Search Results (1,344)

Peer assessment has emerged as a crucial approach for scaling evaluation in educational scenarios, fostering learner engagement, critical thinking, and collaborative learning. Nevertheless, traditional aggregation-based and probabilistic methods often fail to capture the intricate relational dependencies among students and submissions, thereby limiting their capacity to ensure reliable and equitable outcomes. Recent advances in graph neural networks (GNNs) offer promising avenues for representing peer-assessment data as graphs. However, most existing approaches treat all relations uniformly, overlooking variations in the reliability of evaluative interactions. To bridge this gap, we accordingly propose ReSAN (Relation-Sensitive Assessment Network), a novel framework that integrates relation-sensitive attention into the message-passing process. ReSAN dynamically evaluates and weights relationships, enabling the model to distinguish informative signals from noisy or biased assessments. Comprehensive experiments on both synthetic and real-world datasets demonstrate that ReSAN consistently surpasses strong baselines in prediction accuracy and robustness. These findings underscore the importance of explicitly modeling evaluator reliability for effectively capturing the dynamics of peer-assessment networks. Overall, this work advances reliable graph-based evaluation methods and provides new insights into leveraging representation learning techniques for educational analytics. Full article

Background/Objectives: Lower-grade gliomas (LGGs) are a biologically and clinically heterogeneous group of brain tumors, for which molecular stratification plays essential role in diagnosis, prognosis, and therapeutic decision-making. Conventional unimodal classifiers do not necessarily describe cross-layer regulatory dynamics which entail the heterogeneity of glioma. Methods: This paper presents a protein–protein interaction (PPI)-informed hybrid model that combines multi-omics profiles, including RNA expression, DNA methylation, and microRNA expression, with a Graph Attention Network (GAT), Random Forest (RF), and logistic stacking ensemble learning. The proposed model utilizes ElasticNet-based feature selection to obtain the most informative biomarkers across omics layers, and the GAT module learns the biologically significant topological representations in the PPI network. The Synthetic Minority Over-Sampling Technique (SMOTE) was used to mitigate the class imbalance, and the model performance was assessed using a repeated five-fold stratified cross-validation approach using the following performance metrics: accuracy, precision, recall, F1-score, ROC-AUC, and AUPRC. Results: The findings illustrate that a combination of multi-omics data increases subtype classification rates (up to 0.984 ± 0.012) more than single-omics methods, and DNA methylation proves to be the most discriminative modality. In addition, analysis of interpretability using attention revealed the major subtype-specific biomarkers, including UBA2, LRRC41, ANKRD53, and WDR77, that show great biological relevance and could be used as diagnostic and therapeutic tools. Conclusions: The proposed multi-omics based on a biological and explainable framework provides a solid computational approach to molecular stratification and biomarker identification in lower-grade glioma, bridging between predictive power, biological clarification, and clinical benefits. Full article

Effective feature extraction is a key issue in hyperspectral image (HSI) classification task. Recent works have studied hyperspectral classification models based on various deep architectures. However, the specific architecture cannot fully exploit the complementary diversity of global and local features in HSIs, resulting in suboptimal results. To address these issues, we fully utilize the advantages of GNN and CNN in global and local feature extraction and design a new end-to-end global–local feature fusion enhancement network (GLFFEN). Specifically, we first construct a GNN with dynamically weighted neighbor contributions using superpixel-segmented patches as nodes, named the Graph Attention (GA) branch. Additionally, we design a spatial–spectral feature attention module (SSFAM) to enhance the ability of the CNN to extract spatial and spectral features in local neighborhoods, termed the spatial–spectral feature attention (SSFA) branch. Moreover, a multi-feature adaptive fusion (MAF) module is proposed to solve the problem of weight distribution during global–local feature fusion. Experiments on three well-known HSI datasets have shown that our GLFFEN surpasses state-of-the-art (SOTA) methods on three widely used metrics. Full article

