Global Graph Research Articles

Global Dependency Graph Network for Soft Sensing in Process Industry

Global Dependency Graph Network for Soft Sensing in Process Industry

Global information aware network with global interaction graph attention for infrared small target detection

AbstractDetecting small targets in infrared images is crucial for ground surveillance and air traffic control. However, distinguishing small infrared targets from similar backgrounds is challenging due to their lack of structural and textural characteristics. To address these challenges, this study proposes a novel global information‐aware network with global interaction graph attention (GIGA) for infrared small target detection. The GIGA consists of a global interaction layer (GILayer), graph attention weights (GAW), and a global relational learning (GRL) module. Specifically, the GILayer dynamically learns global inter‐pixel relationships of small target images by enhancing the dependencies between feature dimensions. The GAW component calculates pixel‐by‐pixel similarity across the entire feature map using graph attention mechanisms, while the GRL module retains critical similarity features in the feature extraction network, thereby facilitating small target detection. Additionally, the multi‐scale context fusion module utilises self‐attention and dilation convolution to complement richer feature details at different scales. Experimental results on both natural and synthetic datasets demonstrate the proposed method's superiority over other state‐of‐the‐art conventional and deep learning approaches in infrared small target detection.

Functional network characteristics in anxiety- and mania-based subgroups of bipolar I disorder

BackgroundBipolar disorder I (BD-I) is a heterogeneous disorder with a high prevalence of comorbid anxiety. The aim of this study was to investigate whether anxiety and mania symptoms define distinct subgroups within BD-I and to explore potential differences in functional network characteristics between these subgroups. MethodsSubgroups were identified using scores from clinical anxiety and mania scales. After dimension reduction of these scores, data-driven clustering analysis with cross-validation was employed to reveal the existence of subgroups. Resting-state functional magnetic resonance imaging (rs-fMRI) scans were pre-processed using fMRIPrep. After parcellation and network construction, global and regional graph theoretical measures were calculated per subgroup. ResultsClustering results revealed that, based on anxiety symptomatology, subjects fell into two distinct subgroups, whereas mania symptoms divided subjects into four unique subgroups. These subgroups varied notably on several symptom scales. Network assortativity was significantly associated with anxiety subgroups. Post-hoc pairwise comparisons did not reveal significant global functional network differences between the anxiety subgroups or between mania subgroups. Regional network differences between clinical subgroups were especially apparent for strength and degree in the temporal and frontal lobes. LimitationsSmall sample size of some subgroups is a limitation of this study as is the categorical rather than continuous representation of anxiety and mania symptoms. ConclusionsBD-I populations may be stratified into robust subgroups based on anxiety and mania symptoms, showing differences in functional network connectivity. Our findings highlight new avenues of research for investigating heterogeneity in psychiatric populations.

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.

HGOD: Outlier detection based on a hybrid graph

Outlier detection is one of the core problems in the field of data mining. Graph-based approaches are widely acknowledged for their robust performance in outlier detection, yet constructing a comprehensive graph to represent the original data remains challenging. Some methods rely solely on the global distribution of the data, leading to low detection accuracy; in addition, when incorporating the local information of the data, the problem of dangling links may arise. To improve the graph construction process, this paper proposes an outlier detection algorithm based on a hybrid graph (HGOD). First, the neighbors of each object are obtained in an adaptive manner, and a neighborhood graph is created. Subsequently, a global connectivity graph is constructed using a minimum spanning tree. Then, these two graphs are merged into a hybrid graph, and Markov random walks are conducted on it. Finally, outliers are identified based on the converged stationary distribution. The performance of HGOD is evaluated on both real-world and synthetic datasets. The precision and AUC of HGOD algorithm surpasses that of the other seven algorithms. Ablation and analysis experiments further demonstrate that the HGOD algorithm is effective and has outstanding performance in outlier detection.

