Rumor Detection Based on Supervised Multiprototype Contrastive Learning

Abstract

Graph neural networks (GNNs) have shown great promise in rumor detection by leveraging user interactions and propagation structures. However, existing GNN-based methods primarily aggregate low-frequency signals, leading to oversmoothing and the loss of distinctive features in user feedback. Additionally, the data imbalance and sparsity in social media platforms hinder the training of robust detection models. To address these challenges, this article proposes the signed graph transformer network (SGTN) and supervised multiprototype contrastive learning (SMPCL) framework. SGTN adaptsively captures low-frequency similarities and high-frequency differences in user comments, effectively enhancing the representation of relationships in rumor propagation. SMPCL introduces learnable prototypes for each class, mitigating the effects of data imbalance and enabling more effective contrastive learning in small batches. Extensive experiments on real-world datasets, including Twitter15, Twitter16, and PHEME, demonstrate the superior performance of the proposed framework. SGTN and SMPCL achieve significant improvements, with the highest accuracy of 89.7% on Twitter15, 91.3% on Twitter16, and 84.3% on PHEME. Compared with state-of-the-art models, SMPCL achieves up to 3.5% F1-score gains in rumor classification tasks, showcasing its robustness and effectiveness in addressing oversmoothing and data imbalance challenges.