Ignoring Directionality Leads to Compromised Graph Neural Network Explanations
This addresses the need for more faithful GNN explanations in security-critical applications, though it is incremental as it builds on existing explainability methods by focusing on directionality.
The paper tackles the problem of unreliable explanations in Graph Neural Networks (GNNs) caused by discarding directional information through graph symmetrization, showing that preserving directionality significantly improves explanation quality with empirical evidence.
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.