XiaoxiaoMa-MQ / Awesome-Deep-Graph-Anomaly-Detection

Awesome graph anomaly detection techniques built based on deep learning frameworks. Collections of commonly used datasets, papers as well as implementations are listed in this github repository. We also invite researchers interested in anomaly detection, graph representation learning, and graph anomaly detection to join this project as contributors and boost further research in this area.

Awesome-Deep-Graph-Anomaly-Detection

A collection of papers on deep learning for graph anomaly detection, and published algorithms and datasets.

• Awesome-Deep-Graph-Anomaly-Detection
  • A Timeline of graph anomaly detection
  • Surveys
  • Anomalous Node Detection
  • Anomalous Edge Detection
  • Anomalous Sub-graph Detection
  • Anomalous Graph-Level Detection
  • Graph-Based Anomaly Detection Methods
  • Open-sourced Graph Anomaly Detection Libraries
  • Datasets
    • Mostly-used Benchmark Datasets
    • Citation/Co-authorship Networks
    • Social Networks
    • Co-purchasing Networks
    • Transportation Networks
  • Tools

---

A Timeline of graph anomaly detection

Surveys

Paper Title	Venue	Year
A Comprehensive Survey on Graph Anomaly Detection with Deep Learning	TKDE	2021
Deep learning for anomaly detection	ACM Comput. Surv.	2021
Anomaly detection for big data using efficient techniques: A review	AIDE	2021
Anomalous Example Detection in Deep Learning: A Survey	IEEE	2021
Outlier detection: Methods, models, and classification	ACM Comput. Surv.	2020
A comprehensive survey of anomaly detection techniques for high dimensional big data	J. Big Data	2020
Machine learning techniques for network anomaly detection: A survey	Int. Conf. Inform. IoT Enabling Technol	2020
Fraud detection: A systematic literature review of graph-based anomaly detection approaches	DSS	2020
A comprehensive survey on network anomaly detection	Telecommun. Syst.
A survey of deep learning-based network anomaly detection	Clust. Comput.	2019
Combining machine learning with knowledge engineering to detect fake news in social networks-a survey	AAAI	2019
Deep learning for anomaly detection: A survey	arXiv	2019
Anomaly detection in dynamic networks: A survey	Rev. Comput. Stat.	2018
A survey on social media anomaly detection	SIGKDD	2016
Graph based anomaly detection and description: A survey	Data Min. Knowl. Discovery	2015
Anomaly detection in online social networks	Soc. Networks	2014
A survey of outlier detection methods in network anomaly identification	Comput. J.	2011
Anomaly detection: A survey	ACM Comput. Surv.	2009