Recent advances in Chinese Named Entity Recognition (CNER) have integrated lexical features and factual knowledge into pretrained language models. However, existing lexicon-based methods often inject knowledge as restricted, isolated token-level information, lacking rich semantic and structural context. Knowledge graphs (KGs), comprising relational triples, offer explicit relational semantics and reasoning capabilities, while Graph Convolutional Networks (GCNs) effectively capture complex sentence structures. We propose KGGCN, a unified KG-enhanced GCN framework for CNER. KGGCN introduces external factual knowledge without disrupting the original word order, employing a novel end-append serialization scheme and a visibility matrix to control interaction scope. The model further utilizes a two-phase GCN stack, combining a standard GCN for robust aggregation with a multi-head attention GCN for adaptive structural refinement, to capture multi-level structural information. Experiments on four Chinese benchmark datasets demonstrate KGGCN’s superior performance. It achieves the highest F1-scores on MSRA (95.96%) and Weibo (71.98%), surpassing previous bests by 0.26 and 1.18 percentage points, respectively. Additionally, KGGCN obtains the highest Recall on OntoNotes (84.28%) and MSRA (96.14%), and the highest Precision on MSRA (95.82%), Resume (96.40%), and Weibo (72.14%). These results highlight KGGCN’s effectiveness in leveraging structured knowledge and multi-phase graph modeling to enhance entity recognition accuracy and coverage across diverse Chinese texts. Full article

Early and accurate detection of brain tumors is critical for MRI-based diagnosis. Conventional convolutional neural networks often struggle to capture fine-grained details, small or boundary-ambiguous lesions, and hemispheric symmetry patterns. To address these limitations, we propose S-ResGCN, a symmetry-aware framework integrating hierarchical feature extraction, attention mechanisms, and graph-based classification. S-ResGCN employs a ResNet50 backbone to extract multi-level features, with Convolutional Block Attention Modules applied to intermediate and deep layers to enhance key information and discriminative features. Furthermore, we introduce a novel self-paired regularization to enforce feature consistency between original and horizontally flipped images, improving sensitivity to bilateral symmetric structures. Extracted features are converted into nodes and modeled as a small graph, and a graph convolutional network captures inter-node relationships to generate symmetry-aware predictions. Evaluation on three publicly available brain tumor MRI datasets demonstrates that S-ResGCN achieves average accuracies of 99.83%, 99.37% and 99.26% ± 0.16, with consistently high precision, recall, and F1-scores. These results indicate that S-ResGCN effectively captures fine-grained and symmetric tumor characteristics often overlooked by conventional models, providing a robust and efficient tool for automated, graph convolutional network. Full article

To comprehensively capture conversational emotion information within and between modalities, address the challenge of global and local feature modelling in conversation, and enhance the accuracy of multimodal conversation emotion recognition, we present a model called Multimodal Transformer and GNN for Emotion Recognition in Conversations (MTG-ERC). The model incorporates a multi-level Transformer fusion module that employs multi-head self-attention and cross-modal attention mechanisms to effectively capture interaction patterns within and between modalities. To address the shortcomings of attention-mechanism-based models in capturing short-term dependencies, we introduce a directed multi-relational graph fusion module, which employs directed graphs and multiple relation types to achieve efficient multimodal information fusion and to model short-term, speaker-dependent emotional shifts. By integrating the outputs of these two modules, the MTG-ERC model effectively combines global and local conversational emotion features and enhances intra-modal and inter-modal emotional interactions. The proposed model shows consistent improvements (around 1% absolute) in both accuracy and weighted F1 on the IEMOCAP and MELD datasets when compared with other baseline models. This highlights the model’s strong performance indicators and validates its effectiveness in comparison to existing models. Full article

The increasing reliance on Internet-based services has been accompanied by a rapid growth in cyber threats, particularly phishing attacks using misleading Uniform Resource Locators (URLs) to mislead users and compromise sensitive data. This paper proposes a hybrid deep learning architecture that integrates Graph Convolutional Networks (GCN), Attention Mechanism and Long Short-Term Memory (LSTM) networks, and for accurate classification of malicious and benign URLs. The model combines sequential pattern recognition through LSTM, structural graph representations via GCN, and feature prioritization using attention to enhance detection performance. Experiments were conducted on a labeled URL dataset of 100,000 and subsequently 200,000 samples, using consistent training and testing splits. The proposed model showed stable performance across different dataset sizes and ultimately outperformed other approaches on the expanded dataset, demonstrating stronger generalization capabilities. These findings highlight the effectiveness of the proposed hybrid model in capturing structural URL features, providing a reliable approach for detecting phishing attacks via structural URL analysis, and offer a foundation for future research on graph-based cybersecurity systems. Full article

