What question did this study set out to answer?

The research aims to improve the robustness of Graph Neural Networks against network perturbations.

January 25, 2026Open Access

β-GNN: A robust ensemble approach against graph structure perturbation

Key Points

The research aims to improve the robustness of Graph Neural Networks against network perturbations.
Developed the β-GNN model using a weighted ensemble approach.
Combined traditional GNN with a multi-layer perceptron.
Introduced a dynamic weight, β, to balance GNN contributions based on data quality.
Evaluated the model on various datasets to assess performance.
β-GNN demonstrated superior adversarial accuracy compared to standard GNNs.
Effectively quantified attack severity associated with perturbations.
Preserved clean data structure, maintaining performance without assumptions.

Abstract

Graph Neural Networks (GNNs) are playing an increasingly important role in the efficient operation and security of computing systems, with applications in workload scheduling, anomaly detection, and resource management. However, their vulnerability to network perturbations poses a significant challenge. We propose β-GNN, a model enhancing GNN robustness without sacrificing clean data performance. β-GNN uses a weighted ensemble, combining any GNN with a multi-layer perceptron. A learned dynamic weight, β, modulates the GNN's contribution. This β not only weights GNN influence but also indicates data perturbation levels, enabling proactive mitigation. Experimental results on diverse datasets show β-GNN's superior adversarial accuracy and attack severity quantification. Crucially, β-GNN avoids perturbation assumptions, preserving clean data structure and performance.

β-GNN: A robust ensemble approach against graph structure perturbation

Key Points

Abstract

Cite This Study