Search Results (2,136)

The optimization of beamforming in multi-base station (multi-BS) reconfigurable intelligent surface (RIS)-aided systems is a challenging task due to its high computational complexity. This paper first demonstrates that an optimized multi-BS system exhibits superior communication performance compared to a centralized large-scale single-BS system. To efficiently solve the complex beamforming problem in the multi-BS environment, this paper proposes a novel optimization solver based on a graph neural network (GNN) that models the physical structure of the system. Experimental results show that the proposed GNN solver finds solutions of higher quality, achieving a 42% performance increase with 45% less total computational complexity compared to a conventional iterative optimization method. Furthermore, when compared to other complex AI models such as transformer and Bi-LSTM, the proposed GNN achieves similar state-of-the-art performance while having less than 1% of the parameters and a fraction of the computational cost. These findings demonstrate that the GNN is a powerful, efficient, and practical solution for beamforming optimization in multi-BS RIS-aided systems, satisfying the demands for performance, computational efficiency, and model compactness. Full article

This article presents an interaction-aware motion planning framework that integrates a graph neural network (GNN) based multi-modal trajectory predictor with a model predictive control (MPC) based planner. Unlike past studies that predict a single future trajectory per agent, our algorithm outputs three distinct trajectories for each surrounding road user, capturing different interaction scenarios (e.g., yielding, non-yielding, and aggressive driving behaviors). We design a GNN-based predictor with bi-directional gated recurrent unit (Bi-GRU) encoders for agent histories, VectorNet-based lane encoding for map context, an interaction-aware attention mechanism, and multi-head decoders to predict trajectories for each mode. The MPC-based planner employs a bicycle model and solves a constrained optimal control problem using CasADi and IPOPT (Interior Point OPTimizer). All three predicted trajectories per agent are fed to the planner; the primary prediction is thus enforced as a hard safety constraint, while the alternative trajectories are treated as soft constraints via penalty slack variables. The designed motion planning algorithm is examined in real-world intersection scenarios from the INTERACTION dataset. Results show that the multi-modal trajectory predictor covers possible interaction outcomes, and the planner produces smoother and safer trajectories compared to a single-trajectory baseline. In high-conflict situations, the multi-modal trajectory predictor anticipates potential aggressive behaviors of other drivers, reducing harsh braking and maintaining safe distances. The innovative method by integrating the GNN-based multi-modal trajectory predictor with the MPC-based planner is the backbone of the effective motion planning algorithm for robust, safe, and comfortable autonomous driving in complex intersections. Full article

In the face of increasingly severe cybersecurity threats, incomplete information and environmental dynamics have become central challenges in network attack–defense scenarios. In real-world network environments, defenders often find it difficult to fully perceive attack behaviors and network states, leading to a high degree of uncertainty in the system. Traditional approaches are inadequate in dealing with the diversification of attack strategies and the dynamic evolution of network structures, making it difficult to achieve highly adaptive defense strategies and efficient multi-agent coordination. To address these challenges, this paper proposes a multi-agent network defense approach based on joint game modeling, termed JG-Defense (Joint Game-based Defense), which aims to enhance the efficiency and robustness of defense decision-making in environments characterized by incomplete information. The method integrates Bayesian game theory, graph neural networks, and a proximal policy optimization framework, and it introduces two core mechanisms. First, a Dynamic Communication Graph Neural Network (DCGNN) is used to model the dynamic network structure, improving the perception of topological changes and attack evolution trends. A multi-agent communication mechanism is incorporated within the DCGNN to enable the sharing of local observations and strategy coordination, thereby enhancing global consistency. Second, a joint game loss function is constructed to embed the game equilibrium objective into the reinforcement learning process, optimizing both the rationality and long-term benefit of agent strategies. Experimental results demonstrate that JG-Defense outperforms the Cybermonic model by 15.83% in overall defense performance. Furthermore, under the traditional PPO loss function, the DCGNN model improves defense performance by 11.81% compared to the Cybermonic model. These results verify that the proposed integrated approach achieves superior global strategy coordination in dynamic attack–defense scenarios with incomplete information. Full article

To tackle the limitations in simultaneously modeling long-term dependencies in the time dimension and nonlinear interactions in the feature dimension, as well as their inability to fully reflect the impact of real-time load changes on spatial dependencies, a short-term multi-energy load forecasting method based on Transformer Spatio-Temporal Graph neural network (TSTG) is proposed. This method employs a multi-head spatio-temporal attention module to model long-term dependencies in the time dimension and nonlinear interactions in the feature dimension in parallel across multiple subspaces. Additionally, a dynamic adaptive graph convolution module is designed to construct adaptive adjacency matrices by combining physical topology and feature similarity, dynamically adjusting node connection weights based on real-time load characteristics to more accurately characterize the spatial dynamics of multi-energy interactions. Furthermore, TSTG adopts an end-to-end spatio-temporal joint optimization framework, achieving synchronous extraction and fusion of spatio-temporal features through an encoder–decoder architecture. Experimental results show that TSTG significantly outperforms existing methods in short-term load forecasting tasks, providing an effective solution for refined forecasting in integrated energy systems. Full article