Aiming at the problems that traditional heuristic algorithms struggle to capture the complex correlations between damaged equipment and dynamically adjust maintenance task requirements in different task scenarios, the Graph Neural Network (GNN) and Deep Reinforcement Learning (DRL) optimization scheduling method for damaged equipment maintenance tasks is proposed, the purpose is to enhance the efficiency of optimization scheduling in dynamic scenarios. By constructing an attribute graph of damaged equipment and maintenance units, Graph Convolutional Network (GCN) and Graph Attention Network (GAT) are utilized to mine the correlations between nodes. A hierarchical reward function is designed in conjunction with DRL to dynamically adjust the multi-objective weights of maximizing importance, minimizing maintenance time. Hard and soft constraints such as maintenance skill matching, spare parts inventory, and threat thresholds are incorporated into the multi-objective optimization model to achieve real-time scheduling of maintenance tasks in an uncertain task environment. Case studies show that this method can effectively balance multi-objective conflicts through dynamic weight adjustment and online re-optimization mechanisms, making it suitable for multi-constraint task scenarios, compared with the Discrete Particle Swarm Optimization (DPSO) algorithm. GNN-DRL reduces the number of convergence iterations by 40%, improves the learning efficiency by 40%, and enhances the quality of the optimal solution by 11%, effectively improving the efficiency of maintenance task scheduling for damaged equipment. Full article

This study introduces GAT-CAMDA, a novel framework for the structural health monitoring (SHM) of composite materials under temperature-induced variability, leveraging the powerful feature extraction capabilities of Graph Attention Networks (GATs) and advanced domain adaptation (DA) techniques. By combining Maximum Mean Discrepancy (MMD) and Correlation Alignment (CORAL) losses with a domain-discriminative adversarial model, the framework achieves scalable alignment of feature distributions across temperature domains, ensuring robust damage detection. A simple yet at the same time efficient data augmentation process extrapolates damage behaviour across unmeasured temperature conditions, addressing the scarcity of damaged-state observations. Hyperparameter optimisation via Optuna not only identifies the optimal settings to enhance model performance, achieving a classification accuracy of 95.83% on a benchmark dataset, but also illustrates hyperparameter significance for explainability. Additionally, the GAT architecture’s attention demonstrates the importance of various sensors, enhancing transparency and reliability in damage detection. The dual use of Optuna serves to refine model accuracy and elucidate parameter impacts, while GAT-CAMDA represents a significant advancement in SHM, enabling precise, interpretable, and scalable diagnostics across complex operational environments. Full article

An accurate topology of low-voltage distribution grids (LVDGs) serves as the foundation for advanced applications such as line loss analysis, fault location, and power supply planning. This paper proposes a two-stage topology identification strategy for LVDGs based on Contrastive Learning. Firstly, the Dynamic Time Warping (DTW) algorithm is utilized to align the time series of measurement data and evaluate their similarity, yielding the DTW similarity coefficient of the sequences. The Prim algorithm is then employed to construct the initial topology framework. Secondly, aiming at the topology information obtained from the initial identification, an Unsupervised Graph Attention Network (Unsup-GAT) model is proposed to aggregate node features, enabling the learning of complex correlation patterns in unsupervised scenarios. Subsequently, a loss function paradigm that incorporates both InfoNCE loss and power imbalance loss is constructed for updating network parameters, thereby realizing the identification and correction of local connection errors in the topology. Finally, case studies are conducted on 7 LVDGs of different node scales in a certain region of China to verify the effectiveness of the proposed two-stage topology identification strategy. Full article

With the rapid expansion of the civil aviation industry, the surge in flight numbers has led to increasingly pronounced issues of air route congestion and flight conflicts. 4D trajectory prediction, by dynamically adjusting aircraft paths in real time, can prevent air route collisions, alleviate air traffic pressure, and ensure flight safety. Therefore, this paper proposes a combined model—GAT-BiGRU-TPA—based on the Spatio-Temporal Graph Neural Network (STGNN) framework to achieve refined 4D trajectory prediction. This model integrates Graph Attention Networks (GAT) to extract multidimensional spatial features, Bidirectional Gated Recurrent Units (BiGRU) to capture temporal dependencies, and incorporates a Temporal Pattern Attention (TPA) mechanism to emphasize learning critical temporal patterns. This enables the extraction of key information and the deep fusion of spatio-temporal features. Experiments were conducted using real trajectory data, employing a grid search to optimize the observation window size and label length. Results demonstrate that under optimal model parameters (observation window: 30, labels: 4), the proposed model achieves a 45.72% reduction in mean Root Mean Square Error (RMSE) and a 43.40% decrease in Mean Absolute Error (MAE) across longitude, latitude, and altitude compared to the optimal baseline BiLSTM model. Prediction accuracy significantly outperforms multiple mainstream benchmark models. In summary, the proposed GAT-BiGRU-TPA model demonstrates superior accuracy in 4D trajectory prediction, providing an effective approach for refined trajectory management in complex airspace environments. Full article

