Graph Convolutional Neural Networks Research Articles

Similarity-guided graph contrastive learning for lncRNA-disease association prediction

The increasing research evidence indicates that long non-coding RNAs (lncRNAs) play important roles in regulating biological processes and are closely associated with many human diseases. Computational methods have emerged as indispensable tools for identifying associations between long non-coding RNA (lncRNA) and diseases, primarily due to the time-consuming and costly nature of traditional biological experiments. Given the scarcity of verified lncRNA-disease associations, the intensifying focus on deep learning is playing a crucial role in refining the accuracy of predictive models. Moreover, the contrastive learning method exhibits a clear advantage in situations where data is scarce or annotation costs are high. In this paper, we leverage the advantages of graph neural networks and contrastive learning to innovatively propose a similarity-guided graph contrastive learning (SGGCL) model for predicting lncRNA-disease associations. In the SGGCL model, we employ a novel similarity-guided graph data augmentation method to generate high-quality positive and negative sample pairs, addressing the scarcity of verified data. Additionally, we utilize the RWR algorithm and a graph convolutional neural network for contrastive learning, facilitating the capture of global topology and high-level node embeddings. The experimental results on several datasets demonstrate the superior predictive performance and scalability of our method in lncRNA-disease association prediction compared to state-of-the-art methods.

Identifying ADHD-Related Abnormal Functional Connectivity with a Graph Convolutional Neural Network.

Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder that is characterized by inattention, hyperactivity, and impulsivity. The neural mechanisms underlying ADHD remain inadequately understood, and current approaches do not well link neural networks and attention networks within brain networks. Our objective is to investigate the neural mechanisms related to attention and explore neuroimaging biological tags that can be generalized within the attention networks. In this paper, we utilized resting-state functional magnetic resonance imaging data to examine the differential functional connectivity network between ADHD and typically developing individuals. We employed a graph convolutional neural network model to identify individuals with ADHD. After classification, we visualized brain regions with significant contributions to the classification results. Our results suggest that the frontal, temporal, parietal, and cerebellar regions are likely the primary areas of dysfunction in individuals with ADHD. We also explored the relationship between regions of interest and attention networks, as well as the connection between crucial nodes and the distribution of positively and negatively correlated connections. This analysis allowed us to pinpoint the most discriminative brain regions, including the right orbitofrontal gyrus, the left rectus gyrus and bilateral insula, the right inferior temporal gyrus and bilateral transverse temporal gyrus in the temporal region, and the lingual gyrus of the occipital lobe, multiple regions of the basal ganglia and the upper cerebellum. These regions are primarily involved in the attention executive control network and the attention orientation network. Dysfunction in the functional connectivity of these regions may contribute to the underlying causes of ADHD.

Recent Advances and Applications of Graph Convolution Neural Network Methods in Materials Science

With the development of artificial intelligence (AI), AI plus science is increasingly valued, presenting new perspectives to scientific research. The research on using machine learning (including deep learning) to discover patterns from data and predict targeted material properties has received widespread attention, which will have a profound impact in material science studies. In recent years, there has been an increased interest in the use of deep learning in materials science, which has led to significant progress in both fundamental and applied research. One of the most notable advancements is the development of graph convolutional neural network models, which combine graph neural networks and convolutional neural networks to achieve outstanding results in materials science and bridge effectively the deep learning models and material properties predictions. The availability of large materials databases due to the rise of big data has further enhanced the relevance of these models in the field. We present, in this article, a comprehensive overview of graph convolutional neural network models, explaining their fundamental principles and highlighting a few examples of their applications in materials science, as well as current trends. The limitations and challenges that these models face, as well as the potential for future research in this dynamic area are also discussed.

Modeling Tree-like Heterophily on Symmetric Matrix Manifolds.

