Ignoring Directionality Leads to Compromised Graph Neural Network Explanations

TL;DR

This paper shows that ignoring edge direction in Graph Neural Networks leads to poorer explanations, and preserving directionality significantly improves explanation fidelity in critical applications.

Contribution

It provides theoretical and empirical evidence that maintaining edge directionality enhances GNN explanation quality, addressing a key limitation in current practices.

Findings

Ignoring directionality causes information loss and misleading explanations.

Preserving directional semantics improves explanation fidelity.

Direction-aware GNN explanations are crucial for security-critical applications.

Abstract

Graph Neural Networks (GNNs) are increasingly used in critical domains, where reliable explanations are vital for supporting human decision-making. However, the common practice of graph symmetrization discards directional information, leading to significant information loss and misleading explanations. Our analysis demonstrates how this practice compromises explanation fidelity. Through theoretical and empirical studies, we show that preserving directional semantics significantly improves explanation quality, ensuring more faithful insights for human decision-makers. These findings highlight the need for direction-aware GNN explainability in security-critical applications.