Guoyong Cai

With the rapid proliferation of multimodal social media platforms, fake news has been increasingly disseminated through multiple modalities such as text, images, and videos, posing serious threats to social stability, public cognition, and these platforms’ ecosystem. Existing unimodal fake news detection methods face much challenge in multimodal scenarios, as they can not capture fully cross-modal semantic correlations and inconsistencies. Multimodal fake news detection, which integrates heterogeneous information from text, visual, and audio modalities to explore inter-modal consistency and complementarity, has therefore become a major research focus in recent years. A comprehensive survey of recent advances in multimodal fake news detection is presented in the paper, which consists of systematically reviews of the fundamental concepts, detection tasks, and underlying technical principles in this field. Major benchmark datasets and commonly used evaluation metrics are also introduced, followed by a structured taxonomy of representative detection methods and a summary of their experimental results. Furthermore, the key challenges faced by current research are discussed and promising future research directions are outlined. Compared with existing surveys, this work presents a more comprehensive method categorization that emphasizes the evolution of detection techniques, offers clearer comparisons of datasets and experimental analyses, and provides more practical insights for researchers and practitioners in multimodal fake news detection.

Graph classification has gained significant attention in recent years due to its wide applications in many domains such as cheminformatics, bioinformatics and social networks. Graph neural networks have been proved to be an effective solution for graph classification because of their powerful ability of learning graph node features. However, existing spatial graph convolutional neural networks for node-labeled graph classification utilize one-hot encoding or graph kernel methods to initialize node features, leading to their inability to capture semantic dependencies among graph nodes, with the result of a decrease in graph classification accuracy. In this paper, we propose a Node Semantic-based Spatial Graph ConvolutionalNetwork (NSSGCN) for graph classification which integrates multi-scale node semantic into graph neural network with word embedding. Specifically, we construct multiple corpora of different granularity for a graph dataset, and then leverage the PV-DBOW model to extract multiscale node semantic information from built corpora. Then, we normalize non-Euclidean graph data into 3D tensor data by node ordering and receptive field constructing, during which we propose a node importance measurement considering both node semantic and topology. After that, we design a channel attention based spatial graph convolutional neural network to effectively learn graph feature vectors from these 3D tensor data. Finally, we apply a Dense layer followed by a softmax layer to the learned graph feature vectors to classify graphs. Experimental results show that our proposed method achieves superior graph classification accuracy compared with classical graph kernel methods and state-of-the-art spatial graph neural networks on six benchmark graph datasets. On average, our method achieves a remarkable accuracy improvement of 4.12% in graph classification.

Constrained multiobjective optimization problems (CMOPs) are challenging for evolutionary algorithms (EAs). Due to the interaction of multiple constraints, the constrained Pareto fronts (CPFs) exhibit various complex characteristics, e.g., degeneracy, discontinuous or low feasible ratio. Most algorithms achieve poor convergence and diversity performance on these problems. Therefore, we proposed a coevolutionary framework based on constraints decomposition to solve the complex CMOPs. Specifically, this framework decomposes the CMOP into multiple help subproblems with single constraint, thereby decoupling the complex constraints. Then, the subpopulations optimize these subproblems to assist in solving the original problem. Furthermore, to avoid wasting computational resources, a two-stage strategy was used to fully utilize the auxiliary populations to search for feasible solutions. And an evolutionary state detection strategy based on historical information is proposed, which is used to determine whether the evolution moves to the next stage. The framework can take the advantage of the low complexity of single-constraint problems to help algorithm search the complete feasible regions. Experiments on benchmark problems show that the proposed algorithm is competitive with five other most representative constrained evolutionary algorithms in terms of convergence and diversity performance.