Graph Evidential Learning for Anomaly Detection
This work addresses graph anomaly detection for domains with scarce labeled data, offering an incremental improvement over existing unsupervised methods.
The paper tackles the problem of graph anomaly detection by addressing limitations in graph autoencoders, such as sensitivity to noise and overfitting, and proposes Graph Evidential Learning (GEL), which achieves state-of-the-art performance with high robustness against noise and structural perturbations.
Graph anomaly detection faces significant challenges due to the scarcity of reliable anomaly-labeled datasets, driving the development of unsupervised methods. Graph autoencoders (GAEs) have emerged as a dominant approach by reconstructing graph structures and node features while deriving anomaly scores from reconstruction errors. However, relying solely on reconstruction error for anomaly detection has limitations, as it increases the sensitivity to noise and overfitting. To address these issues, we propose Graph Evidential Learning (GEL), a probabilistic framework that redefines the reconstruction process through evidential learning. By modeling node features and graph topology using evidential distributions, GEL quantifies two types of uncertainty: graph uncertainty and reconstruction uncertainty, incorporating them into the anomaly scoring mechanism. Extensive experiments demonstrate that GEL achieves state-of-the-art performance while maintaining high robustness against noise and structural perturbations.