Source code for the paper "AAAD: Asynchronous Inter-variable Relationship-Aware Anomaly Detection for Multivariate Time Serie"

1. Install Python3.7, PyTorch $\geq$ 1.4.0.
2. Download data to dataset folder. You can obtain four benchmarks from Google Cloud. All the datasets are well pre-processed. For the SWaT dataset, you can apply for it by following its official tutorial.
3. Train and evaluate. run python main.py. The result records are in the res directory.