---

Anomalous Node Detection

Paper Title	Venue	Year	Model	Code
ComGA: Community-Aware Attributed Graph Anomaly Detection	WSDM	2022	ComGA	[Code]
Anomaly detection on attributed networks via contrastive self-supervised learning	TNNLS	2021	CoLA	[Code]
Cross-domain graph anomaly detection	TNNLS	2021	-	-
A Synergistic Approach for Graph Anomaly Detection with Pattern Mining and Feature Learning	TNNLS	2021	PamFul	[Code]
ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning	CIKM	2021	ANEMONE	[Code]
Error-bounded Graph Anomaly Loss for GNNs	CIKM	2021	GAL	[Code]
Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection	TKDE	2021	SL-GAD	[Code]
Fraudre: Fraud detection dual-resistant to graph inconsistency and imbalance	ICDM	2021	Fraudre	[Code]
Few-shot network anomaly detection via cross-network meta-learning	WWW	2021	-	-
Towards Consumer Loan Fraud Detection: Graph Neural Networks with Role-Constrained Conditional Random Field	AAAI	2021	-	-
One-class graph neural networks for anomaly detection in attributed networks	NCA	2021	OCGNN	[Code]
Decoupling representation learning and classification for gnn-based anomaly detection	SIGIR	2021	DCI	[Code]
Resgcn: Attention-based deep residual modeling for anomaly detection on attributed networks	ML	2021	Resgcn	[Code]
Selective network discovery via deep reinforcement learning on embedded spaces	ANS	2021	NAC	-
A deep multi-view framework for anomaly detection on attributed networks	TKDE	2020	ALARM	-
Enhancing graph neural network-based fraud detectors against camouflaged fraudsters	CIKM	2020	CARE-GNN	[Code]
Outlier resistant unsupervised deep architectures for attributed network embedding	WSDM	2020	DONE/AdONE	[Code]
Gcn-based user representation learning for unifying robust recommendation and fraudster detection	SIGIR	2020	GraphRfi	-
Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection	SIGIR	2020	GraphConsis	[Code]
Inductive anomaly detection on attributed networks	IJCAI	2020	AEGIS	-
Anomalydae: Dual autoencoder for anomaly detection on attributed networks	ICAPSP	2020	Anomalydae	[Code]
Specae: Spectral autoencoder for anomaly detection in attributed networks	CIKM	2019	Specae	-
A semi-supervised graph attentive network for financial fraud detection	ICDM	2019	SemiGNN	[Code]
Deep anomaly detection on attributed networks	SDM	2019	Dominant	[Code]
One-class adversarial nets for fraud detection	AAAI	2019	OCAN	[Code]
Interactive anomaly detection on attributed networks	WSDM	2019	GraphUCB	-
Fdgars: Fraudster detection via graph convolutional networks in online app review system	WWW	2019	Wang et al.	[Code]
A robust embedding method for anomaly detection on attributed networks	IJCNN	2019	REMAD	-
Semi-supervised embedding in attributed networks with outliers	SDM	2018	SEANO	-
Netwalk: A flexible deep embedding approach for anomaly detection in dynamic networks	SIGKDD	2018	Netwalk	[Code]
Anomalous: A joint modeling approach for anomaly detection on attributed networks	IJCAI	2018	ANOMALOUS	-
Accelerated local anomaly detection via resolving attributed networks	IJCAI	2017	ALAD	-
Radar: Residual analysis for anomaly detection in attributed networks	IJCAI	2017	Radar	[Code]
Anomaly detection in dynamic networks using multi-view time-series hypersphere learning	CIKM	2017	MTHL	-
An embedding approach to anomaly detection	ICDE	2016	-	[Code]
Oddball: Spotting anomalies in weighted graphs	PAKDD	2016	Oddball	[Code]
Fraudar: Bounding graph fraud in the face of camouflage	SIGKDD	2016	Fraudar	[Code]
Intrusion as (anti)social communication: characterization and detection	SIGKDD	2012	-	-

---

Anomalous Edge Detection

Paper Title	Venue	Year	Model	Code
Anomaly Detection in Dynamic Graphs via Transformer	TKDE	2021	TADDY	[Code]
efraudcom: An e-commerce fraud detection system via competitive graph neural networks	IS	2021	efraudcom	[Code]
Unified graph embedding-based anomalous edge detection	IJCNN	2020	-	-
AANE: Anomaly aware network embedding for anomalous link detection	ICDM	2020	AANE	-
Addgraph: Anomaly detection in dynamic graph using attention-based temporal gcn	IJCAI	2019	Addgraph	-
Netwalk: A flexible deep embedding approach for anomaly detection in dynamic networks	SIGKDD	2018	Netwalk	[Code]

---

Anomalous Sub-graph Detection

Paper Title	Venue	Year	Model	Code
SliceNDice: Mining suspicious multi-attribute entity groups with multi-view graphs	arXiv	2020	SliceNDice	[Code]
Deep structure learning for fraud detection	ICDM	2018	DeepFD	[Code]
Fraudne: A joint embedding approach for fraud detection	IJCNN	2018	FraudNE	-