Self-adaptive selection graph pooling based fault diagnosis method under few samples and noisy environment

Neural network (NN)-based methods are extensively used for intelligent fault diagnosis in industrial systems. Nevertheless, due to the limited availability of faulty samples and the presence of noise interference, most existing NN-based methods perform limited diagnosis performance. In response to these challenges, a self-adaptive selection graph pooling method is proposed. Firstly, graph encoders with sharing parameters are designed to extract local structure-feature information (SFI) of multiple sensor-wise sub-graphs. Then, the temporal continuity of the SFI is maintained through time-by-time concatenation, resulting in a global sensor graph and reducing the dependency on data volume from the perspective of adding prior knowledge. Subsequently, leveraging a self-adaptive node selection mechanism, the noise interference of redundant and noisy sensor-wise nodes in the graph is alleviated, allowing the networks to concentrate on the fault-attention nodes. Finally, the local max pooling and global mean pooling of the node-selection graph are incorporated in the readout module to get the multi-scale graph features, which serve as input to a multi-layer perceptron for fault diagnosis. Two experimental studies involving different mechanical and electrical systems demonstrate that the proposed method not only achieves superior diagnosis performance with limited data, but also maintains strong anti-interference ability in noisy environments. Additionally, it exhibits good interpretability through the proposed self-adaptive node selection mechanism and visualization methods.

Global-local graph attention: unifying global and local attention for node classification

Abstract Graph Neural Networks (GNNs) are deep learning models specifically designed for analyzing graph-structured data, capturing complex relationships and structures to improve analysis and prediction. A common task in GNNs is node classification, where each node in the graph is assigned a predefined category. The Graph Attention Network (GAT) is a popular variant of GNNs known for its ability to capture complex dependencies by assigning importance weights to nodes during information aggregation. However, the GAT’s reliance on local attention mechanisms limits its effectiveness in capturing global information and long-range dependencies. To address this limitation, we propose a new attention mechanism called Global-Local Graph Attention (GLGA). Our mechanism enables the GAT to capture long-range dependencies and global graph structures while maintaining its ability to focus on local interactions. We evaluate our algorithm on three citation datasets (Cora, Citeseer, and Pubmed) using multiple metrics, demonstrating its superiority over other baseline models. The proposed GLGA mechanism has been proven to be an effective solution for improving node classification tasks.

Hippocampal hub failure is linked to long-term memory impairment in anti-NMDA-receptor encephalitis: insights from structural connectome graph theoretical network analysis

BackgroundAnti-N-methyl-d-aspartate receptor (NMDAR) encephalitis is characterized by distinct structural and functional brain alterations, predominantly affecting the medial temporal lobes and the hippocampus. Structural connectome analysis with graph-based investigations of network properties allows for an in-depth characterization of global and local network changes and their relationship with clinical deficits in NMDAR encephalitis.MethodsStructural networks from 61 NMDAR encephalitis patients in the post-acute stage (median time from acute hospital discharge: 18 months) and 61 age- and sex-matched healthy controls (HC) were analyzed using diffusion-weighted imaging (DWI)-based probabilistic anatomically constrained tractography and volumetry of a selection of subcortical and white matter brain volumes was performed. We calculated global, modular, and nodal graph measures with special focus on default-mode network, medial temporal lobe, and hippocampus. Pathologically altered metrics were investigated regarding their potential association with clinical course, disease severity, and cognitive outcome.ResultsPatients with NMDAR encephalitis showed regular global graph metrics, but bilateral reductions of hippocampal node strength (left: p = 0.049; right: p = 0.013) and increased node strength of right precuneus (p = 0.013) compared to HC. Betweenness centrality was decreased for left-sided entorhinal cortex (p = 0.042) and left caudal middle frontal gyrus (p = 0.037). Correlation analyses showed a significant association between reduced left hippocampal node strength and verbal long-term memory impairment (p = 0.021). We found decreased left (p = 0.013) and right (p = 0.001) hippocampal volumes that were associated with hippocampal node strength (left p = 0.009; right p < 0.001).ConclusionsFocal network property changes of the medial temporal lobes indicate hippocampal hub failure that is associated with memory impairment in NMDAR encephalitis at the post-acute stage, while global structural network properties remain unaltered. Graph theory analysis provides new pathophysiological insight into structural network changes and their association with persistent cognitive deficits in NMDAR encephalitis.

LGGNet: Learning From Local-Global-Graph Representations for Brain-Computer Interface.

