Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

CAD

Code for WWW'25 paper "Semi-Supervised Anomaly Detection through Denoising-Aware Contrastive Distance Learning".

CAD is implemented using PyTorch. You may need the packages below to run CAD:

  • numpy==1.23.1
  • torch==1.13.1
  • pyod==1.0.0
  • scikit-learn==1.0.2
  • tqdm==4.65.0

Raw data is accessed from ODDS dataset and ADbench and processed using data_preprocess.py, and processed data can be found in processed_data.

To perfrom anomaly detection, run

python CAD-main.py --dataset Your-dataset --batch_size batch-size --labeled_ratio ratio-of-labeled-anomalies

About

Semi-Supervised Anomaly Detection through Denoising-Aware Contrastive Distance Learning

Resources

Stars

4 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages