Explore the vast range of titles available.

Academic performance is a crucial issue in the field of Online learning analytics. While deep learning-based models have made significant progress in the era of big data, many of these methods need help to capture the complex relationships present in online learning activities and student attributes, which are essential for improving prediction accuracy. We present a novel model for predicting academic performance in this paper. This model harnesses the power of dual graph neural networks to effectively utilize both the structural information derived from interaction activities and the attribute feature spaces of students. The proposed model uses an interaction-based graph neural network module to learn local academic performance representations from online interaction activities and an attribute-based graph neural network to learn global academic performance representations from attribute features of all students using dynamic graph convolution operations. The learned representations from local and global levels are combined in a local-to-global representation learning module to generate predicted academic performances. The empirical study results demonstrate that the proposed model significantly outperforms existing methods. Notably, the proposed model achieves an accuracy of 83.96% for predicting students who pass or fail and an accuracy of 90.18% for predicting students who pass or withdraw on a widely recognized public dataset. The ablation studies confirm the effectiveness and superiority of the proposed techniques.

Predicting drug–drug interactions (DDI) is crucial for preventing adverse reactions in patients and plays a vital role in drug design and development. However, traditional Chinese medicine (TCM) formulations, typically composed of multiple herbal ingredients with diverse bioactive compounds, present a unique challenge in comprehensively assessing potential adverse interactions among their components. To address this challenge, we propose a novel Dual Graph Attention Network (DGAT) designed to predict TCM drug-drug interactions (TCMDDI) by extracting key structural features of active molecules within the herbal ingredients. Our approach leverages graph-based representations of chemical molecules and employs attention mechanism to extract deep structural features, enabling the effective prediction of TCMDDI by capturing spatial structural relationships among different compounds. Furthermore, we construct a comprehensive dataset encompassing three different categories of herbal ingredients, informed by traditional TCM principles. Experimental results reveal that the proposed DGAT method significantly outperforms currently advanced deep learning techniques, including Graph Convolutional Networks, Weave, and Message Passing Neural Networks. Compared to traditional rule-based two-dimensional molecular descriptors, DGAT more effectively captures the spatial structural information of molecules. Notably, DGAT exhibits robust performance and strong generalizability on unseen samples, providing valuable insights for future research on TCMDDI prediction and advancing the integration of artificial intelligence in TCM studies.

Community detection has long been designed to find communities with different structures in various networks. It is now widely believed that these communities often overlap with each other. However, due to the complexity and diversity of the network, it is often difficult to accurately identify the overlapping community structure in many real networks. Considering the above problem, we introduce a dual graph neural network for overlapping community detection (DGOCD) under the framework of the extended Bernoulli–Poisson. First, we build two graphs to model information of different orders between nodes, respectively, and use a set of GCNs as a backbone to learn semantic representations of the above graphs in parallel. Then we introduce the concept of topological potential matrix to aggregate the embedding representations of the two channel graphs. Moreover, for learning the affiliations between nodes and communities, we carry out network reconstruction based on the former information. Finally, the reconstructed network is sent into the GCN to get the final community division. Experimental results on real network datasets demonstrate that the proposed DGOCD consistently outperforms existing methods.

Cell type identification is an indispensable analytical step in single-cell data analyses. To address the high noise stemming from gene expression data, existing computational methods often overlook the biologically meaningful relationships between genes, opting to reduce all genes to a unified data space. We assume that such relationships can aid in characterizing cell type features and improving cell type recognition accuracy. To this end, we introduce scPriorGraph, a dual-channel graph neural network that integrates multi-level gene biosemantics. Experimental results demonstrate that scPriorGraph effectively aggregates feature values of similar cells using high-quality graphs, achieving state-of-the-art performance in cell type identification.

The research on node classification is based on node embeddings. Node classification accuracy can be improved if the embeddings of different nodes are well discriminated. With the rapid development of deep learning, researchers have proposed many graph neural network models (GNNs), such as GCN and GAT, which generally obtain node embeddings by aggregating neighborhood information. However, such methods only emphasize feature aggregation in neighborhoods and do not consider the class labels of nodes, which leads to the oversmoothing problem and weak differences in inter-class nodes. In this paper, we propose a gated graph attention network based on dual graph convolution for node embedding (GGAN-DGC). To strengthen the embedding difference of inter-class nodes, GGAN-DGC introduces a gated attention mechanism. This mechanism utilizes a supervised gated attention (GA) matrix to separate the GNN aggregation process according to the node class, so as to heterogenize the homogenous graphs. The GA matrix is obtained by the dual graph convolutional network (DGC), which can improve the receptive field of the original graph. In addition, GGAN-DGC adopts triplet loss as the global supervision function of node embedding, which can streng-then the class correlation of node embedding at the global level. Finally, based on the obtained node embedding, nodes can be classified correctly. The experimental results on five datasets confirm that our GGAN-DGC model performs better than other representative methods in node classification, especially for datasets with strong heterophily. In addition, we verify that GGAN-DGC can also perform better than other methods in graph classification experiments.

The design of 3D scenes is of great significance, and one of the crucial areas is interior scene design. This study not only pertains to the living environment of individuals but also has applications in the design and development of virtual environments. Previous work on indoor scenes has focused on understanding and editing existing indoor scenes, such as scene reconstruction, segmentation tasks, texture, object localization, and rendering. In this study, we propose a novel task in the realm of indoor scene comprehension, amalgamating interior design principles with professional evaluation criteria: 3D indoor scene design assessment. Furthermore, we propose an approach using a transformer encoder–decoder architecture and a dual-graph convolutional network. Our approach facilitates users in posing text-based inquiries; accepts input in two modalities, point cloud representations of indoor scenes and textual queries; and ultimately generates a probability distribution indicating positive, neutral, and negative assessments of interior design. The proposed method uses separately pre-trained modules, including a 3D visual question-answering module and a dual-graph convolutional network for identifying emotional tendencies of text.

