Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
25,187
result(s) for
"Graph neural networks"
Sort by:
Concepts and techniques of graph neural network
\"This book will aim to provide stepwise discussion; exhaustive literature review; detailed analysis and discussion; rigorous experimentation results, application-oriented approach that will be demonstrated with respect to applications of Graph Neural Network (GNN). It will be written to develop the understanding of concepts and techniques on GNN and to establish the familiarity of different real applications in various domains for GNN. Moreover, it will also cover the prevailing challenges and opportunities\"-- Provided by publisher.
Book
Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues
Traffic forecasting plays an important role of modern Intelligent Transportation Systems (ITS). With the recent rapid advancement in deep learning, graph neural networks (GNNs) have become an emerging research issue for improving the traffic forecasting problem. Specifically, one of the main types of GNNs is the spatial-temporal GNN (ST-GNN), which has been applied to various time-series forecasting applications. This study aims to provide an overview of recent ST-GNN models for traffic forecasting. Particularly, we propose a new taxonomy of ST-GNN by dividing existing models into four approaches such as graph convolutional recurrent neural network, fully graph convolutional network, graph multi-attention network, and self-learning graph structure. Sequentially, we present experimental results based on the reconstruction of representative models using selected benchmark datasets to evaluate the main contributions of the key components in each type of ST-GNN. Finally, we discuss several open research issues for further investigations.
Journal Article
TSG‐Net: A Multiscale Decomposition and Spatio‐Temporal Graph Neural Network Framework for High‐Precision Wind Power Forecasting
Wind energy's intermittency poses significant challenges for power grid stability. Existing forecasting methods exhibit notable limitations: traditional machine learning models struggle with long‐term temporal dependencies, while deep learning approaches often overlook spatial relationships among turbines. This paper proposes TSG‐Net, a novel framework integrating multiscale decomposition, graph neural networks, and attention mechanisms. TSG‐Net employs three innovative components: a multiscale decomposition linear network (MDLinear) with learnable decomposition weights for adaptive temporal feature extraction, a spatio‐temporal graph network (XTGN) that constructs dynamic adjacency matrices based on real‐time wind directions for wake effect modeling, and an adaptive attention fusion mechanism for scenario‐specific weight allocation. Experiments on the SDWPF dataset demonstrate that TSG‐Net achieves MAE of 36.53 kW and RMSE of 45.17 kW, representing improvements of 8.3% and 5.7%, respectively, compared with the best baseline TSB‐GNN (39.85‐kW MAE, 47.92‐kW RMSE), with particularly strong performance during wind direction changes, extreme weather, and power ramp events.
Journal Article
HGNN−BRFE: Heterogeneous Graph Neural Network Model Based on Region Feature Extraction
With the strong capability of heterogeneous graphs in accurately modeling various types of nodes and their interactions, they have gradually become a research hotspot, promoting the rapid development of the field of heterogeneous graph neural networks (HGNNs). However, most existing HGNN models rely on meta−paths for feature extraction, which can only utilize part of the data from the graph for training and learning. This not only limits the data generalization ability of deep learning models but also affects the application effect of data−driven adaptive technologies. In response to this challenge, this study proposes a new model—heterogeneous graph neural network based on regional feature extraction (HGNN−BRFE). This model enhances performance through an “extraction−fusion” strategy in three key aspects: first, it efficiently extracts features of neighboring nodes of the same type according to specific regions; second, it effectively fuses information from different regions and hierarchical neighbors using attention mechanisms; third, it specially designs a process for feature extraction and fusion targeting heterogeneous type nodes, ensuring that the rich semantic and heterogeneity information within the heterogeneous graph is retained while maintaining the node’s own characteristics during the node embedding process to prevent the loss of its own features and potential over−smoothing issues. Experimental results show that HGNN−BRFE achieves a performance improvement of 1–3% over existing methods on classification tasks across multiple real−world datasets.
Journal Article
Physics-informed graph neural network for predicting fluid flow in porous media
With the rapid development of deep learning neural networks, new solutions have emerged for addressing fluid flow problems in porous media. Combining data-driven approaches with physical constraints has become a hot research direction, with physics-informed neural networks (PINNs) being the most popular hybrid model. PINNs have gained widespread attention in subsurface fluid flow simulations due to their low computational resource requirements, fast training speeds, strong generalization capabilities, and broad applicability. Despite success in homogeneous settings, standard PINNs face challenges in accurately calculating flux between irregular Eulerian cells with disparate properties and capturing global field influences on local cells. This limits their suitability for heterogeneous reservoirs and the irregular Eulerian grids frequently used in reservoir. To address these challenges, this study proposes a physics-informed graph neural network (PIGNN) model. The PIGNN model treats the entire field as a whole, integrating information from neighboring grids and physical laws into the solution for the target grid, thereby improving the accuracy of solving partial differential equations in heterogeneous and Eulerian irregular grids. The optimized model was applied to pressure field prediction in a spatially heterogeneous reservoir, achieving an average L2 error and R2 score of 6.710 × 10−4 and 0.998, respectively, which confirms the effectiveness of model. Compared to the conventional PINN model, the average L2 error was reduced by 76.93%, the average R2 score increased by 3.56%. Moreover, evaluating robustness, training the PIGNN model using only 54% and 76% of the original data yielded average relative L2 error reductions of 58.63% and 56.22%, respectively, compared to the PINN model. These results confirm the superior performance of this approach compared to PINN.
