Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective

• URL: http://arxiv.org/abs/2507.14677v1
• Date: Sat, 19 Jul 2025 16:05:27 GMT
• Title: Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective
• Authors: Yiming Xu, Zhen Peng, Bin Shi, Xu Hua, Bo Dong, Song Wang, Chen Chen,
• Abstract summary: This paper presents a novel GCL-based framework named AD-GCL.<n>It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes.<n>The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL.
• Score: 22.263273250889615
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies.

Related papers

• Multi-Head Spectral-Adaptive Graph Anomaly Detection [7.788514265469946]
  Graph anomaly detection has broad applications in financial fraud and risk control.<n>Existing graph anomaly detection methods often face significant challenges when dealing with complex and variable abnormal patterns.<n>We propose a Multi-Head Spectral-Adaptive Graph Neural Network (MHSA-GNN)<n>Our method effectively preserves high-frequency abnormal signals and significantly outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T14:55:43Z)
• Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning [7.277472116667557]
  Graph Anomaly (GAD) plays a vital role in various data mining applications such as e-commerce fraud prevention and malicious user detection.<n>We propose a Heterophilic Graph Detection (HGE) module to learn distinguishable abnormal representations for potential anomalies.<n>Then, we propose a Multi-Hypersphere Learning (MHL) module to enhance the detection capability for context-dependent anomalies.
  arXiv  Detail & Related papers  (2025-03-15T08:08:13Z)
• Alleviating Structural Distribution Shift in Graph Anomaly Detection [70.1022676681496]
  Graph anomaly detection (GAD) is a challenging binary classification problem. Gallon neural networks (GNNs) benefit the classification of normals from aggregating homophilous neighbors. We propose a framework to mitigate the effect of heterophilous neighbors and make them invariant.
  arXiv  Detail & Related papers  (2024-01-25T13:07:34Z)
• Multitask Active Learning for Graph Anomaly Detection [48.690169078479116]
  We propose a novel MultItask acTIve Graph Anomaly deTEction framework, namely MITIGATE. By coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies. Empirical studies on four datasets demonstrate that MITIGATE significantly outperforms the state-of-the-art methods for anomaly detection.
  arXiv  Detail & Related papers  (2024-01-24T03:43:45Z)
• 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)
• Open-Set Graph Anomaly Detection via Normal Structure Regularisation [30.638274744518682]
  Open-set Graph Anomaly Detection (GAD) aims to train a detection model using a small number of normal and anomaly nodes.<n>Current supervised GAD methods tend to over-emphasise fitting the seen anomalies, leading to many errors of detecting the unseen anomalies as normal nodes.<n>We propose a novel open-set GAD approach, namely normal structure regularisation (NSReg), to achieve generalised detection ability to unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-12T13:25:28Z)
• BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection [50.26074811655596]
  We propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE) By swapping the context embeddings between nodes and edges, we enable the mutual detection of node and edge anomalies. BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs.
  arXiv  Detail & Related papers  (2023-07-28T00:44:57Z)
• 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)
• Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation [61.39364567221311]
  Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs. We introduce a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations.
  arXiv  Detail & Related papers  (2021-12-19T05:04:53Z)

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.