Natural disasters often compromise telecommunications infrastructure, leading to unstable services or complete communication blackouts that hinder rescue operations and exacerbate victims’ distress. Rapidly deployable alternatives are, therefore, critical to sustaining reliable connectivity in affected regions. This work proposes a self-organizing multi-Unmanned Aerial Vehicle (UAV) swarm network capable of providing stand-alone and temporary coverage to both victims and emergency personnel in areas with compromised infrastructure through access points installed onboard UAVs. To address the challenges of partial observability in decentralized coordination, we introduce the Soft Transformer Recurrent Graph Network (STRGN), a novel encoder–decoder architecture inspired by the transformer model and extending the Soft Deep Recurrent Graph Network (SDRGN). By leveraging multi-head and cross-attention mechanisms, the STRGN captures higher-order spatiotemporal relationships, enabling UAVs to integrate information about neighbor proximity and ground user density when selecting actions. This facilitates adaptive positioning strategies that enhance coverage, fairness, and connectivity under dynamic conditions. Simulation results show that transformer-based approaches, including STRGN, the Soft Transformer Graph Network, and the Transformer Graph Network, consistently outperform SDRGN, and the Soft Deep Graph Network, and Deep Graph Network baselines by approximately $16\%$ across core metrics, while also demonstrating improved scalability across diverse terrains and swarm sizes. These findings highlight STRGN’s potential as a resilient framework for UAV-assisted communications in disaster response. Full article

With the rapid development of modern society and the continuous growth of electricity demand, the stability of power systems has become increasingly critical. In particular, Transient Stability Assessment (TSA) plays a vital role in ensuring the secure and reliable operation of power systems. Existing studies have employed Graph Attention Networks (GAT) to model both the topological structure and vertex attributes of power systems, achieving excellent results under ideal test environments. However, the continuous expansion of power systems and the large-scale integration of renewable energy sources have significantly increased system complexity, posing major challenges to TSA. Traditional methods often struggle to handle various disturbances. To address this issue, we propose a graph attention network framework with multi-branch feature aggregation. This framework constructs multiple GAT branches from different information sources and employs a learnable mask mechanism to enhance diversity among branches. In addition, this framework adopts an uncertainty-aware aggregation strategy to efficiently fuse the information from all branches. Extensive experiments conducted on the IEEE-39 bus and IEEE-118 bus systems demonstrate that our method consistently outperforms existing approaches under different disturbance scenarios, providing more accurate and reliable identification of potential instability risks. Full article

In the context of Industry 4.0 and smart manufacturing, predicting cutting tool remaining useful life (RUL) is crucial for enabling and enhancing the reliability and efficiency of CNC machining. This paper presents an innovative predictive model based on the data fusion architecture of Graph Neural Networks (GNNs) and Transformers to address the complexity of shallow multimodal data fusion, insufficient relational modeling, and single-task limitations simultaneously. The model harnesses time-series data, geometric information, operational parameters, and phase contexts through dedicated encoders, employs graph attention networks (GATs) to infer complex structural dependencies, and utilizes a cross-modal Transformer decoder to generate fused features. A dual-head output enables collaborative RUL regression and health state classification of cutting tools. Experiments are conducted on a multimodal dataset of 824 entries derived from multi-sensor data, constructing a systematic framework centered on tool flank wear width (VB), which includes correlation analysis, trend modeling, and risk assessment. Results demonstrate that the proposed model outperforms baseline models, with MSE reduced by 26–41%, MAE by 33–43%, R² improved by 6–12%, accuracy by 6–12%, and F1-Score by 7–14%. Full article

Steganalysis is a critical research direction in the field of information security. Traditional approaches typically employ convolution operations for feature extraction, followed by classification on noise residuals. However, since steganographic signals are inherently weak, convolution alone cannot fully capture their characteristics. To address this limitation, we propose a steganalysis method based on relationship mining, termed RMNet, which leverages positional relationships of steganographic signals for detection. Specifically, features are modeled as graph nodes, where both locally focused and globally adaptive dynamic adjacency matrices guide the propagation paths of these nodes. Meanwhile, the results are further constrained in the feature space, encouraging intra-class compactness and inter-class separability, thereby increasing inter-class separability of positional features and yielding a more discriminative decision boundary. Additionally, to counter signal attenuation during network propagation, we introduce a multi-scale perception module with cross-attention fusion. Experimental results demonstrate that RMNet achieves performance comparable to state-of-the-art models on the BOSSbase and BOWS2 datasets, while offering superior generalization capability. Full article