Graph Contrastive Learning With Feature Augmentation for Rumor Detection

While online social media brings convenience to people’s communication, it has also caused the widespread spread of rumors and brought great harm. Recent deep-learning approaches attempt to identify rumors by engaging in interactive user feedback. However, the performance of these models suffers from insufficient and noisy labeled data. In this article, we propose a novel rumor detection model called graph contrastive learning with feature augmentation (FAGCL), which injects noise into the feature space and learns contrastively by constructing asymmetric structures. FAGCL takes user preference and news embedding as the initial features of the rumor propagation tree and then adopts a graph attention network to update node representations. To obtain the graph-level representation for rumor classification, FAGCL fuses multiple pooling techniques. Moreover, FAGCL adopts graph contrastive learning as an auxiliary task to constrain the representation consistency. Contrastive learning on noisy data mines the supervision information of the rumor propagation tree itself, making the model more robust and effective. Results on two real-world datasets demonstrate that our proposed FAGCL model achieves significant improvements over the baseline models.