As distributed terminals are increasingly integrated into modern power systems with high penetration of renewable energy and decentralized resources, access control mechanisms must support continuous and highly detailed trust assessment. Existing approaches based on machine learning primarily rely on network traffic features from a single source and analyze terminals in isolation, which limits their ability to capture complex device states and correlated attack behaviors. This paper presents a trust assessment framework for distributed power grid terminals that combines multidimensional behavioral modeling with dual domain graph neural networks. Behavioral features are collected from network traffic, runtime environment, and hardware or kernel events and are fused into compact representations through a variational autoencoder to mitigate redundancy and reduce computational overhead. Based on the fused features and observed communication relationships, two graphs are constructed in parallel: a feature domain graph reflecting behavioral similarity and a topological domain graph capturing communication structure between terminals. Graph convolution is performed in both domains to jointly model individual behavioral risk and correlation across terminals. A fusion mechanism based on attention is further introduced to adaptively integrate embeddings specific to each domain, together with a loss function that enforces both shared and complementary representations across domains. Experiments conducted on the CIC EV Charger Attack Dataset 2024 show that the proposed framework achieves a classification accuracy of 96.84%, while maintaining a recall rate above 95% for the low trust category. These results indicate that incorporating multidimensional behavior perception and dual domain relational modeling improves trust assessment performance for distributed power grid terminals under complex attack scenarios.

Social unrest is endemic in many societies. It is a vital task to predict social unrest events be-cause these events can lead to societal changes and endanger public security. We combine two data sources, using social media data as the historical texts and news media data as the ground truth of unrest events. We propose a temporal dual graph convolutional network (TDGCN), which extracts the contextual semantic information and the communication relationship between social network users from the historical texts and constructs two dynamic graphs to capture the implied semantic and temporal features. The TDGCN can predict the occurrence of unrest events. Experimental results on a specific data set of unrest show that the proposed method has better performance than other state-of-the-art social unrest event predictions.

Studying the association between microbes and diseases not only aids in the prevention and diagnosis of diseases, but also provides crucial theoretical support for new drug development and personalized treatment. Due to the time‐consuming and costly nature of laboratory‐based biological tests to confirm the relationship between microbes and diseases, there is an urgent need for innovative computational frameworks to anticipate new associations between microbes and diseases. Here, we propose a novel computational approach based on a dual branch graph convolutional network (GCN) module, abbreviated as DBGCNMDA, for identifying microbe–disease associations. First, DBGCNMDA calculates the similarity matrix of diseases and microbes by integrating functional similarity and Gaussian association spectrum kernel (GAPK) similarity. Then, semantic information from different biological networks is extracted by two GCN modules from different perspectives. Finally, the scores of microbe–disease associations are predicted based on the extracted features. The main innovation of this method lies in the use of two types of information for microbe/disease similarity assessment. Additionally, we extend the disease nodes to address the issue of insufficient features due to low data dimensionality. We optimize the connectivity between the homogeneous entities using random walk with restart (RWR), and then use the optimized similarity matrix as the initial feature matrix. In terms of network understanding, we design a dual branch GCN module, namely GlobalGCN and LocalGCN, to fine‐tune node representations by introducing side information, including homologous neighbour nodes. We evaluate the accuracy of the DBGCNMDA model using five‐fold cross‐validation (5‐fold‐CV) technique. The results show that the area under the receiver operating characteristic curve (AUC) and area under the precision versus recall curve (AUPR) of the DBGCNMDA model in the 5‐fold‐CV are 0.9559 and 0.9630, respectively. The results from the case studies using published experimental data confirm a significant number of predicted associations, indicating that DBGCNMDA is an effective tool for predicting potential microbe–disease associations.

Multi-Behavior Recommendation (MBR) attracts much attention in recent years, whose goal is to improve the prediction of the target behavior (i.e., purchase) by exploiting multi-typed auxiliary behaviors (e.g., view, favorite and add-to-cart). Recently, leveraging Graph Convolutional Networks (GCNs) to capture collaborative signals has been the mainstream paradigm for MBR. However, the existing multi-behavior recommendation methods have suffered from two limitations. On the one hand, personalized user preferences hidden in multi-behavior data are not fully exploited. Users’ multiple types of interactions, such as views, clicks, and so on, offer fine-grained and a deep understanding of the preferences. The importance of different types of behaviors should be carefully distinguished. On the other hand, these methods aggregate the original neighbors of target user and item independently. Users’ preferences may change dynamically with a specific target item. Therefore, users’ dynamic preferences based on specific items should be sufficiently considered. These limitations motivate us to propose a novel recommendation model DGAMR ( D ual G raph A ttention Networks for M ulti-behavior R ecommendation), which accurately learns user and item representation by multiple types of behaviors. First, we utilize node-level attention to learn the representation of users and items under specific behavior. Second, behavioral-level attention is used to aggregate different behaviors to generate the final representation of users and items. In addition, we learn the dynamic characteristics of target user and target item by modeling the dependency relation between them. Finally, we utilize the static and dynamic embedding of users/items to predict users’ preferences for items. Extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model.