Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks

TL;DR

OPEN is a pioneering explainability method for GNNs that captures comprehensive decision logic across diverse data distributions without strict prerequisites, improving fidelity and robustness.

Contribution

It introduces OPEN, the first method to infer GNN decision logic across multiple environments without requiring edge or internal GNN access.

Findings

OPEN outperforms state-of-the-art methods in fidelity.

It captures nearly complete GNN decision logic.

Enhances robustness in real-world scenarios.

Abstract

To enhance the reliability and credibility of graph neural networks (GNNs) and improve the transparency of their decision logic, a new field of explainability of GNNs (XGNN) has emerged. However, two major limitations severely degrade the performance and hinder the generalizability of existing XGNN methods: they (a) fail to capture the complete decision logic of GNNs across diverse distributions in the entire dataset's sample space, and (b) impose strict prerequisites on edge properties and GNN internal accessibility. To address these limitations, we propose OPEN, a novel c\textbf{O}mprehensive and \textbf{P}rerequisite-free \textbf{E}xplainer for G\textbf{N}Ns. OPEN, as the first work in the literature, can infer and partition the entire dataset's sample space into multiple environments, each containing graphs that follow a distinct distribution. OPEN further learns the decision logic of GNNs across different distributions by sampling subgraphs from each environment and analyzing their predictions, thus eliminating the need for strict prerequisites. Experimental results demonstrate that OPEN captures nearly complete decision logic of GNNs, outperforms state-of-the-art methods in fidelity while maintaining similar efficiency, and enhances robustness in real-world scenarios.