Tree-like structures, characterized by hierarchical relationships and power-law distributions, are prevalent in a multitude of real-world networks, ranging from social networks to citation networks and protein-protein interaction networks. Recently, there has been significant interest in utilizing hyperbolic space to model these structures, owing to its capability to represent them with diminished distortions compared to flat Euclidean space. However, real-world networks often display a blend of flat, tree-like, and circular substructures, resulting in heterophily. To address this diversity of substructures, this study aims to investigate the reconstruction of graph neural networks on the symmetric manifold, which offers a comprehensive geometric space for more effective modeling of tree-like heterophily. To achieve this objective, we propose a graph convolutional neural network operating on the symmetric positive-definite matrix manifold, leveraging Riemannian metrics to facilitate the scheme of information propagation. Extensive experiments conducted on semi-supervised node classification tasks validate the superiority of the proposed approach, demonstrating that it outperforms comparative models based on Euclidean and hyperbolic geometries.

Multiple object tracking based on appearance and motion graph convolutional neural networks with an explainer

Multiple object tracking based on appearance and motion graph convolutional neural networks with an explainer

Efficient Generation of Conformer Ensembles Using Internal Coordinates and a Generative Directional Graph Convolution Neural Network.

We present a neural-network-based high-throughput molecular conformer-generation algorithm. A chemical graph-convolutional network is trained to predict low-energy conformers in internal coordinate representation (bond lengths, bond, and torsion angles), starting from two-dimensional (2D) chemical topology. Generative neural network (NN) architecture performs denoising from torsion space, producing conformer ensembles with populations that are well correlated with torsion energy profiles. Short force-field-based energy minimization is applied to refine final conformers. All computation-intensive stages of the algorithm are GPU-optimized. The procedure (termed GINGER) is benchmarked on a commonly used test set of bioactive three-dimensional (3D) conformers from the PDB. We demonstrate highly competitive results in conformer recovery and throughput rates suitable for giga-scale compound library processing. A web server that allows interactive conformer ensemble generation by GINGER and their viewing is made freely available at https://www.molsoft.com/gingerdemo.html.

Incorporating Adaptive Sparse Graph Convolutional Neural Networks for Segmentation of Organs at Risk in Radiotherapy

Precisely segmenting the organs at risk (OARs) in computed tomography (CT) plays an important role in radiotherapy’s treatment planning, aiding in the protection of critical tissues during irradiation. Renowned deep convolutional neural networks (DCNNs) and prevailing transformer-based architectures are widely utilized to accomplish the segmentation task, showcasing advantages in capturing local and contextual characteristics. Graph convolutional networks (GCNs) are another specialized model designed for processing the nongrid dataset, e.g., citation relationship. The DCNNs and GCNs are considered as two distinct models applicable to the grid and nongrid datasets, respectively. Motivated by the recently developed dynamic-channel GCN (DCGCN) that attempts to leverage the graph structure to enhance the feature extracted by the DCNNs, this paper proposes a novel architecture termed adaptive sparse GCN (ASGCN) to mitigate the inherent limitations in DCGCN from the aspect of node’s representation and adjacency matrix’s construction. For the node’s representation, the global average pooling used in the DCGCN is replaced by the learning mechanism to accommodate the segmentation task. For the adjacency matrix, an adaptive regularization strategy is leveraged to penalize the coefficient in the adjacency matrix, resulting in a sparse one that can better exploit the relationships between nodes. Rigorous experiments on multiple OARs’ segmentation tasks of the head and neck demonstrate that the proposed ASGCN can effectively improve the segmentation accuracy. Comparison between the proposed method and other prevalent architectures further confirms the superiority of the ASGCN.

Research on traffic flow prediction method based on adaptive multi-channel graph convolutional neural networks

In order to address the issues of predefined adjacency matrices inadequately representing information in road networks, insufficiently capturing spatial dependencies of traffic networks, and the potential problem of excessive smoothing or neglecting initial node information as the layers of graph convolutional neural networks increase, thus affecting traffic prediction performance, this paper proposes a prediction model based on Adaptive Multi-channel Graph Convolutional Neural Networks (AMGCN). The model utilizes an adaptive adjacency matrix to automatically learn implicit graph structures from data, introduces a mixed skip propagation graph convolutional neural network model, which retains the original node states and selectively acquires outputs of convolutional layers, thus avoiding the loss of node initial states and comprehensively capturing spatial correlations of traffic flow. Finally, the output is fed into Long Short-Term Memory networks to capture temporal correlations. Comparative experiments on two real datasets validate the effectiveness of the proposed model.

