Generalist Graph Anomaly Detection via Prototype-Based Distillation

• URL: http://arxiv.org/abs/2605.26857v1
• Date: Tue, 26 May 2026 11:16:31 GMT
• Title: Generalist Graph Anomaly Detection via Prototype-Based Distillation
• Abstract summary: We introduce ProMoS, the first unsupervised generalist GAD framework.<n>It detects anomalies by modeling the abundant normality in unlabeled data.<n>ProMoS adopts a knowledge-distillation paradigm to distill normality priors from a frozen self-supervised graph neural network (GNN) teacher to a mixture-of-students model.
• Score: 35.05528401287102
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector transferable across new graphs, has recently gained growing attention. However, existing methods often rely on scarce and costly annotations for training and sometimes even require few-shot support at inference, which limits their robustness to diverse and unseen anomaly patterns. To address this limitation, we introduce ProMoS, the first unsupervised generalist GAD framework, which detects anomalies by modeling the abundant normality in unlabeled data. ProMoS adopts a knowledge-distillation paradigm to distill normality priors from a frozen self-supervised graph neural network (GNN) teacher to a mixture-of-students model with shared global and lightweight personalized branches, enabling efficient and expressive normality modeling without learning from scratch. We further propose prototype-guided soft-label distillation to align teacher and student in a shared prototype space, enhancing cross-graph generalizability. During inference, ProMoS performs zero-shot anomaly detection on unseen graphs via distillation bias and prototype geometric deviation. Extensive experiments show the effectiveness and efficiency of ProMoS, charting a practical path toward label-free, zero-shot generalist GAD.

Related papers

• Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detection [66.0756595768692]
  We introduce a weakly supervised graph anomaly detection method that leverages a feature learning strategy tailored for graph anomalies.<n>Our approach is built upon a multi-task learning scheme that extracts robust feature representations through synthesized anomalies.<n>Experiments on public datasets demonstrate the superior performance of our method over its competitors.
  arXiv  Detail & Related papers  (2026-05-12T08:27:06Z)
• Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time [60.341117019125214]
  We propose a lightweight and plug-and-play Test-time adaptation framework for correcting Unseen Normal pattErns in graph anomaly detection (GAD)<n>To address semantic confusion, a graph aligner is employed to align the shifted data to the original one at the graph attribute level.<n>Extensive experiments on 10 real-world datasets demonstrate that TUNE significantly enhances the generalizability of pre-trained GAD models to both synthetic and real unseen normal patterns.
  arXiv  Detail & Related papers  (2025-11-10T12:10:05Z)
• Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models [57.20761595019967]
  We present Normalized Attention Guidance (NAG), an efficient, training-free mechanism that applies extrapolation in attention space with L1-based normalization and refinement.<n>NAG restores effective negative guidance where CFG collapses while maintaining fidelity.<n>NAG generalizes across architectures (UNet, DiT), sampling regimes (few-step, multi-step), and modalities (image, video)
  arXiv  Detail & Related papers  (2025-05-27T13:30:46Z)
• AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection [22.584555292512427]
  AnomalyGFM is a graph foundation model that supports zero-shot inference and few-shot prompt tuning for GAD.<n>We show that AnomalyGFM significantly outperforms state-of-the-art competing methods under both zero- and few-shot GAD settings.
  arXiv  Detail & Related papers  (2025-02-13T12:10:05Z)
• Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphs [5.415950005432774]
  We propose a novel GAD framework (EL$2$-DGAD) to tackle anomaly detection problem in dynamic graphs with extremely limited labels.<n>Specifically, a transformer-based graph encoder model is designed to more effectively preserve evolving graph structures beyond the local neighborhood.
  arXiv  Detail & Related papers  (2025-01-25T02:35:48Z)
• 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)
• Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning [61.57383634677747]
  Graph anomaly detection (GAD) has attracted increasing attention in machine learning and data mining. Here, we propose a normality learning-based GAD framework via multi-scale contrastive learning networks (NLGAD for abbreviation) Notably, the proposed algorithm improves the detection performance (up to 5.89% AUC gain) compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-12T08:06:04Z)
• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation [30.81263206800531]
  Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage the available labels as prior knowledge, have achieved superior performances than unsupervised methods. We propose a data augmentation method named textitAugAN to enrich training data and boost the generalizability of GAD models.
  arXiv  Detail & Related papers  (2023-06-18T11:54:18Z)
• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation [32.532227090731354]
  Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage the available labels as prior knowledge, have achieved superior performances than unsupervised methods. We propose a data augmentation method named textitAugAN to enrich training data and boost the generalizability of GAD models.
  arXiv  Detail & Related papers  (2022-09-21T07:57:27Z)
• 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.