RGSE: Robust Graph Structure Embedding for Anomalous Link Detection

Anomalous links such as noisy links or adversarial edges widely exist in real-world networks, which may undermine the credibility of the network study, e.g., community detection in social networks. Therefore, anomalous links need to be removed from the polluted network by a detector. Due to the co-existence of normal links and anomalous links, how to identify anomalous links in a polluted network is a challenging issue. By designing a robust graph structure embedding framework, also called RGSE, the link-level feature representations that are generated from both global embedding view and local stable view can be used for anomalous link detection on contaminated graphs. Comparison experiments on a variety of datasets demonstrate that the new model and its variants achieve up to an average 5.2% improvement with respect to the accuracy of anomalous link detection against the traditional graph representation models. Further analyses also provide interpretable evidence to support the model's superiority.

Automated summary

Anomalous links such as noisy links or adversarial edges are common in real-world networks, which can undermine the credibility of network studies, such as community detection in social networks. To address this issue, a robust graph structure embedding framework called RGSE is proposed, which utilizes link-level feature representations generated from both global embedding view and local stable view for anomalous link detection on contaminated graphs. Experimental results on various datasets show that the new model and its variants achieve up to an average 5.2% improvement in accuracy compared to traditional graph representation models. Further analysis provides interpretable evidence supporting the superiority of the model.