smaller level.
BibTeX
@inproceedings{ding2023mega,
author = {Feng Ding and Naiwen Luo and Shuo Yu and Tingting Wang and Feng Xia},
title = {{MEGA: Explaining Graph Neural Networks with Network Motifs}},
booktitle = {IJCNN},
year = {2023},
doi = {10.1109/ijcnn54540.2023.10191684},
}Loading related content...