Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks

TL;DR

This paper introduces ConfExplainer, a confidence-aware framework for explaining GNNs that quantifies explanation reliability, improving trustworthiness and robustness especially on out-of-distribution data.

Contribution

It proposes a theoretically grounded confidence scoring module for GNN explanations, addressing the reliability issue in unknown test scenarios.

Findings

Confidence scores improve explanation trustworthiness.

The method outperforms existing explanation techniques.

Enhanced robustness on out-of-distribution data.

Abstract

Explaining Graph Neural Networks (GNNs) has garnered significant attention due to the need for interpretability, enabling users to understand the behavior of these black-box models better and extract valuable insights from their predictions. While numerous post-hoc instance-level explanation methods have been proposed to interpret GNN predictions, the reliability of these explanations remains uncertain, particularly in the out-of-distribution or unknown test datasets. In this paper, we address this challenge by introducing an explainer framework with the confidence scoring module ( ConfExplainer), grounded in theoretical principle, which is generalized graph information bottleneck with confidence constraint (GIB-CC), that quantifies the reliability of generated explanations. Experimental results demonstrate the superiority of our approach, highlighting the effectiveness of the confidence score in enhancing the trustworthiness and robustness of GNN explanations.