GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks

TL;DR

GraphLIME introduces a local explanation method for GNNs that uses HSIC Lasso to identify key features in a node's neighborhood, improving interpretability of complex graph models.

Contribution

It proposes a novel local explanation framework for GNNs using nonlinear feature selection with HSIC Lasso, enhancing interpretability of node predictions.

Findings

Explanations are more descriptive than existing methods.

GraphLIME effectively identifies key features in real-world datasets.

The method provides high-quality local explanations for GNN predictions.

Abstract

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.