Enhance Graph-Based Intrusion Detection in Optical Networks via Pseudo-Metapaths
Gang Qu, Haochun Jin, Liang Zhang, Minhui Ge, Xin Wu, Haoran Li, Jian Feng Xu · Mathematics · 2025
Deep learning on graphs has emerged as a leading paradigm for intrusion detection, yet its performance in optical networks is often hindered by sparse labeled data and severe class imbalance, leading to an “under-reaching” issue where supervision signals fail to propagate effectively. To address this, we introduce Pseudo-Metapaths: dynamic, semantically aware propagation routes discovered on-the-fly. Our framework first leverages Beta-Wavelet spectral filters for robust, frequency-aware node representations. It then transforms the graph into a dynamic heterogeneous structure using the model’s own pseudo-labels to define transient ‘normal’ or ‘anomaly’ node types. This enables an attention mechanism to learn the importance of different Pseudo-Metapaths (e.g., Anomaly–Normal–Anomaly), guiding supervision signals along the most informative routes. Extensive experiments on four benchmark datasets demonstrate quantitative superiority. Our model achieves state-of-the-art F1-scores, outperforming a strong spectral GNN backbone by up to 3.15%. Ablation studies further confirm that our Pseudo-Metapath module is critical, as its removal causes F1-scores to drop by as much as 7.12%, directly validating its effectiveness against the under-reaching problem.