Deep Graph Anomaly Detection (DGAD): A Survey and New Perspectives

A professionally curated list of awesome resources (paper, code, data, etc.) on Deep Graph Anomaly Detection (DGAD), which is the first work to comprehensively and systematically summarize the recent advances of deep graph anomaly detection from the methodology design to the best of our knowledge.

We will continue to update this list with the newest resources. If you find any missed resources (paper/code) or errors, please feel free to open an issue or make a pull request.

Survey Paper

Deep Graph Anomaly Detection: A Survey and New Perspectives

Hezhe Qiao, Hanghang Tong, Bo An, Irwin King, Charu Aggarwal, Guansong Pang.

****

If you find this repository helpful for your work, please kindly cite our paper.

Taxonomy of Deep Graph Anomaly Detection

Category of Deep Graph Anomaly Detection

GNN Backbone Design

Discriminative GNNs

Aggregation Mechanism

• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters in CIKM, 2020. [paper][code]

• Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection in SIGIR, 2020. [paper][code]

• Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection in WWW, 2021.[paper][code]

• FRAUDRE: Fraud Detection Dual-Resistant to Graph Inconsistency and Imbalance in ICDM, 2021. [paper][code]

• Dual-discriminative Graph Neural Network for Imbalanced Graph-level Anomaly Detection in NeurIPS, 2022. [paper]

• Explainable Graph-based Fraud Detection via Neural Meta-graph Search in CIKM, 2022. [paper][code]

• Bi-Level Selection via Meta Gradient for Graph-based Fraud Detection in DASFAA, 2022. [paper]

• H2-FDetector: A GNN-based Fraud Detector with Homophilic and Heterophilic Connections in WebConf, 2022. [paper]

• Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum in WebConf, 2023. [paper][code]

• Towards Graph-level Anomaly Detection via Deep Evolutionary Mapping in KDD, 2023. [paper][code]

• Multitask Active Learning for Graph Anomaly Detection in Arxiv, 2024. [paper][code]

• Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection in Arxiv, 2024. [paper]

• Boosting Graph Anomaly Detection with Adaptive Message Passing in ICLR, 2024. [paper]

• Partitioning Message Passing for Graph Fraud Detection in ICLR, 2024. [paper][code]

• Graph Anomaly Detection with Bi-level Optimization in WebConf, 2024. [paper][code]

Feature Transformation

• Can Abnormality be Detected by Graph Neural Networks? in IJCAI, 2022. [paper][code]

• Rethinking Graph Neural Networks for Anomaly Detection in ICML, 2022.[paper][code]

• Alleviating Structural Distribution Shift in Graph Anomaly Detection in WSDM, 2023.[paper][code]

• Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection in ICLR, 2024.[paper][code]

• SmoothGNN: Smoothing-based GNN for Unsupervised Node Anomaly Detection in Arxiv, 2024. [paper]

Generative GNNs

Feature Interpolation

• GRAPHENS:Neighbor-aware Ego Network Synthesis for Class-imbalance Node Classification in ICLR, 2022. [paper][code]

• DAGAD: Data Augmentation for Graph Anomaly Detection in ICDM, 2022. [paper][code]

• GADY Unsupervised Anomaly Detection on Dynamic Graphs in Arxiv, 2023. [paper]

• Generative Graph Augmentation for Minority Class in Fraud Detection in CIKM, 2023. [paper]

• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation in TKDE, 2023. [paper][code]

• Class-Imbalanced Graph Learning without Class Rebalancing in ICML, 2024. [paper][code]

• Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision in ICLR, 2024. [paper][code]

Noise Perturbation

• Self-Discriminative Modeling for Anomalous Graph Detection in Arxiv, 2023. [paper]

• GODM Data Augmentation for Supervised Graph Outlier Detection with Latent Diffusion Models in Arxiv, 2023. [paper][code]

• GADY: Unsupervised Anomaly Detection on Dynamic Graphs in Arxiv, 2023. [paper][code]

• Graph Anomaly Detection with Few Labels: A Data-Centric Approach in KDD, 2024. [paper]

• Generative Semi-supervised Graph Anomaly Detection in Arxiv, 2024. [paper][code]

Proxy Task Design

Data Reconstruction

• NetWalk: A Flexible Deep Embedding Approach for Anomaly Detection in Dynamic Networks in KDD, 2018. [paper][code]

• Deep Anomaly Detection on Attributed Networks in SDM, 2019. [paper][code]

• ANOMALYDAE: Dual Autoencoder for Anomaly Detection on Attribute Networks in ICASSP, 2020. [paper][code]

• Outlier Resistant Unsupervised Deep Architectures for Attributed Network Embedding in WSDM, 2020. [paper][code]

• ResGCN Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks in Machine Learning, 2021. [paper][code]

• Mul-GAD: a semi-supervised graph anomaly detection framework via aggregating multi-view information in Arxiv, 2022. [paper][code]

• AnomMAN: Detect Anomaly on Multi-view Attributed Networks in Information Sciences, 2022.[paper]

• A Deep Multi-View Framework for Anomaly in TKDE, 2022. [paper]

• ComGA: Community-Aware Attributed Graph Anomaly Detection in WSDM, 2022. [paper][code]

• Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks in IJCAI, 2022. [paper][code]

• Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method in Arxiv, 2022. [paper][code]

• Graph-level Anomaly Detection via Hierarchical Memory Networks in ECML PKDD, 2023. [paper][code]

• Hybrid-Order Anomaly Detection on Attributed Networks in TKDE, 2023 [paper][code]

