Exploring and modeling the spreading process of rumors have shown great potential in improving rumor detection performance. However, existing propagation-based rumor detection models often overlook the uncertainty of the underlying propagation structure and typically require a large amount of labeled data for training. To address these challenges, we propose a novel rumor detection framework, namely, the Uncertainty-Inference Contrastive Learning (UICL) model. Specifically, UICL innovatively incorporates an edge-wise augmentation strategy into the general contrastive learning framework, including an edge-inference augmentation component and an EdgeDrop augmentation component, which primarily aim to capture the edge uncertainty of the propagation structure and alleviate the sparsity problem of the original dataset. A new negative sampling strategy is also introduced to enhance contrastive learning on rumor propagation graphs. Furthermore, we use labeled data to fine-tune the detection module. Our experiments, conducted on three real-world datasets, demonstrate that UICL can not only significantly improve detection accuracy but also reduce the dependency on labeled data compared to state-of-the-art baselines.

The discovery of the Ti₃C₂T_x compounds (MXenes) a decade ago opened new research directions and valuable opportunities for high-rate energy storage applications. The unique ability of the MXenes to host various mono- and multivalent cations and their high stability in different electrolyte environments including aqueous, organic, and ionic liquid solutions, promoted the rapid development of advanced MXene-based electrodes for a large variety of applications. Unlike the vast majority of typical intercalation compounds, the electrochemical performance of MXene electrodes is strongly influenced by the presence of co-inserted solvent molecules, which cannot be detected by conventional current/potential electrochemical measurements. Furthermore, the electrochemical insertion of ions into MXene interspaces results in strong coupling with the intercalation-induced structural, dimensional, and viscoelastic changes in the polarized MXene electrodes. To shed light on the charging mechanisms of MXene systems and their associated phenomena, the use of a large variety of real-time monitoring techniques has been proposed in recent years. This review summarizes the most essential findings related to the charging mechanism of Ti₃C₂T_x electrodes and their potential induced structural and mechanical phenomena obtained by in situ investigations.