Electricity demand forecasting is essential for smart grid management, yet it presents challenges due to the dynamic nature of consumption trends and regional variability in usage patterns. While federated learning (FL) offers a privacy-preserving solution for handling sensitive, region-specific data, traditional FL approaches struggle when local datasets are limited, often leading models to overfit noisy peak fluctuations. Additionally, many regions exhibit stable, periodic consumption behaviors, further complicating the need for a global model that can effectively capture diverse patterns without overfitting. To address these issues, we propose Federated Hybrid Graph Attention Network with Two-step Optimization for Electricity Consumption Forecasting (FedHMGAT), a hybrid modeling framework designed to balance periodic trends and numerical variations. Specifically, FedHMGAT leverages a numerical structure graph with a Gaussian encoder to model peak fluctuations as dynamic covariance features, mitigating noise-driven overfitting, while a multi-scale attention mechanism captures periodic consumption patterns through hybrid feature representation. These feature components are then fused to produce robust predictions. To enhance global model aggregation, FedHMGAT employs a two-step parameter aggregation strategy: first, a regularization term ensures parameter similarity across local models during training, and second, adaptive dynamic fusion at the server tailors aggregation weights to regional data characteristics, preventing feature dilution. Experimental results verify that FedHMGAT outperforms conventional FL methods, offering a scalable and privacy-aware solution for electricity demand forecasting. Full article

Humans have the ability to incrementally learn, accumulate, update, and apply knowledge from dynamic environments. This capability, known as continual learning or lifelong learning, is also a long-term goal in the development of artificial intelligence. However, neural network-based continual learning suffers from catastrophic forgetting: the acquisition of new knowledge typically disrupts previously learned knowledge, leading to partial forgetting and a decline in the model’s overall performance. Most current continual learning methods can only mitigate catastrophic forgetting and fail to incrementally improve the overall performance. In this work, we aim to incrementally improve performance within sample incremental context by utilizing inter-stage edges as a pathway for explicit knowledge transfer in continual graph learning. Building on this pathway, we propose a knowledge-augmented replay method by leveraging evolving subgraphs of important nodes. This method enhances the distinction between patterns associated with different node classes and consolidates previously learned knowledge. Experiments on phishing detection in Ethereum transaction networks validate the effectiveness of the proposed method, demonstrating effective knowledge retention and augmentation while overcoming catastrophic forgetting and incrementally improving performance. The results also reveal the relationship between average accuracy and average forgetting. Lastly, we identify the key factor to incremental performance improvement, which lays a foundation for convergence of continual graph learning. Full article

This research evaluates the suitability of Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) for improving financial return predictions across 15 major worldwide stock indices. The proposed method uses graph modeling to represent financial index relationships which enables the detection of symmetric market dependencies including mutual spillover effects and bidirectional influence patterns. The symmetric network structures become most important during financial instability because market interdependencies strengthen at such times. The evaluation process compares these models against XGBoost and Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM) traditional forecasting approaches. The results of 30 time-series cross-validation experiments show that GNN models produce lower RMSE and MAE values, especially during financial crises and recovery phases and volatile market periods. The models show reduced advantages when markets remain stable. The research demonstrates that graph-based forecasting models which incorporate symmetry effectively detect complex financial relationships which leads to important implications for investment strategies and financial risk management and global economic forecasting. Full article

In recommender systems research, the data sparsity problem has driven the development of hybrid recommendation algorithms integrating multimodal information and the application of graph neural networks (GNNs). However, conventional GNNs relying on homogeneous Euclidean embeddings fail to effectively model the non-Euclidean geometric manifold structures prevalent in real-world scenarios, consequently constraining the representation capacity for heterogeneous interaction patterns and compromising recommendation accuracy. As a consequence, the representation capability for heterogeneous interaction patterns is restricted, thereby affecting the overall representational power and recommendation accuracy of the models. In this paper, we propose a hyperbolic graph neural network model with contrastive learning for rating–review recommendation, implementing a dual-graph construction strategy. First, it constructs a review-aware graph to integrate rich semantic information from reviews, thus enhancing the recommendation system’s context awareness. Second, it builds a user–item interaction graph to capture user preferences and item characteristics. The hyperbolic graph neural network architecture enables joint learning of high-order features from these two graphs, effectively avoiding the embedding distortion problem commonly associated with high-order feature learning. Furthermore, through contrastive learning in hyperbolic space, the model effectively leverages review information and user–item interaction data to enhance recommendation system performance. Experimental results demonstrate that the proposed algorithm achieves excellent performance on multiple real-world datasets, significantly improving recommendation accuracy. Full article

