GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
This addresses the problem of interpretability in GNNs for researchers and practitioners in domains like physics, chemistry, and social networks, offering a novel explanation method that is incremental in improving upon existing techniques.
The paper tackles the challenge of explaining predictions made by Graph Neural Networks (GNNs) on graph-structured data by proposing GraphLIME, a local interpretable model explanation framework that uses HSIC Lasso for nonlinear feature selection. The result shows that GraphLIME provides explanations with an extraordinary degree and more descriptive quality compared to existing methods, as validated on two real-world datasets.
Graph structured data has wide applicability in various domains such as physics, chemistry, biology, computer vision, and social networks, to name a few. Recently, graph neural networks (GNN) were shown to be successful in effectively representing graph structured data because of their good performance and generalization ability. GNN is a deep learning based method that learns a node representation by combining specific nodes and the structural/topological information of a graph. However, like other deep models, explaining the effectiveness of GNN models is a challenging task because of the complex nonlinear transformations made over the iterations. In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method. GraphLIME is a generic GNN-model explanation framework that learns a nonlinear interpretable model locally in the subgraph of the node being explained. More specifically, to explain a node, we generate a nonlinear interpretable model from its $N$-hop neighborhood and then compute the K most representative features as the explanations of its prediction using HSIC Lasso. Through experiments on two real-world datasets, the explanations of GraphLIME are found to be of extraordinary degree and more descriptive in comparison to the existing explanation methods.