• A graph encoder–decoder network for unsupervised anomaly detection in Arxiv, 2023. [paper]

• Label-based Graph Augmentation with Metapath for Graph Anomaly Detection in Arxiv, 2023. [paper][code]

• GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction in WSDM, 2024. [paper][code]

• ADA-GAD:Anomaly-Denoised Autoencoders for Graph Anomaly Detection in AAAI, 2024. [paper][code]

• STRIPE Spatial-temporal Memories Enhanced Graph Autoencoder for Anomaly Detection in Dynamic Graphs in Arxiv, 2024. [paper]

Contrastive Learning

• ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning in CIKM, 2021. [paper]

• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection in TKDE, 2021. [paper][code]

• Anomaly Detection in Dynamic Graphs via Transformer in TKDE, 2021. [paper][code]

• CoLA Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning in TNNLS, 2021. [paper][code]

• CONDA Contrastive Attributed Network Anomaly Detection with Data Augmentation in PAKDD, 2022. [paper][code]

• Decoupling Representation Learning and Classification for GNN-based Anomaly Detection in SIGIR, 2021. [paper][code]

• GCCAD:Graph Contrastive Coding for Anomaly Detection in TKDE, 2022. [paper][code]

• Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment in AAAI, 2022. [paper][code]

• Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks in IJCAI, 2022. [paper][code]

• Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection in Arxiv, 2023. [paper]

• ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness in TNNLS, 2023. [paper][code]

• BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection in Arxiv, 2023. [paper]

• GOOD-D:On Unsupervised Graph Out-Of-Distribution Detection in WSDM, 2023. [paper][code]

• GRADATE:Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View in AAAI, 2023. [paper][code]

• GraphFC:Customs Fraud Detection with Label Scarcity in Arxiv, 2023. [paper][code]

• Revisiting Graph Contrastive Learning for Anomaly Detection in Arxiv, 2023. [paper][code]

• Multi-representations Space Separation based Graph-level Anomaly-aware Detection in SSDBM, 2023. [paper][code]

• Towards Self-Interpretable Graph-Level Anomaly Detection in NeurIPS, 2023. [paper][code]

• Learning Node Abnormality with Weak Supervision in CIKM, 2023. [paper]

• Federated Graph Anomaly Detection via Contrastive Self-Supervised Learning in TNNLS, 2024. [paper]

Knowledge Distillation

• Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation in CIKM, 2020. [paper][code]

• Discriminative Graph-level Anomaly Detection via Dual-students-teacher Model in Arxiv, 2023. [paper]

• FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework in Arxiv, 2024. [paper]

Adversarial Score Learning

• Generative Adversarial Attributed Network Anomaly Detection in CIKM, 2020. [paper][code]

• Inductive Anomaly Detection on Attributed Networks in IJCAI, 2021. [paper][code]

• Counterfactual_Graph_Learning_for_Anomaly_Detection_on_Attributed_Networks in TKDE, 2023. [paper][code]

• Generative Graph Augmentation for Minority Class in Fraud Detection in Arxiv, 2023. [paper][code]

Score Prediction

• DevNet Deep Anomaly Detection with Deviation Networks in KDD, 2019. [paper][code]

• Few-shot Network Anomaly Detection via Cross-network in WebConf, 2021. [paper][code]

• SAD:Semi-Supervised Anomaly Detection on Dynamic Graphs in IJCAI, 2023. [paper][code]

• Learning Node Abnormality with Weak Supervision in CIKM, 2023. [paper]

Graph Anomaly Measure

One-class Distance

• Deep into Hypersphere: Robust and Unsupervised Anomaly Discovery in Dynamic Networks in IJCAI, 2018. [paper][code]

• Subtractive Aggregation for Attributed Network Anomaly Detection in CIKM, 2021. [paper][code]

• HRGCN: Heterogeneous Graph-level Anomaly Detection with Hierarchical Relation-augmented Graph Neural Networks in DSAA, 2023. [paper][code]

• Deep Graph-level Orthogonal Hypersphere Compression for Anomaly Detection in ICLR, 2024. [paper][code]

Community Adherence

• NetWalk: A Flexible Deep Embedding Approach for Anomaly Detection in Dynamic Networks in KDD, 2018. [paper][code]

• Unseen Anomaly Detection on Networks via Multi-Hypersphere Learning in SDM, 2024. [paper][code]

Local Affinity

• Class Label-aware Graph Anomaly Detection in CIKM, 2023. [paper][code]

• PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection in ICDM, 2023. [paper][code]

• Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection in NeurIPS, 2023. [paper][code]

• ARC: A Generalist Graph Anomaly Detector with In-Context Learning in Arxiv, 2024. [paper]

Graph Isolation

• Deep Isolation Forest for Anomaly Detection in TKDE, 2023. [paper][code]

• Subgraph Centralization: A Necessary Step for Graph Anomaly Detection in SDM,2023. [paper][code]

Graph Anomaly Detection Related Survey

• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning in TKDE, 2021. [paper]

• BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs in NeurIPS, 2022. [paper][code]

• GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection in NeurIPS, 2023. [paper][code]

• A survey of imbalanced learning on graphs: Problems, techniques, and future direction in Arxiv, 2024. [paper]

• Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection:A Benchmark in Arxiv, 2024. [paper][code]

Anomaly Detection Related Survey

• Deep Learning for Anomaly Detection: A Review in CSUR, 2020. [paper]

• Weakly Supervised Anomaly Detection: A Survey in Arxiv, 2023. [paper][code]