Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection

doi:doi:10.57702/7r7312uz

Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection

A critical aspect of Graph Neural Networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable.

BibTex:

@dataset{Chunjing_Xiao_and_Shikang_Pang_and_Xovee_Xu_and_Xuan_Li_and_Goce_Trajcevski_and_Fan_Zhou_2024,
    abstract = {A critical aspect of Graph Neural Networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable.},
    author = {Chunjing Xiao and Shikang Pang and Xovee Xu and Xuan Li and Goce Trajcevski and Fan Zhou},
    doi = {10.57702/7r7312uz},
    institution = {No Organization},
    keyword = {'Anomaly Detection', 'Counterfactual Data Augmentation', 'Graph Neural Networks'},
    month = {dec},
    publisher = {TIB},
    title = {Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection},
    url = {https://service.tib.eu/ldmservice/dataset/counterfactual-data-augmentation-with-denoising-diffusion-for-graph-anomaly-detection},
    year = {2024}
}