Log2Graph: A graph convolution neural network based method for insider threat detection

With the advancement of network security equipment, insider threats gradually replace external threats and become a critical contributing factor for cluster security threats. When detecting and combating insider threats, existing methods often concentrate on users’ behavior and analyze logs recording their operations in an information system. Traditional sequence-based method considers temporal relationships for user actions, but cannot represent complex logical relationships well between various entities and different behaviors. Current machine learning-based approaches, such as graph-based methods, can establish connections among log entries but have limitations in terms of complexity and identifying malicious behavior of user’s inherent intention. In this paper, we propose Log2Graph, a novel insider threat detection method based on graph convolution neural network. To achieve efficient anomaly detection, Log2Graph first retrieves logs and corresponding features from log files through feature extraction. Specifically, we use an auxiliary feature of anomaly index to describe the relationship between entities, such as users and hosts, instead of establishing complex connections between them. Second, these logs and features are augmented through a combination of oversampling and downsampling, to prepare for the next-stage supervised learning process. Third, we use three elaborated rules to construct the graph of each user by connecting the logs according to chronological and logical relationships. At last, the dedicated built graph convolution neural network is used to detect insider threats. Our validation and extensive evaluation results confirm that Log2Graph can greatly improve the performance of insider threat detection compared to existing state-of-the-art methods.

Bearing fault diagnosis based on a multiple-constraint modal-invariant graph convolutional fusion network

Multisensor data fusion method can improve the accuracy of bearing fault diagnosis, in order to address the problems of single-sensor data types and the insufficient exploration of redundancy and complementarity between different modal data in most existing multisensor data fusion methods for bearing fault diagnosis, a bearing fault diagnosis method based on a Multiple-Constraint Modal-Invariant Graph Convolutional Fusion Network (MCMI-GCFN) is proposed in this paper. Firstly, a Convolutional Autoencoder (CAE) and Squeeze-and-Excitation Block (SE block) are used to extract features of raw current and vibration signals. Secondly, the model introduces source domain classifiers and domain discriminators to capture modal invariance between different modal data based on domain adversarial training, making use of the redundancy and complementarity between multimodal data. Then, the spatial aggregation property of Graph Convolutional Neural Networks (GCN) is utilized to capture the dependency relationship between current and vibration modes with similar time step features for accurately fusing contextual semantic information. Finally, the validation is conducted on the public bearing damage current and vibration dataset from Paderborn University. The experimental results showed that the delivered fusion method achieved a bearing fault diagnosis accuracy of 99.6 %, which was about 9 %–11.4 % better than that with nonfusion methods.

Health insurance fraud detection based on multi-channel heterogeneous graph structure learning

Health insurance fraud is becoming more common and impacting the fairness and sustainability of the health insurance system. Traditional health insurance fraud detection primarily relies on recognizing established data patterns. However, with the ever-expanding and complex nature of health insurance data, it is difficult for these traditional methods to effectively capture evolving fraudulent activity and tactics and keep pace with the constant improvements and innovations of fraudsters. As a result, there is an urgent need for more accurate and flexible analytics to detect potential fraud. To address this, the Multi-channel Heterogeneous Graph Structured Learning-based health insurance fraud detection method (MHGSL) was proposed. MHGSL constructs a graph of health insurance data from various entities, such as patients, departments, and medicines, and employs graph structure learning to extract topological structure, features, and semantic information to construct multiple graphs that reflect the diversity and complexity of the data. We utilize deep learning methods such as heterogeneous graph neural networks and graph convolutional neural networks to combine multi-channel information transfer and feature fusion to detect anomalies in health insurance data. The results of extensive experiments on real health insurance data demonstrate that MHGSL achieves a high level of accuracy in detecting potential fraud, which is better than existing methods, and is able to quickly and accurately identify patients with fraudulent behaviors to avoid loss of health insurance funds. Experiments have shown that multi-channel heterogeneous graph structure learning in MHGSL can be very helpful for health insurance fraud detection. It provides a promising solution for detecting health insurance fraud and improving the fairness and sustainability of the health insurance system. Subsequent research on fraud detection methods can consider semantic information between patients and different types of entities.