Neuropsychological studies suggest that co-operative activities among different brain functional areas drive high-level cognitive processes. To learn the brain activities within and among different functional areas of the brain, we propose local-global-graph network (LGGNet), a novel neurologically inspired graph neural network (GNN), to learn local-global-graph (LGG) representations of electroencephalography (EEG) for brain-computer interface (BCI). The input layer of LGGNet comprises a series of temporal convolutions with multiscale 1-D convolutional kernels and kernel-level attentive fusion. It captures temporal dynamics of EEG which then serves as input to the proposed local- and global-graph-filtering layers. Using a defined neurophysiologically meaningful set of local and global graphs, LGGNet models the complex relations within and among functional areas of the brain. Under the robust nested cross-validation settings, the proposed method is evaluated on three publicly available datasets for four types of cognitive classification tasks, namely the attention, fatigue, emotion, and preference classification tasks. LGGNet is compared with state-of-the-art (SOTA) methods, such as DeepConvNet, EEGNet, R2G-STNN, TSception, regularized graph neural network (RGNN), attention-based multiscale convolutional neural network-dynamical graph convolutional network (AMCNN-DGCN), hierarchical recurrent neural network (HRNN), and GraphNet. The results show that LGGNet outperforms these methods, and the improvements are statistically significant ( ) in most cases. The results show that bringing neuroscience prior knowledge into neural network design yields an improvement of classification performance. The source code can be found at https://github.com/yi-ding-cs/LGG.

Short-Term Power Forecasting of Wind Farm Cluster Based on Global Information Adaptive Perceptual Graph Convolution Network

Short-Term Power Forecasting of Wind Farm Cluster Based on Global Information Adaptive Perceptual Graph Convolution Network

Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition

Skeleton-based action recognition has attracted increasing interest in recent years. With the flexibility of modeling long-range dependency of joints, the self-attention module has served as the basic component in skeleton-based action recognition. However, the global receptive field of self-attention is not conducive to the modeling of skeleton locality, and the self-attention model is imbued with less inductive bias, which leads to overfitting. In this paper, we propose an attention graph convolutional network (AGCN) with multi-scale sampling to effectively model the local and global features of the skeleton. Firstly, we propose two extreme sampling strategies for generating and ordering neighboring nodes of root nodes. A local-first sampling method is introduced to construct local graph windows, and a global-first sampling method is proposed to assemble long-range joints for constructing global graph windows. The local-first sampling and global-first sampling introduce more skeleton-specific inductive biases to regularize the model capacity. Secondly, the AGCN combines the self-attention mechanism with graph convolution operation, which alleviates the over-smoothing of graph convolution and preserves the translation invariant. Based on the multi-scale sampling strategy, the AGCN can effectively model the locality and non-locality of the skeleton. Finally, by coupling the aforementioned proposals, we develop a two-pathway model for multi-scale feature fusion. Extensive experiments demonstrate that our model could achieve comparable performance with state-of-the-art works on the NTU RGB+D 60, NTU RGB+D 120, the UAV-HUMAN and NW-UCLA datasets.

Inter-structure and intra-semantics graph contrastive learning for disease prediction

Ever-evolving healthcare applications have witnessed a surge in the utilization of electronic health records (EHR) for predicting future patient diagnoses. While Graph Neural Networks have demonstrated that promise in modeling disease-patient relationships, challenges arise from the sparsity and imbalance of patient and diagnostic data. Moreover, the existing models face difficulties in learning the unique disease combination features of patients. To address these challenges, we proposed a novel disease. prediction architecture based on Contrastive Learning (CL) from interstructural and intrasemantic perspectives, rather than traditional CL methods. We generated an initial global static disease graph to directly represent the relationships. among all diseases and a local dynamic disease graph to capture the indirect latent disease relationships among different patients. Multiple CL tasks were designed to learn sparse and imbalanced potentials. Relationships Between Diseases. Interstructure graph CL was first proposed to sample a graph enhancement, based on the distribution of nodes in the global disease graph. To further explore the deep embedding space of the disease, an intra-view graph CL was introduced by injecting noise at the semantic level for robust graph comparison. Experimental validation on two real EHR datasets demonstrates the superior performance of the approach by comparing it with state-of-the-art models.

Predicting the Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Graph Frequency Bands and Functional Connectivity-Based Features.

Accurate prediction of the progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD) is crucial for disease management. Machine learning techniques have demonstrated success in classifying AD and MCI cases, particularly with the use of resting-state functional magnetic resonance imaging (rs-fMRI) data.This study utilized three years of rs-fMRI data from the ADNI, involving 142 patients with stable MCI (sMCI) and 136 with progressive MCI (pMCI). Graph signal processing was applied to filter rs-fMRI data into low, middle, and high frequency bands. Connectivity-based features were derived from both filtered and unfiltered data, resulting in a comprehensive set of 100 features, including global graph metrics, minimum spanning tree (MST) metrics, triadic interaction metrics, hub tendency metrics, and the number of links. Feature selection was enhanced using particle swarm optimization (PSO) and simulated annealing (SA). A support vector machine (SVM) with a radial basis function (RBF) kernel and a 10-fold cross-validation setup were employed for classification. The proposed approach demonstrated superior performance, achieving optimal accuracy with minimal feature utilization. When PSO selected five features, SVM exhibited accuracy, specificity, and sensitivity rates of 77%, 70%, and 83%, respectively. The identified features were as follows: (Mean of clustering coefficient, Mean of strength)/Radius/(Mean Eccentricity, and Modularity) from low/middle/high frequency bands of graph. The study highlights the efficacy of the proposed framework in identifying individuals at risk of AD development using a parsimonious feature set. This approach holds promise for advancing the precision of MCI to AD progression prediction, aiding in early diagnosis and intervention strategies.

