Towards Robust Rumor Detection with Graph Contrastive and Curriculum Learning

Abstract

Establishing a robust rumor detection model is vital in safeguarding the veracity of information on social media platforms. However, existing approaches to stopping rumor from spreading rely on abundant and clean training data, which is rarely available in real-world scenarios. In this work, we aim to develop a trustworthy rumor detection model that can handle inadequate and noisy labeled data. Our work addresses robust rumor detection, including classic and early detection, as well as five types of robustness issues: noisy and incomplete propagation, label scarcity and noise, and user disappearance. We propose a novel method, Robustness-Enhanced Rumor Detection (RERD), which mainly leverages the information propagation graphs of source tweets, along with user profiles and retweeting knowledge, for model learning. The novelty of RERD is four-fold. First, we jointly exploit the propagation structures of non-text and text retweets to learn the representation of a source tweet. Second, we simultaneously utilize the top-down and bottom-up information flows with relational propagations for graph representation learning. Third, to have effective early and robust detection, we implement contrastive learning on graphs with early and complete views of information propagation so that small snapshots can foresee their future shapes. Last, we use curriculum pseudo-labeling to mitigate the impact of label scarcity and noisy labels, and to correct representations learned from corrupted data. Experimental results on three benchmark datasets demonstrate that RERD consistently outperforms competitors in classic, early, and robust rumor detection scenarios. To the best of our knowledge, we are the first to simultaneously cope with early and five robust detections of rumors.