Journal Article
Darknet Traffic and Application Classification Using Heterogeneous Graph Neural Network
The proliferation of Virtual Private Networks (VPNs) and The Onion Router (TOR) has both benefits and drawbacks for individuals and organisations. These technologies offer enhanced privacy and security online, but can also facilitate illegal or harmful behaviour by masking users’ identities. Therefore, it is crucial to develop reliable methods for identifying and monitoring VPN and TOR traffic to mitigate potential risks and ensure online safety. In this paper, we propose a Darknet Heterogeneous Graph Neural Network (DHGNN) model to address the challenge of detecting traffic and applications in the Darknet. Our approach utilizes the CIC-Darknet2020 dataset, a large collection of openly available network traffic data, to train and evaluate our DHGNN classifier. The dataset is systematically explored to identify the most informative features and preprocessed into a clean tabular format. This tabular data is then converted into a graph structure suitable for the DHGNN classifier. Experimental results show that the proposed model achieves 99.80% accuracy in traffic classification and 98.80% accuracy in application classification, outperforming existing methods in Darknet classification. This approach demonstrates the effectiveness of integrating feature-driven preprocessing with graph-based neural network modeling for robust and accurate classification.
Journal Article
A Data-centric graph neural network for node classification of heterophilic networks
In the real world, numerous heterophilic networks effectively model the tendency of similar entities to repel each other and dissimilar entities to be attracted to each other within complex systems. Concerning the node classification problem in heterophilic networks, a plethora of heterophilic Graph Neural Networks (GNNs) have emerged. However, these GNNs demand extensive hyperparameter tuning, activation function selection, parameter initialization, and other configuration settings, particularly when dealing with diverse heterophilic networks and resource constraints. This situation raises a fundamental question: Can a method be designed to directly preprocess heterophilic networks and then leverage the trained models in network representation learning systems? In this paper, we propose a novel approach to transform heterophilic network structures. Specifically, we train an edge classifier and subsequently employ this edge classifier to transform a heterophilic network into its corresponding homophilic counterpart. Finally, we conduct experiments on heterophilic network datasets with variable sizes, demonstrating the effectiveness of our approach. The code and datasets are publicly available at
https://github.com/xueyanfeng/D_c_GNNs
.
Journal Article
Online social network user performance prediction by graph neural networks
Online social networks provide rich information that characterizes the user’s personality, his interests, hobbies, and reflects his current state. Users of social networks publish photos, posts, videos, audio, etc. every day. Online social networks (OSN) open up a wide range of research opportunities for scientists. Much research conducted in recent years using graph neural networks (GNN) has shown their advantages over conventional deep learning. In particular, the use of graph neural networks for online social network analysis seems to be the most suitable. In this article we studied the use of graph convolutional neural networks with different convolution layers (GCNConv, SAGEConv, GraphConv, GATConv, TransformerConv, GINConv) for predicting the user’s professional success in VKontakte online social network, based on data obtained from his profiles. We have used various parameters obtained from users’ personal pages in VKontakte social network (the number of friends, subscribers, interesting pages, etc.) as their features for determining the professional success, as well as networks (graphs) reflecting connections between users (followers/ friends). In this work we performed graph classification by using graph convolutional neural networks (with different types of convolution layers). The best accuracy of the graph convolutional neural network (0.88) was achieved by using the graph isomorphism network (GIN) layer. The results, obtained in this work, will serve for further studies of social success, based on metrics of personal profiles of OSN users and social graphs using neural network methods.
Journal Article
A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions
Deep learning has seen significant growth recently and is now applied to a wide range of conventional use cases, including graphs. Graph data provides relational information between elements and is a standard data format for various machine learning and deep learning tasks. Models that can learn from such inputs are essential for working with graph data effectively. This paper identifies nodes and edges within specific applications, such as text, entities, and relations, to create graph structures. Different applications may require various graph neural network (GNN) models. GNNs facilitate the exchange of information between nodes in a graph, enabling them to understand dependencies within the nodes and edges. The paper delves into specific GNN models like graph convolution networks (GCNs), GraphSAGE, and graph attention networks (GATs), which are widely used in various applications today. It also discusses the message-passing mechanism employed by GNN models and examines the strengths and limitations of these models in different domains. Furthermore, the paper explores the diverse applications of GNNs, the datasets commonly used with them, and the Python libraries that support GNN models. It offers an extensive overview of the landscape of GNN research and its practical implementations.
Journal Article
Multichannel Adaptive Data Mixture Augmentation for Graph Neural Networks
Graph neural networks (GNNs) have demonstrated significant potential in analyzing complex graph-structured data. However, conventional GNNs encounter challenges in effectively incorporating global and local features. Therefore, this paper introduces a novel approach for GNN called multichannel adaptive data mixture augmentation (MAME-GNN). It enhances a GNN by adopting a multi-channel architecture and interactive learning to effectively capture and coordinate the interrelationships between local and global graph structures. Additionally, this paper introduces the polynomial–Gaussian mixture graph interpolation method to address the problem of single and sparse graph data, which generates diverse and nonlinear transformed samples, improving the model's generalization ability. The proposed MAME-GNN is validated through extensive experiments on publicly available datasets, showcasing its effectiveness. Compared to existing GNN models, the MAME-GNN exhibits superior performance, significantly enhancing the model's robustness and generalization ability.
Journal Article