Compared to text-only online fake news, combined graphic forms of fake news are more likely to gain people's trust. Most of these forms of fake news have been detected using multimodal feature fusion, with less attention being paid to the correlation between two modalities and the interaction within and between individual modalities. To address this problem, we propose a multimodal mechanism based on CLIP for fake news detection, referred to as CLIP-FND. First, the visual encoder and text encoder of the large-scale graphical pre-training model CLIP are used to unify and map the image and text data into the same feature space respectively. Then, the attention mechanism and the bilinear pooling method are used to fuse the text feature vector and the visual feature vector and input to the fake news detector for fake news detection. The experimental results show that the accuracy and F1 value of the model are much higher than the traditional multimodal fake news detection model on the publicly available dataset, which improves the fake news detection effect.

Complex machine learning tasks for knowledge discovery in networked data, such as community detection, node categorization, network visualization, and dimension reduction, have been successfully addressed by coarsening algorithms. It iteratively reduces the original network into a hierarchy of smaller networks, resulting in informative simplifications of the original network at various degrees of detail. Few of these algorithms, however, have been specially built to cope with bipartite networks. Besides of this, current coarsening algorithms present the following theoretical limitations that should be addressed: 1) A high-cost search strategy in dense networks; 2) current coarsening algorithms are usually based on label propagation, which is limited to propagate single-labels; and 3) the synchronous label propagation scheme yields the cyclic oscillation problem. To overcome such limitations, we propose a coarsening algorithm based on multi-label propagation, which is more suitable for large-scale bipartite networks and allows a time-effective implementation. Furthermore, our proposal improves the standard semi-synchronous strategy and simultaneously propagates multiple labels to create the coarsened network representation. The empirical analysis of synthetic and real-world networks provides evidence that our coarsening strategy leads to significant gains regarding accuracy and runtime against standard techniques.