Under the advancing urban–rural integration strategy, last-mile logistics, and their spatial accessibility, have become key indicators for measuring regional coordination. Focusing on Guangzhou as the case study area, this study constructs an urban–rural spatial accessibility assessment model integrating multimodal convolutional neural networks and Graph Neural Networks (GNN) to systematically examine the evolving accessibility patterns in last-mile logistics distribution across urban and rural spaces. The study finds that Guangzhou’s urban space continues to expand while rural space gradually decreases during this period, showing an overall development trend from centralized single-core to multi-polar networked patterns. The spatial accessibility of last-mile logistics in Guangzhou exhibits higher levels in urban core areas and lower levels in peripheral rural areas, but the overall accessibility is progressively expanding and improving in outlying regions. These accessibility changes not only reflect the optimization path of logistics infrastructure but also reveal the practical progress of urban–rural integration development. Through spatial distribution analysis and dynamic simulation of logistics networks, this study establishes a novel explanatory framework for understanding the spatial mechanisms of urban–rural integration. The findings provide decision-making support for optimizing last-mile logistics network layouts while offering both theoretical foundations and practical approaches for promoting co-construction and sharing of urban–rural infrastructure and achieving integrated regional spatial governance. Full article

The innovation capability of seed enterprises reflects their core competitiveness and serves as a vital foundation for sustainable agricultural development and modernization. Therefore, evaluating this capability is of great importance. However, existing evaluation methods primarily focus on internal enterprise attributes, overlooking the complex inter-enterprise relationships and lacking sufficient feature fusion capabilities to capture latent information. To address these limitations, this paper proposes a Multi-Channel Graph Convolutional Network (MGCN) model that integrates enterprise attributes with three types of relational graphs. The model adopts a multi-channel architecture for feature extraction and employs a gated attention mechanism for cross-graph feature fusion, jointly considering node features and relation information to improve prediction accuracy. Experimental results demonstrate that MGCN achieves an average accuracy of 83.59% under five-fold cross-validation, outperforming several mainstream models such as Random Forest and traditional GCN. Case studies further reveal that MGCN not only captures key features of individual enterprises but also leverages features and label distribution from neighboring enterprises, facilitating more context-aware classification decisions. In conclusion, the MGCN model provides an effective method for the intelligent evaluation of innovation capability in seed enterprises and supports the formulation of sustainable strategic plans at both the national and enterprise level. Full article

Optimization of stock selection strategies has been a topic of interest in finance. Although deep learning models have demonstrated superior performance over traditional methods, there are still shortcomings. For example, previous studies do not provide enough explanation for feature selection and usually use features such as closing price directly to make predictions; for example, most studies predict the trend of multiple stock indices or only individual stocks, which is difficult to be directly applied to actual stock selection. In this paper, a multivariate hybrid neural network model CNN-LSTM-GNN (CLGNN) for stock prediction is proposed, in which the CNN and the LSTM modules analyze the local and the whole, respectively, while the multivariate time series GNN module is added to explore the potential relationships between the data through the graph learning, graph convolutional, and temporal convolutional layers. CLGNN analyzes the potential relationships between the data based on the returns to classify stocks, and then develops a stock selection strategy, and directly outputs the returns and stock codes. In this paper, a hybrid filter approach based on entropy and Pearson correlation is proposed for feature selection, and experiments are conducted on all stocks in the CSI All Share Index (CSI); the results show that among multiple models, the returns obtained when the features of daily return, turnover rate, relative strength index, volume, and forward adjusted closing price are used as inputs are all the highest, and the return obtained by CLGNN is even higher than that of the other models (e.g., TCN, Transformer, etc.). Full article

