Graph Anomaly Detection

Graph anomaly detection (GAD) aims to identify unusual patterns—nodes, edges, or subgraphs—within complex network data. Current research heavily utilizes graph neural networks (GNNs), often incorporating contrastive learning, autoencoders, and reinforcement learning to improve anomaly detection accuracy and efficiency, with a growing emphasis on handling noisy labels, multi-view data, and temporal dynamics. GAD's significance lies in its broad applicability across diverse fields, including fraud detection, cybersecurity, and social network analysis, where identifying outliers is crucial for maintaining system integrity and security.

Papers

December 2, 2022

Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment
Qizhou Wang, Guansong Pang, Mahsa Salehi, Wray Buntine, Christopher Leckie
Anomaly Detection Graph Anomaly Detection Contrastive Alignment Novel Domain Adaptation Anomaly Aware

December 1, 2022

Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View
Jingcan Duan, Siwei Wang, Pei Zhang, En Zhu, Jingtao Hu, Hu Jin, Yue Liu, Zhibin Dong
Graph Contrastive Learning Graph Anomaly Detection Anomalous Graph Robust Graph Scale Contrastive Learning Augmented View Maximum Common Subgraph

November 28, 2022

ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness
Jingcan Duan, Bin Xiao, Siwei Wang, Haifang Zhou, Xinwang Liu
Graph Anomaly Detection Attributed Network Network Anomaly Detection Anomaly Node ApeRIodic SEmi Parametric Topology Attack

November 22, 2022

MGADN: A Multi-task Graph Anomaly Detection Network for Multivariate Time Series
Weixuan Xiong, Xiaochen Sun
Anomaly Detection LSTM Network Multivariate Time Series Graph Anomaly Detection

October 18, 2022

September 29, 2022

Graph Anomaly Detection with Graph Neural Networks: Current Status and Challenges
Hwan Kim, Byung Suk Lee, Won-Yong Shin, Sungsu Lim
Graph Neural Network Technical Challenge Graph Classification Graph Anomaly Detection Graph AutoEncoder Current State Anomalous Graph

September 21, 2022

Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
Shuang Zhou, Xiao Huang, Ninghao Liu, Fu-Lai Chung, Long-Kai Huang
Data Augmentation Stronger Generalizability Graph Anomaly Detection Training Graph Semi Supervised Graph Anomaly Detection

August 17, 2022

AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approach
Shujie Yang, Binchi Zhang, Shangbin Feng, Zhaoxuan Tan, Qinghua Zheng, Jun Zhou, Minnan Luo
Graph Anomaly Detection Heterogeneous Information Network Heterogeneity Challenge Triple Attention

June 30, 2022

DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
Xuanwen Huang, Yang Yang, Yang Wang, Chunping Wang, Zhisheng Zhang, Jiarong Xu, Lei Chen, Michalis Vazirgiannis
Dynamic Graph Graph Anomaly Detection Anomaly Sample Financial Dataset Anomaly Node

May 31, 2022

Rethinking Graph Neural Networks for Anomaly Detection
Jianheng Tang, Jiajin Li, Ziqi Gao, Jia Li
Graph Neural Network Anomaly Detection Graph Anomaly Detection Graph Spectrum

February 11, 2022

From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach
Yu Zheng, Ming Jin, Yixin Liu, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen
Anomaly Detection Unsupervised Setting Graph Anomaly Detection Shot Anomaly Detection Scale Contrastive Learning

Graph Anomaly Detection

Papers

Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment

Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View

ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness

MGADN: A Multi-task Graph Anomaly Detection Network for Multivariate Time Series

DAGAD: Data Augmentation for Graph Anomaly Detection

Graph Anomaly Detection with Unsupervised GNNs

Graph Anomaly Detection with Graph Neural Networks: Current Status and Challenges

Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation

AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approach

DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection

Rethinking Graph Neural Networks for Anomaly Detection

From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach