Skip to content

[VLDB'22] Anomaly Detection using Transformers, self-conditioning and adversarial training.

License

Notifications You must be signed in to change notification settings

TIKI-Institut/TranAD

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

License Python 3.7, 3.8 Hits

TranAD

This repository supplements our paper "TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data" accepted in VLDB 2022. This is a refactored version of the code used for results in the paper for ease of use. Follow the below steps to replicate each cell in the results table. The code is provided as-is. Due to limited resources, we are unable to provide support on any issues you may experience with installing or running the tool.

Our work has been discussed in the PodBean podcast! See here.

Results

Alt text

Installation

This code needs Python-3.7 or higher.

pip3 install torch==1.8.1+cpu torchvision==0.9.1+cpu torchaudio===0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
pip3 install -r requirements.txt

Dataset Preprocessing

Preprocess all datasets using the command

python3 preprocess.py SMAP MSL SWaT WADI SMD MSDS UCR MBA NAB

Distribution rights to some datasets may not be available. Check the readme files in the ./data/ folder for more details. If you want to ignore a dataset, remove it from the above command to ensure that the preprocessing does not fail.

Result Reproduction

To run a model on a dataset, run the following command:

python3 main.py --model <model> --dataset <dataset> --retrain

where <model> can be either of 'TranAD', 'GDN', 'MAD_GAN', 'MTAD_GAT', 'MSCRED', 'USAD', 'OmniAnomaly', 'LSTM_AD', and dataset can be one of 'SMAP', 'MSL', 'SWaT', 'WADI', 'SMD', 'MSDS', 'MBA', 'UCR' and 'NAB. To train with 20% data, use the following command

python3 main.py --model <model> --dataset <dataset> --retrain --less

You can use the parameters in src/params.json to set values in src/constants.py for each file.

Note: to reproduce exact results of baselines, use their original codebases (links given in our paper) as the ones implemented in this repository are not the ones used in the paper, which used the original versions. The versions provided here are for use of initial comparison and may not be identical to the original versions.

For ablation studies, use the following models: 'TranAD_SelfConditioning', 'TranAD_Adversarial', 'TranAD_Transformer', 'TranAD_Basic'.

The output will provide anomaly detection and diagnosis scores and training time. For example:

$ python3 main.py --model TranAD --dataset SMAP --retrain 
Using backend: pytorch
Creating new model: TranAD
Training TranAD on SMAP
Epoch 0,        L1 = 0.09839354782306504
Epoch 1,        L1 = 0.039524692888342115
Epoch 2,        L1 = 0.022258711623482686
Epoch 3,        L1 = 0.01833707226553135
Epoch 4,        L1 = 0.016330517334598792
100%|███████████████████████████████████████████████████████████████████| 5/5 [00:03<00:00,  1.57it/s]
Training time:     3.1920 s
Testing TranAD on SMAP
{'FN': 0,
 'FP': 182,
 'Hit@100%': 1.0,
 'Hit@150%': 1.0,
 'NDCG@100%': 0.9999999999999999,
 'NDCG@150%': 0.9999999999999999,
 'TN': 7575,
 'TP': 748,
 'f1': 0.8915325929177795,
 'precision': 0.8043010666204187,
 'recall': 0.9999999866310163,
 'threshold': 0.16133320075167037}

All outputs can be run multiple times to ensure statistical significance.

Supplementary video

IMAGE ALT TEXT HERE

Cite this work

Our paper is available in the Proceedings of VLDB: http://vldb.org/pvldb/vol15/p1201-tuli.pdf. If you use this work, please cite using the following bibtex entry.

@article{tuli2022tranad,
  title={{TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data}},
  author={Tuli, Shreshth and Casale, Giuliano and Jennings, Nicholas R},
  journal={Proceedings of VLDB},
  volume={15},
  number={6},
  pages={1201-1214},
  year={2022}
}

License

BSD-3-Clause. Copyright (c) 2022, Shreshth Tuli. All rights reserved.

See License file for more details.

About

[VLDB'22] Anomaly Detection using Transformers, self-conditioning and adversarial training.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%