CRoC: Context Refactoring Contrast for Graph Anomaly Detection with Limited Supervision

• URL: http://arxiv.org/abs/2508.12278v2
• Date: Sun, 14 Sep 2025 10:08:13 GMT
• Title: CRoC: Context Refactoring Contrast for Graph Anomaly Detection with Limited Supervision
• Authors: Siyue Xie, Da Sun Handason Tam, Wing Cheong Lau,
• Abstract summary: We propose Context Refactoring Contrast (CRoC), a framework that trains Graph Neural Networks (GNNs) for Graph Anomaly Detection (GAD)<n>CRoC exploits the class imbalance inherent in GAD to leverage limited labeled and abundant unlabeled data.<n>In the training stage, CRoC is further integrated with the contrastive learning paradigm. This allows GNNs to effectively harness unlabeled data during training, producing richer, more discnative node embeddings.
• Score: 11.139587480845144
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Neural Networks (GNNs) are widely used as the engine for various graph-related tasks, with their effectiveness in analyzing graph-structured data. However, training robust GNNs often demands abundant labeled data, which is a critical bottleneck in real-world applications. This limitation severely impedes progress in Graph Anomaly Detection (GAD), where anomalies are inherently rare, costly to label, and may actively camouflage their patterns to evade detection. To address these problems, we propose Context Refactoring Contrast (CRoC), a simple yet effective framework that trains GNNs for GAD by jointly leveraging limited labeled and abundant unlabeled data. Different from previous works, CRoC exploits the class imbalance inherent in GAD to refactor the context of each node, which builds augmented graphs by recomposing the attributes of nodes while preserving their interaction patterns. Furthermore, CRoC encodes heterogeneous relations separately and integrates them into the message-passing process, enhancing the model's capacity to capture complex interaction semantics. These operations preserve node semantics while encouraging robustness to adversarial camouflage, enabling GNNs to uncover intricate anomalous cases. In the training stage, CRoC is further integrated with the contrastive learning paradigm. This allows GNNs to effectively harness unlabeled data during joint training, producing richer, more discriminative node embeddings. CRoC is evaluated on seven real-world GAD datasets with varying scales. Extensive experiments demonstrate that CRoC achieves up to 14% AUC improvement over baseline GNNs and outperforms state-of-the-art GAD methods under limited-label settings.

Related papers

• Causal Neighbourhood Learning for Invariant Graph Representations [8.854365724044984]
  We propose Causal Neighbourhood Learning with Graph Neural Networks (CNL-GNN), a novel framework that performs causal interventions on graph structure.<n>CNL-GNN effectively identifies and preserves causally relevant connections and reduces spurious influences.<n>Our approach improves causal graph learning beyond traditional feature-based methods, resulting in a robust classification model.
  arXiv  Detail & Related papers  (2026-02-20T01:52:58Z)
• Enhancing Fairness in Autoencoders for Node-Level Graph Anomaly Detection [3.487370856323828]
  Graph anomaly detection (GAD) has become an increasingly important task across various domains.<n>However, fairness considerations in GAD remain largely underexplored.<n>We propose textbfDistextbfEntangled textbfCounterfactual textbfAdversarial textbfFair (DECAF)-GAD, a framework that alleviates bias while preserving GAD performance.
  arXiv  Detail & Related papers  (2025-08-14T16:12:15Z)
• Graph Structure Refinement with Energy-based Contrastive Learning [56.957793274727514]
  We introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation.<n>We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR.<n>ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.
  arXiv  Detail & Related papers  (2024-12-20T04:05:09Z)
• Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning [47.74244053386216]
  Graph condensation is a promising solution to synthesize a compact, substitute graph of the large-scale original graph. We introduce Contrastive Graph Condensation (CTGC), which adopts a self-supervised surrogate task to extract critical, causal information from the original graph. CTGC excels in handling various downstream tasks with a limited number of labels, consistently outperforming state-of-the-art GC methods.
  arXiv  Detail & Related papers  (2024-11-26T03:01:22Z)
• Graph as a feature: improving node classification with non-neural graph-aware logistic regression [2.952177779219163]
  Graph-aware Logistic Regression (GLR) is a non-neural model designed for node classification tasks. Unlike traditional graph algorithms that use only a fraction of the information accessible to GNNs, our proposed model simultaneously leverages both node features and the relationships between entities.
  arXiv  Detail & Related papers  (2024-11-19T08:32:14Z)
• HGAttack: Transferable Heterogeneous Graph Adversarial Attack [63.35560741500611]
  Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce. This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs.
  arXiv  Detail & Related papers  (2024-01-18T12:47:13Z)
• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [72.33336385797944]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias.<n>We show that LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• 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)
• DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
  We propose DEGREE to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
  arXiv  Detail & Related papers  (2023-05-22T10:29:52Z)
• Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation [60.50994154879244]
  Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack. We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
  arXiv  Detail & Related papers  (2022-11-15T11:44:31Z)
• SCGC : Self-Supervised Contrastive Graph Clustering [1.1470070927586016]
  Graph clustering discovers groups or communities within networks. Deep learning methods such as autoencoders cannot incorporate rich structural information. We propose Self-Supervised Contrastive Graph Clustering (SCGC)
  arXiv  Detail & Related papers  (2022-04-27T01:38:46Z)

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.