LG-GNN: Local and Global Information-aware Graph Neural Network for default detection

Default detection, a crucial aspect of individual credit scoring, has attracted considerable attention in research. Previous approaches typically focus on classifying applicants using only explicit attributes, overlooking the importance of latent relations among them. Concurrently, graph-based techniques have emerged as promising tools for credit scoring. However, existing graph-based methods often need to be more accurate in aggregating information from limited neighbors, which can lead to misclassification when the target node has differently labeled neighbors. Motivated by these challenges, we propose a Local and Global Information-aware Graph Neural Network (LG-GNN) approach for default detection. By leveraging the loan applicant relation graph, LG-GNN dynamically learns the representation of the target node from both local and global perspectives. Furthermore, it adaptively fuses the information from these perspectives and employs contrastive learning to enhance feature variations. Extensive experiments demonstrate the superiority of LG-GNN over mainstream methods across several widely used default detection datasets. Specifically, LG-GNN achieves an average relative performance improvement of 47.9% compared to baselines. Moreover, compared to the most competitive default detection methods, LG-GNN exhibits an average performance improvement of 11.9%. Our code is publicly available at https://github.com/BERA-wx/LG-GNN.

Autonomous Exploration Method of Unmanned Ground Vehicles Based on an Incremental B-Spline Probability Roadmap.

Autonomous exploration in unknown environments is a fundamental problem for the practical application of unmanned ground vehicles (UGVs). However, existing exploration methods face difficulties when directly applied to UGVs due to limited sensory coverage, conservative exploration strategies, inappropriate decision frequencies, and the non-holonomic constraints of wheeled vehicles. In this paper, we present IB-PRM, a hierarchical planning method that combines Incremental B-splines with a probabilistic roadmap, which can support rapid exploration by a UGV in complex unknown environments. We define a new frontier structure that includes both information-gain guidance and a B-spline curve segment with different arrival orientations to satisfy the non-holonomic constraint characteristics of UGVs. We construct and maintain local and global graphs to generate and store filtered frontiers. By jointly solving the Traveling Salesman Problem (TSP) using these frontiers, we obtain the optimal global path traversing feasible frontiers. Finally, we optimize the global path based on the Time Elastic Band (TEB) algorithm to obtain a smooth, continuous, and feasible local trajectory. We conducted comparative experiments with existing advanced exploration methods in simulation environments of different scenarios, and the experimental results demonstrate that our method can effectively improve the efficiency of UGV exploration.

Graph Contrastive Multi-view Learning: A Pre-training Framework for Graph Classification

Recent advancements in node and graph classification tasks can be attributed to the implementation of contrastive learning and similarity search. Despite considerable progress, these approaches present challenges. The integration of similarity search introduces an additional layer of complexity to the model. At the same time, applying contrastive learning to non-transferable domains or out-of-domain datasets results in less competitive outcomes. In this work, we propose maintaining domain specificity for these tasks, which has demonstrated the potential to improve performance by eliminating the need for additional similarity searches. We adopt a fraction of domain-specific datasets for pre-training purposes, generating augmented pairs that retain structural similarity to the original graph, thereby broadening the number of views. This strategy involves a comprehensive exploration of optimal augmentations to devise multi-view embeddings. An evaluation protocol, which focuses on error minimization, accuracy enhancement, and overfitting prevention, guides this process to learn inherent, transferable structural representations that span diverse datasets. We combine pre-trained embeddings and the source graph as a beneficial input, leveraging local and global graph information to enrich downstream tasks. Furthermore, to maximize the utility of negative samples in contrastive learning, we extend the training mechanism during the pre-training stage. Our method consistently outperforms comparative baseline approaches in comprehensive experiments conducted on benchmark graph datasets of varying sizes and characteristics, establishing new state-of-the-art results.

