Awesome

CAT: Beyond Efficient Transformer for Content-Aware Anomaly Detection in Event Sequences

This is the origin Pytorch implementation of CAT in the following paper: [CAT: Beyond Efficient Transformer for Content-Aware AnomalyDetection in Event Sequences].

<img src=".\img\Architecture.PNG" height = "300" alt="" align=center /> Figure 1. The architecture of CAT.

Requirements

Python 3.6
matplotlib == 3.1.1
numpy == 1.19.4
pandas == 0.25.1
scikit_learn == 0.21.3
torch == 1.8.0

Dependencies can be installed using the following command:

pip install -r requirements.txt

Data

The log datasets used in the paper can be found in the repo loghub. In this repository, an small sample of the HDFS dataset is proposed for a quick hands-up.

For generating the Log template files, please refer to the official implementation repo of logparser.

Usage

The simplest way of running CAT is to run python main_cat.py --data HDFS.

Contact

If you have any questions, feel free to contact Shengming Zhang through Email (shengming.zhang@rutgers.edu) or Github issues.