Cyber security attack recognition on cloud computing networks based on graph convolutional neural network and graphsage models

In this paper, the modeling of the network attacks of cloud computing through Graph Neural Networks is considered. Based on structural features and relationships between neighboring nodes and the edges of the cloud ecosystem a cyberattack detection method is proposed. A simulation dataset is created on the CSE-CIC-IDS2018 dataset to train and test the proposed graph neural network based models. In a comparative analysis of the suggested method with the existing one superior results are obtained from the model constructed on the GraphSAGE algorithm. Thus in the recognition of dataset samples, the model obtained a value of 0.97739 according to the accuracy metric. The values obtained by the algorithm on precision, recall, and F1-score metrics were also higher compared to the Graph Convolutional Neural Network model.

Drug-Online: an online platform for drug-target interaction, affinity, and binding sites identification using deep learning

BackgroundAccurately identifying drug-target interaction (DTI), affinity (DTA), and binding sites (DTS) is crucial for drug screening, repositioning, and design, as well as for understanding the functions of target. Although there are a few online platforms based on deep learning for drug-target interaction, affinity, and binding sites identification, there is currently no integrated online platforms for all three aspects.ResultsOur solution, the novel integrated online platform Drug-Online, has been developed to facilitate drug screening, target identification, and understanding the functions of target in a progressive manner of “interaction-affinity-binding sites”. Drug-Online platform consists of three parts: the first part uses the drug-target interaction identification method MGraphDTA, based on graph neural networks (GNN) and convolutional neural networks (CNN), to identify whether there is a drug-target interaction. If an interaction is identified, the second part employs the drug-target affinity identification method MMDTA, also based on GNN and CNN, to calculate the strength of drug-target interaction, i.e., affinity. Finally, the third part identifies drug-target binding sites, i.e., pockets. The method pt-lm-gnn used in this part is also based on GNN.ConclusionsDrug-Online is a reliable online platform that integrates drug-target interaction, affinity, and binding sites identification. It is freely available via the Internet at http://39.106.7.26:8000/Drug-Online/.

GCN-Net: 3D Point Cloud Classification & Localization Using Graph-CNN

In this paper, we have demonstrated the application of a graph convolutional neural network for the purpose of object detection in a LiDAR point cloud. In order to encode the point cloud in the most time-effective manner, we make use of a near-neighbors graph with a defined radius. We create a graph convolutional neural network so that we can find out what kind of object and what class each vertex in a graph represents. We design a box merging and scoring operation to reliably combine detections from numerous vertices into a single score, and we offer an auto-registration strategy as a means of reducing the amount of translation errors that occur inside the system. According to the results of our tests using the KITTI benchmark, we are able to draw the conclusion that the method that was suggested achieves competitive accuracy with the point cloud, even beating fusion-based methods in some instances. According to the results of our research, the graph neural network has the potential to become an effective new tool for the detection of 3D objects.