Label generation with consistency on the graph for multi-label feature selection

Multi-label feature selection involves the selection of informative features in high-dimensional data sets based on the relationships among different variables. However, large-scale data sets often contain unknown labels that hold latent information, posing a challenge for discovery. Explicitly uncovering latent information among labels not only helps establish robust mappings between features and labels but also expands the applicable knowledge. This paper introduces a novel feature selection method called Label Generation with Consistency on the Graph for Multi-label Feature Selection (LGCM) to effectively integrate label generation and feature selection processes. The proposed method incorporates a two-way flipping mechanism that leverages the consistency on the global graph to guide label generation for each instance. Additionally, the feature selection model utilizes a shared low-rank feature space to minimize deviation from the label generation, providing feedback to the label generation process. Extensive experiments validate the effectiveness of LGCM in improving state-of-the-art feature selection methods in multi-label learning.

Exploring potential circRNA biomarkers for cancers based on double-line heterogeneous graph representation learning

BackgroundCompared with the time-consuming and labor-intensive for biological validation in vitro or in vivo, the computational models can provide high-quality and purposeful candidates in an instant. Existing computational models face limitations in effectively utilizing sparse local structural information for accurate predictions in circRNA-disease associations. This study addresses this challenge with a proposed method, CDA-DGRL (Prediction of CircRNA-Disease Association based on Double-line Graph Representation Learning), which employs a deep learning framework leveraging graph networks and a dual-line representation model integrating graph node features.MethodCDA-DGRL comprises several key steps: initially, the integration of diverse biological information to compute integrated similarities among circRNAs and diseases, leading to the construction of a heterogeneous network specific to circRNA-disease associations. Subsequently, circRNA and disease node features are derived using sparse autoencoders. Thirdly, a graph convolutional neural network is employed to capture the local graph network structure by inputting the circRNA-disease heterogeneous network alongside node features. Fourthly, the utilization of node2vec facilitates depth-first sampling of the circRNA-disease heterogeneous network to grasp the global graph network structure, addressing issues associated with sparse raw data. Finally, the fusion of local and global graph network structures is inputted into an extra trees classifier to identify potential circRNA-disease associations.ResultsThe results, obtained through a rigorous five-fold cross-validation on the circR2Disease dataset, demonstrate the superiority of CDA-DGRL with an AUC value of 0.9866 and an AUPR value of 0.9897 compared to existing state-of-the-art models. Notably, the hyper-random tree classifier employed in this model outperforms other machine learning classifiers.ConclusionThus, CDA-DGRL stands as a promising methodology for reliably identifying circRNA-disease associations, offering potential avenues to alleviate the necessity for extensive traditional biological experiments. The source code and data for this study are available at https://github.com/zywait/CDA-DGRL.

Global and Local Interattribute Relationships-Based Graph Convolutional Network for Flight Trajectory Prediction

Global and Local Interattribute Relationships-Based Graph Convolutional Network for Flight Trajectory Prediction

SAMSGL: Series-aligned multi-scale graph learning for spatiotemporal forecasting.

Spatiotemporal forecasting in various domains, like traffic prediction and weather forecasting, is a challenging endeavor, primarily due to the difficulties in modeling propagation dynamics and capturing high-dimensional interactions among nodes. Despite the significant strides made by graph-based networks in spatiotemporal forecasting, there remain two pivotal factors closely related to forecasting performance that need further consideration: time delays in propagation dynamics and multi-scale high-dimensional interactions. In this work, we present a Series-Aligned Multi-Scale Graph Learning (SAMSGL) framework, aiming to enhance forecasting performance. In order to handle time delays in spatial interactions, we propose a series-aligned graph convolution layer to facilitate the aggregation of non-delayed graph signals, thereby mitigating the influence of time delays for the improvement in accuracy. To understand global and local spatiotemporal interactions, we develop a spatiotemporal architecture via multi-scale graph learning, which encompasses two essential components: multi-scale graph structure learning and graph-fully connected (Graph-FC) blocks. The multi-scale graph structure learning includes a global graph structure to learn both delayed and non-delayed node embeddings, as well as a local one to learn node variations influenced by neighboring factors. The Graph-FC blocks synergistically fuse spatial and temporal information to boost prediction accuracy. To evaluate the performance of SAMSGL, we conduct experiments on meteorological and traffic forecasting datasets, which demonstrate its effectiveness and superiority.