Disent-AD

[AAAI 2025] Disentangling Tabular Data Towards Better One-Class Anomaly Detection

Environments

We run our code on RTX3090 with Python 3.9 and PyTorch 1.13.0.

Dataset Preparation

Download tabular datasets from ODDS and ADBench. Move the data into ./data_preprocess/data.

Run

Run train.py to start training and evaluation.

Citation

If you find this project helpful for your research, please consider citing the following BibTex entry:

@inproceedings{Disent-AD,
  title={Disentangling Tabular Data Towards Better One-Class Anomaly Detection},
  author={Ye, Jianan and Tan, Zhaorui and Hu, Yijie and Yang, Xi and Cheng, Guangliang and Huang, Kaizhu},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2025}
}