Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection
This work addresses graph anomaly detection for unsupervised learning, offering a domain-specific incremental improvement.
The paper tackles the problem of graph anomaly detection where abnormal nodes become less distinguishable due to averaging with normal neighbors, proposing CAGAD, a counterfactual data augmentation method using denoising diffusion, which improves performance by an average of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR across four datasets.
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. To tackle this issue, we propose CAGAD -- an unsupervised Counterfactual data Augmentation method for Graph Anomaly Detection -- which introduces a graph pointer neural network as the heterophilic node detector to identify potential anomalies whose neighborhoods are normal-node-dominant. For each identified potential anomaly, we design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. At last, we involve these translated neighbors in GNN neighborhood aggregation to produce counterfactual representations of anomalies. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance. The experimental results on four datasets demonstrate that CAGAD significantly outperforms strong baselines, with an average improvement of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR.