GTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation
This addresses the challenge of identifying rare nodes in graphs for applications like fraud detection or network security, though it appears to be an incremental improvement over existing graph-based anomaly detection methods.
The paper tackles the problem of anomaly detection in graph-structured data by proposing GTHNA, a framework that integrates a local-global Transformer encoder, memory-guided reconstruction, and multi-scale representation matching to capture structural dependencies and suppress anomalous node interference, achieving state-of-the-art performance on seven benchmark datasets.
Anomaly detection in graph-structured data is an inherently challenging problem, as it requires the identification of rare nodes that deviate from the majority in both their structural and behavioral characteristics. Existing methods, such as those based on graph convolutional networks (GCNs), often suffer from over-smoothing, which causes the learned node representations to become indistinguishable. Furthermore, graph reconstruction-based approaches are vulnerable to anomalous node interference during the reconstruction process, leading to inaccurate anomaly detection. In this work, we propose a novel and holistic anomaly evaluation framework that integrates three key components: a local-global Transformer encoder, a memory-guided reconstruction mechanism, and a multi-scale representation matching strategy. These components work synergistically to enhance the model's ability to capture both local and global structural dependencies, suppress the influence of anomalous nodes, and assess anomalies from multiple levels of granularity. Anomaly scores are computed by combining reconstruction errors and memory matching signals, resulting in a more robust evaluation. Extensive experiments on seven benchmark datasets demonstrate that our method outperforms existing state-of-the-art approaches, offering a comprehensive and generalizable solution for anomaly detection across various graph domains.