enoche / tGraphAD

Research sources on graph-based anomaly detection

Graph-based Anomaly Detection in Time Series (2020 →)

A curated list of recent awesome graph-based anomaly detection resources from 2020 (code first: messy code is better than no code). Please contact us if your work is not in the list.
-- Last updated: 2022/11/02
-- Personal Recommend: 1️⃣ 2️⃣ 3️⃣ 4️⃣ 5️⃣ (With 5️⃣ means a must read.)

Experimental Evaluation

• Anomaly detection in time series: a comprehensive evaluation - Sebastian Schmidl, Phillip Wenig, Thorsten Papenbrock. P-VLDB, Jul 2022 | [pdf] | [code] 5️⃣

General Survey

• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning - Xiaoxiao Ma, Jia Wu, Shan Xue, Jian Yang, Chuan Zhou, Quan Z. Sheng, Hui Xiong, Leman Akoglu. TKDE, Oct 2021 | [pdf] | paper lists

Table of Contents

• 2022
• 2021
• 2020
• Public Datasets
• Personal included
  • Static GAD
  • non-Graph AD

2022

• GANF: Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series - Enyan Dai, Jie Chen. ICLR, May 2022 | [pdf] | [code]
• TranAD: Deep transformer networks for anomaly detection in multivariate time series data - Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings. P-VLDB, Feb 2022 | [pdf] | [code]
• STGAN: Graph convolutional adversarial networks for spatiotemporal anomaly detection - Leyan Deng, Defu Lian, Zhenya Huang, Enhong Chen. TNNLS, Jan 2022 | [code]

2021

• StrGNN: Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs - Lei Cai, Zhengzhang Chen, Chen Luo, Jiaping Gui, Jingchao Ni, Ding Li, Haifeng Chen. CIKM, Oct, 2021 | [pdf] | [code]
• GTA: Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT - Zekai Chen, Dingshuo Chen, Xiao Zhang, Zixuan Yuan, Xiuzhen Cheng. IoTJ, Jul 2021 | [pdf] | [code]
• GDN: Graph Neural Network-Based Anomaly Detection in Multivariate Time Series - Ailin Deng, Bryan Hooi. AAAI, May 2021 | [pdf] | [code]

2020

• Series2Graph: graph-based subsequence anomaly detection for time series - Paul Boniol, Themis Palpanas. P-VLDB, Aug 2020 | [pdf] | code
• MTAD-GAT: Multivariate Time-Series Anomaly Detection via Graph Attention Network - Hang Zhao, Yujing Wang, Juanyong Duan, Congrui Huang, Defu Cao, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, Qi Zhang. ICDM, Nov 2020 | [pdf] | code

Public Datasets (Link verified ✔️)

• [SWaT] (https://itrust.sutd.edu.sg/itrust-labs_datasets/dataset_info/)
• [SMD] (https://github.com/NetManAIOps/OmniAnomaly)
• [SMAP&MSL] (https://drive.google.com/drive/folders/1uahSegdky35rdTeN8rufAzU8osfvyrFw?usp=sharing)

---

Personal Included High-Quality Publications

Static GAD

• Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation - Rongrong Ma, Guansong Pang, Ling Chen, Anton van den Hengel. WSDM, Feb 2022 | [pdf] | [code]

• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection - Yu Zheng; Ming Jin; Yixin Liu; Lianhua Chi; Khoa T. Phan; Yi-Ping Phoebe Chen. TKDE, Oct 2021 | [pdf] | [code]

• Decoupling Representation Learning and Classification for GNN-based Anomaly Detection - Yanling Wang, Jing Zhang, Shasha Guo, Hongzhi Yin, Cuiping Li, Hong Chen. SIGIR, Jul 2021 | [pdf] | [code]

non-Graph AD

• DGHL: Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection - Cristian Challu, Peihong Jiang, Ying Nian Wu, Laurent Callot. AISTATS, Mar 2022 | [pdf] | [code]