$β$-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation
This addresses a critical security challenge for computing systems using GNNs in applications like anomaly detection, though it appears incremental as it builds on existing GNN methods.
The paper tackles the vulnerability of Graph Neural Networks (GNNs) to network perturbations by proposing $\beta$-GNN, a robust ensemble model that enhances adversarial accuracy without compromising clean data performance, as demonstrated on diverse datasets.
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.