Lune

NeurIPS2024Top-tier venue

Generative Semi-supervised Graph Anomaly Detection

Hezhe Qiao, Qingsong Wen, Xiaoli Li, Ee-Peng Lim, Guansong Pang

Abstract

This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the extensively explored unsupervised setting with a fully unlabeled graph. We reveal that having access to the normal nodes, even just a small percentage of normal nodes, helps enhance the detection performance of existing unsupervised GAD methods when they are adapted to the semi-supervised setting. However, their utilization of these normal nodes is limited. In this paper, we propose a novel Generative GAD approach (namely GGAD) for the semi-supervised scenario to better exploit the normal nodes. The key idea is to generate pseudo anomaly nodes, referred to as 'outlier nodes', for providing effective negative node samples in training a discriminative one-class classifier. The main challenge here lies in the lack of ground truth information about real anomaly nodes. To address this challenge, GGAD is designed to leverage two important priors about the anomaly nodes -- asymmetric local affinity and egocentric closeness -- to generate reliable outlier nodes that assimilate anomaly nodes in both graph structure and feature representations. Comprehensive experiments on six real-world GAD datasets are performed to establish a benchmark for semi-supervised GAD and show that GGAD substantially outperforms state-of-the-art unsupervised and semi-supervised GAD methods with varying numbers of training normal nodes. Code will be made available at https://github.com/mala-lab/GGAD.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

13 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Rethinking Graph Neural Networks for Anomaly Detection cites Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
  • Normality Calibration in Semi-supervised Graph Anomaly Detection cites Rethinking Graph Neural Networks for Anomaly Detection
  • Normality Calibration in Semi-supervised Graph Anomaly Detection cites Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
  • Normality Calibration in Semi-supervised Graph Anomaly Detection cites Semi-supervised Graph Anomaly Detection via Robust Homophily Learning
  • Normality Calibration in Semi-supervised Graph Anomaly Detection cites Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
  • Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum cites Rethinking Graph Neural Networks for Anomaly Detection
  • Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum cites Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
  • Conditional Diffusion Anomaly Modeling on Graphs cites Rethinking Graph Neural Networks for Anomaly Detection
  • Conditional Diffusion Anomaly Modeling on Graphs cites Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
  • Conditional Diffusion Anomaly Modeling on Graphs cites Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
  • Semi-supervised Graph Anomaly Detection via Robust Homophily Learning cites Rethinking Graph Neural Networks for Anomaly Detection
  • Semi-supervised Graph Anomaly Detection via Robust Homophily Learning cites Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
  • Semi-supervised Graph Anomaly Detection via Robust Homophily Learning cites Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
  • IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning cites Rethinking Graph Neural Networks for Anomaly Detection
  • IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning cites Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers13

  1. Semi-supervised Graph Anomaly Detection via Robust Homophily LearningGuoguo Ai, Hezhe Qiao, Hui Yan, Guansong PangNeurIPS 2025 · 7 citations
  2. Conditional Diffusion Anomaly Modeling on GraphsChunyu Wei, Haozhe Lin, Yueguo Chen, Yunhai WangNeurIPS 2025 · 3 citations
  3. IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity LearningXiong Zhang, Zhenli He, Changlong Fu, Cheng XieNeurIPS 2025 · 3 citations
  4. AP-OOD: Attention Pooling for Out-of- Distribution DetectionClaus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz et al.ICLR 2026 · 2 citations
  5. Normality Calibration in Semi-supervised Graph Anomaly DetectionGuolei Zeng, Hezhe Qiao, Guoguo Ai, Jinsong Guo et al.ICML 2026 · 1 citation

Builds on19

  1. Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud DetectionYang Liu, Xiang Ao, Zidi Qin, Jianfeng Chi et al.WWW 2021 · 527 citations
  2. Rethinking Graph Neural Networks for Anomaly DetectionJianheng Tang, Jiajin Li, Ziqi Gao, Jia LiICML 2022 · 365 citations
  3. DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly DetectionYiyuan Yang, Chaoli Zhang, Tian Zhou, Qingsong Wen et al.KDD 2023 · 244 citations
  4. Generative Cooperative Learning for Unsupervised Video Anomaly DetectionMuhammad Zaigham Zaheer, Arif Mahmood, Muhammad Haris Khan, Mattia Segù et al.CVPR 2022 · 195 citations
  5. Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph SpectrumYuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu et al.WWW 2023 · 189 citations

Related papers

  1. Topological Anomaly Quantification for Semi-supervised Graph Anomaly DetectionTing Guo, Yangrui Fan, Caixia Cui, Jiye Liang et al.ICLR 2026
  2. CR-Aug: Community Risk-Guided Adaptive Augmentation for Semi-supervised Graph Anomaly DetectionJing Huang, Yicun Liu, Zhixin Li, Yinan Jing et al.KDD 2026
  3. Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly DetectionHezhe Qiao, Guansong PangNeurIPS 2023 · 84 citations
  4. PAGE: Progressive Anomaly Generation Network for Semi-supervised Graph Anomaly DetectionTing Guo, Dongyu Pei, Gangzhu Qiao, Kaixuan Yao et al.WWW 2026
  5. Open-Set Graph Anomaly Detection via Normal Structure RegularisationQizhou Wang, Guansong Pang, Mahsa Salehi, Xiaokun Xia et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines