Work

Ignoring Directionality Leads to Compromised Graph Neural Network Explanations

Year: 2025

Type: conference-paper

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.

Source: IEEE Security and Privacy Workshops (SPW)

DOI: 10.1109/spw67851.2025.00032

Authors: Changsheng Sun, Xinke Li, Jin Song Dong

Institutions: National University of Singapore, City University of Hong Kong

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4411996595

FWCI:

Cites: 25

Cited by:

Related to: 10