Distributed acoustic sensing (DAS), which can provide dense spatial and temporal measurements using optical fibers, is quickly becoming critical for large-scale infrastructure monitoring. However, anomaly detection in DAS data is still challenging owing to the spatial correlations between sensing channels and nonlinear temporal dynamics. Recent approaches often disregard the explicit sensor layout and instead handle DAS data as two-dimensional images or flattened sequences, eliminating the spatial topology. This work proposes GraphDiffusion, a novel generative anomaly-detection model that combines a conditional denoising diffusion probabilistic model (DDPM) and a graph neural network (GNN) to overcome these limitations. By treating each channel as a graph node and building edges based on Euclidean proximity, the GNN explicitly models the spatial arrangement of DAS sensors, allowing the network to capture local interchannel dependencies. The conditional DDPM uses iterative denoising to model the temporal dynamics of standard signals, enabling the system to detect deviations without the need for anomalies. The performance evaluations based on real-world DAS datasets reveal that GraphDiffusion achieves 98.2% and 98.0% based on the area under the curve (AUC) of the F1-score at K different levels (F1_K-AUC), an AUC of receiver operating characteristic (ROC) at K different levels (ROC_K-AUC), outperforming other comparative models. Full article

Background: Brain–computer interfaces (BCIs) based on motor imagery (MI) offer promising solutions for motor rehabilitation and communication. However, electroencephalography (EEG) signals are often characterized by low signal-to-noise ratios, strong non-stationarity, and significant inter-subject variability, which pose significant challenges for accurate decoding. Existing methods often struggle to simultaneously model the spatial interactions between EEG channels, the local fine-grained features within signals, and global semantic patterns. Methods: To address this, we propose the graph attention-based hierarchical temporal network (GAH-TNet), which integrates spatial graph attention modeling with hierarchical temporal feature encoding. Specifically, we design the graph attention temporal encoding block (GATE). The graph attention mechanism is used to model spatial dependencies between EEG channels and encode short-term temporal dynamic features. Subsequently, a hierarchical attention-guided deep temporal feature encoding block (HADTE) is introduced, which extracts local fine-grained and global long-term dependency features through two-stage attention and temporal convolution. Finally, a fully connected classifier is used to obtain the classification results. The proposed model is evaluated on two publicly available MI-EEG datasets. Results: Our method outperforms multiple existing state-of-the-art methods in classification accuracy. On the BCI IV 2a dataset, the average classification accuracy reaches 86.84%, and on BCI IV 2b, it reaches 89.15%. Ablation experiments validate the complementary roles of GATE and HADTE in modeling. Additionally, the model exhibits good generalization ability across subjects. Conclusions: This framework effectively captures the spatio-temporal dynamic characteristics and topological structure of MI-EEG signals. This hierarchical and interpretable framework provides a new approach for improving decoding performance in EEG motor imagery tasks. Full article

The topology of distribution networks changes frequently, and the uncertainty of load level and distributed generator (DG) output makes the operation scenarios more complex and variable. Based on this, a fault recovery method for active distribution networks based on graph-based deep reinforcement learning is proposed. Firstly, considering the time-varying characteristics of DG output and load, a fault recovery framework for distribution networks based on a graph attention network (GAT) and soft actor–critic (SAC) algorithm is constructed, and the fault recovery method and its algorithm principle are introduced. Then, a graph-based deep reinforcement learning model for distribution network fault recovery is established. By embedding GAT into the pre-neural network of the SAC algorithm, the agent’s perception ability of the distribution network operation status and topology is improved, and an invalid action masking mechanism is innovatively introduced to avoid illegal actions. Through the interaction between the agent and the environment, the optimal switch action control strategy is found to realize the optimal learning of recovery under high DG penetration. Finally, the proposed method is verified on IEEE 33-bus and 148-bus examples and, compared with multiple baseline methods, the proposed method can achieve the fastest fault recovery at the millisecond level, and has a more efficient and superior recovery effect; the load supply rate under topology change increased by 4% to 5% compared with the benchmark model. Full article

In recent years, graph neural networks (GNNs) have shown powerful performance in processing non-Euclidean data. However, similar to other machine-learning algorithms, GNNs can amplify data bias in high-risk decision-making systems, which can easily lead to unfairness in the final decision-making results. At present, a large number of studies focus on solving the fairness problem of GNNs, but the existing methods mostly rely on building complex model architectures or rely on technical means in the field of non-GNNs. To this end, this paper proposes FairCNCB (Fair Graph Neural Network based on Counterfactual and Category Balance) to address the problem of class imbalancing in minority sensitive attribute groups. First, we conduct a causal analysis of fair representation and employ the adversarial network to generate counterfactual node samples, effectively mitigating bias induced by sensitive attributes. Secondly, we calculate the weights for minority sensitive attribute groups, and reconstruct the loss function to achieve the fairness of sensitive attribute classes among different groups. The synergy between the two modules optimizes GNNs from multiple dimensions and significantly improves the performance of GNNs in terms of fairness. The experimental results on the three datasets show the effectiveness and fairness of FairCNCB. The performance metrics (such as AUC, F1, and ACC) have been improved by approximately 2%, and the fairness metrics (△sp, △eo) have been enhanced by approximately 5%. Full article