---

Anomalous Graph-Level Detection

Paper Title	Venue	Year	Model	Code
User preference-aware fake news detection	SIGIR	2021	UPFD	[Code]
On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights	arXiv	2021	OCGIN	[Code]
Glad-paw: Graph-based log anomaly detection by position aware weighted graph attention network	PAKDD	2021	Glad-paw	-
Deep into hypersphere: Robust and unsupervised anomaly discovery in dynamic networks	IJCAI	2018	DeepSphere	[Code]

---

Graph-Based Anomaly Detection Methods

Paper Title	Venue	Year	Model	Code
Detecting rumours with latency guarantees using massive streaming data	VLDB J.	2022	-	-
Graph Neural Networks for Anomaly Detection in Industrial Internet of Things	IEEE Internet of Things Journal	2022	-	-
Dynamic Graph-Based Anomaly Detection in the Electrical Grid	Trans. Power Syst.	2021	-	[Code]
Nonparametric Anomaly Detection on Time Series of Graphs	J. Comput. Graph. Stat.	2021	-	[Code]
NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification	SSDBM	2021	NF-GNN	-

---

Open-sourced Graph Anomaly Detection Libraries

Library	Link
pygod	[Github]
DGFraud	[Github]

---

Datasets

Mostly-used Benchmark Datasets

• BlogCatalog https://github.com/XiaoxiaoMa-MQ/Awesome-Deep-Graph-Anomaly-Detection/tree/main/Datasets
• ACM https://github.com/XiaoxiaoMa-MQ/Awesome-Deep-Graph-Anomaly-Detection/tree/main/Datasets
• Flickr https://github.com/XiaoxiaoMa-MQ/Awesome-Deep-Graph-Anomaly-Detection/tree/main/Datasets

Citation/Co-authorship Networks

• Citeseer, Cora, Pubmed https://linqs.soe.ucsc.edu/data
• DBLP http://snap.stanford.edu/data/com-DBLP.html, http://www.informatik.uni-trier.de/ ̃ley/db/
• ACM http://www.arnetminer.org/open-academic-graph

Social Networks

• Enron http://odds.cs.stonybrook.edu/#table2
• UCI Message http://archive.ics.uci.edu/ml
• Google+ https://wangbinghui.net/dataset.html
• Twitter Sybil https://wangbinghui.net/dataset.html
• Twitter World-Cup2014 http://shebuti.com/SelectiveAnomalyEnsemble/
• Twitter Security2014 http://shebuti.com/SelectiveAnomalyEnsemble/
• Reality Mining http://shebuti.com/SelectiveAnomalyEnsemble/
• NYTNews http://shebuti.com/SelectiveAnomalyEnsemble/
• Politifact https://github.com/safe-graph/GNN-FakeNews
• Gossipcop https://github.com/safe-graph/GNN-FakeNews

Co-purchasing Networks

• Disney Calls https://www.ipd.kit.edu/mitarbeiter/muellere/consub/
• Amazon-v1 https://www.ipd.kit.edu/mitarbeiter/muellere/consub/
• Amazon-v2 https://github.com/dmlc/dgl/blob/master/python/dgl/data/fraud.py
• Elliptic https://www.kaggle.com/ellipticco/elliptic-data-set
• Yelp https://github.com/dmlc/dgl/blob/master/python/dgl/data/fraud.py

Transportation Networks

• New York City Taxi http://www.nyc.gov/html/tlc/html/about/triprecorddata.shtml

---

Tools

• Gephi https://gephi.org/
• Pajek http://mrvar.fdv.uni-lj.si/pajek/
• LFR https://www.santofortunato.net/resources

---

Disclaimer

If you have any questions or updated news on graph anomaly detection, please feel free to contact us. We also invite researchers interested in anomaly detection, graph representation learning, and graph anomaly detection to join this project as contributors and boost further research in this area.

Emails: [e-mail], [e-mail].