GTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation

• URL: http://arxiv.org/abs/2509.10869v1
• Date: Sat, 13 Sep 2025 15:52:16 GMT
• Title: GTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation
• Authors: Mingkang Li, Xuexiong Luo, Yue Zhang, Yaoyang Li, Fu Lin,
• Abstract summary: Anomaly detection in graph-structured data is an inherently challenging problem.<n>Existing methods, such as those based on graph convolutional networks (GCNs), often suffer from over-smoothing.<n>We propose a novel and holistic anomaly evaluation framework that integrates three key components.
• Score: 7.287914649294607
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• On the Problem of Consistent Anomalies in Zero-Shot Anomaly Detection [0.0]
  Zero-shot anomaly classification and segmentation (AC/AS) aim to detect anomalous samples and regions without any training data.<n>This dissertation aims to investigate the core challenges of zero-shot AC/AS and presents principled solutions rooted in theory and algorithmic design.
  arXiv  Detail & Related papers  (2025-12-02T08:23:03Z)
• Graph Evidential Learning for Anomaly Detection [19.046244103954855]
  We propose Graph Evidential Learning (GEL) to redefine the reconstruction process through evidential learning.<n>GEL quantifies two types of uncertainty: graph uncertainty and reconstruction uncertainty, incorporating them into the anomaly scoring mechanism.<n>GEL achieves state-of-the-art performance while maintaining high robustness against noise and structural perturbations.
  arXiv  Detail & Related papers  (2025-05-31T15:06:42Z)
• What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding [67.59552859593985]
  Graph Transformers, which incorporate self-attention and positional encoding, have emerged as a powerful architecture for various graph learning tasks. This paper introduces first theoretical investigation of a shallow Graph Transformer for semi-supervised classification.
  arXiv  Detail & Related papers  (2024-06-04T05:30:16Z)
• ARC: A Generalist Graph Anomaly Detector with In-Context Learning [62.202323209244]
  ARC is a generalist GAD approach that enables a one-for-all'' GAD model to detect anomalies across various graph datasets on-the-fly.<n> equipped with in-context learning, ARC can directly extract dataset-specific patterns from the target dataset.<n>Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance, efficiency, and generalizability of ARC.
  arXiv  Detail & Related papers  (2024-05-27T02:42:33Z)
• ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection [84.0718034981805]
  We introduce a novel framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD) In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. In the next stage, the decoders are retrained for detection on the original graph.
  arXiv  Detail & Related papers  (2023-12-22T09:02:01Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction [34.82023223790515]
  Graph Auto-Encoders (GAEs) encode graph data into node representations and identify anomalies by assessing the reconstruction quality of the graphs based on these representations.<n>We propose GAD-NR, a new variant of GAE that incorporates neighborhood reconstruction for graph anomaly detection.<n>Extensive experimentation conducted on six real-world datasets validates the effectiveness of GAD-NR, showcasing significant improvements (by up to 30% in AUC) over state-of-the-art competitors.
  arXiv  Detail & Related papers  (2023-06-02T23:23:34Z)
• ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness [70.60721571429784]
  We propose a new graph anomaly detection framework on attributed networks via substructure awareness (ARISE) ARISE focuses on the substructures in the graph to discern abnormalities. Experiments show that ARISE greatly improves detection performance compared to state-of-the-art attributed networks anomaly detection (ANAD) algorithms.
  arXiv  Detail & Related papers  (2022-11-28T12:17:40Z)
• AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approach [23.096589854894884]
  AHEAD is an unsupervised graph anomaly detection approach based on the encoder-decoder framework. We show the superiority of AHEAD on several real-world heterogeneous information networks compared with the state-of-arts in the unsupervised setting.
  arXiv  Detail & Related papers  (2022-08-17T10:08:28Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks [35.93516937521393]
  This paper proposes a self-supervised learning framework that jointly optimize a multi-view contrastive learning-based module and an attribute reconstruction-based module to more accurately detect anomalies on attributed networks. Experiments conducted on five benchmark datasets show our model outperforms current state-of-the-art models.
  arXiv  Detail & Related papers  (2022-05-10T11:35:32Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.