Counterfactual Graph Learning for Anomaly Detection with Feature Disentanglement and Generation (Student Abstract)
Abstract
Graph anomaly detection has received remarkable research interests, and various techniques have been employed for enhancing detection performance. However, existing models tend to learn dataset-specific spurious correlations based on statistical associations. A well-trained model might suffer from performance degradation when applied to newly observed nodes with different environments. To handle this situation, we propose CounterFactual Graph Anomaly Detection model, CFGAD. In this model, we design a gradient-based separator to disentangle node features into class features and environment features. Then, we present a weight-varying diffusion model to combine class features and environment features from different nodes to generate counterfactual samples. These counterfactual samples will be adopted to enhance model robustness. Comprehensive experiments demonstrate the effectiveness of our CFGAD.
Cite
Text
Wei et al. "Counterfactual Graph Learning for Anomaly Detection with Feature Disentanglement and Generation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30524Markdown
[Wei et al. "Counterfactual Graph Learning for Anomaly Detection with Feature Disentanglement and Generation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/wei2024aaai-counterfactual/) doi:10.1609/AAAI.V38I21.30524BibTeX
@inproceedings{wei2024aaai-counterfactual,
title = {{Counterfactual Graph Learning for Anomaly Detection with Feature Disentanglement and Generation (Student Abstract)}},
author = {Wei, Yutao and Shu, Wenzheng and Cheng, Zhangtao and Tai, Wenxin and Xiao, Chunjing and Zhong, Ting},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23682-23683},
doi = {10.1609/AAAI.V38I21.30524},
url = {https://mlanthology.org/aaai/2024/wei2024aaai-counterfactual/}
}