Transferring predictions of formation energy across lattices of increasing size*

In this study, we show the transferability of graph convolutional neural network (GCNN) predictions of the formation energy of the nickel-platinum solid solution alloy across atomic structures of increasing sizes. The original dataset was generated with the large-scale atomic/molecular massively parallel simulator using the second nearest-neighbor modified embedded-atom method empirical interatomic potential. Geometry optimization was performed on the initially randomly generated face centered cubic crystal structures and the formation energy has been calculated at each step of the geometry optimization, with configurations spanning the whole compositional range. Using data from various steps of the geometry optimization, we first trained our open-source, scalable implementation of GCNN called HydraGNN on a lattice of 256 atoms, which accounts well for the short-range interactions. Using this data, we predicted the formation energy for lattices of 864 atoms and 2048 atoms, which resulted in lower-than-expected accuracy due to the long-range interactions present in these larger lattices. We accounted for the long-range interactions by including a small amount of training data representative for those two larger sizes, whereupon the predictions of HydraGNN scaled linearly with the size of the lattice. Therefore, our strategy ensured scalability while reducing significantly the computational cost of training on larger lattice sizes.

A Metro Passenger Flow Forecasting Model Based On Time-series Evolving Interaction Graph Network

Passenger flow forecasting is an important task in metro operation management. In order to achieve more accurate metro passenger flow forecasting, this paper proposes a metro passenger flow forecasting model based on time-series evolution interaction graph. First, by introducing two kinds of inter-station interaction graphs, namely connectivity graph and temporal correlation graph, to capture the potential interaction relationship among metro passenger flow stations. Then, by using the time-series evolving graph, the weights of the graph convolutional neural network are dynamically evolved in time series. Finally, taking Suzhou Metro as an example, the short-term passenger flow of the metro is forecasted. The experimental results show that the Root Mean Squared Error (RMSE) of this model is 34.17, the Mean Absolute Error (MAE) is 16.35, the R-Squared is 0.94, the Mean Absolute Percent Error (MAPE) is 0.21. All evaluation metrics are better than the baseline models, thus verifying the effectiveness and applicability of the metro passenger flow forecasting model based on the time series evolution interaction graph.

Boosting efficiency in state estimation of power systems by leveraging attention mechanism

Ensuring stability and reliability in power systems requires accurate state estimation, which is challenging due to the growing network size, noisy measurements, and nonlinear power-flow equations. In this paper, we introduce the Graph Attention Estimation Network (GAEN) model to tackle power system state estimation (PSSE) by capitalizing on the inherent graph structure of power grids. This approach facilitates efficient information exchange among interconnected buses, yielding a distributed, computationally efficient architecture that is also resilient to cyber-attacks. We develop a thorough approach by utilizing Graph Convolutional Neural Networks (GCNNs) and attention mechanism in PSSE based on Supervisory Control and Data Acquisition (SCADA) and Phasor Measurement Unit (PMU) measurements, addressing the limitations of previous learning architectures. In accordance with the empirical results obtained from the experiments, the proposed method demonstrates superior performance and scalability compared to existing techniques. Furthermore, the amalgamation of local topological configurations with nodal-level data yields a heightened efficacy in the domain of state estimation. This work marks a significant achievement in the design of advanced learning architectures in PSSE, contributing and fostering the development of more reliable and secure power system operations.

StellarPath: Hierarchical-vertical multi-omics classifier synergizes stable markers and interpretable similarity networks for patient profiling.

The Patient Similarity Network paradigm implies modeling the similarity between patients based on specific data. The similarity can summarize patients' relationships from high-dimensional data, such as biological omics. The end PSN can undergo un/supervised learning tasks while being strongly interpretable, tailored for precision medicine, and ready to be analyzed with graph-theory methods. However, these benefits are not guaranteed and depend on the granularity of the summarized data, the clarity of the similarity measure, the complexity of the network's topology, and the implemented methods for analysis. To date, no patient classifier fully leverages the paradigm's inherent benefits. PSNs remain complex, unexploited, and meaningless. We present StellarPath, a hierarchical-vertical patient classifier that leverages pathway analysis and patient similarity concepts to find meaningful features for both classes and individuals. StellarPath processes omics data, hierarchically integrates them into pathways, and uses a novel similarity to measure how patients' pathway activity is alike. It selects biologically relevant molecules, pathways, and networks, considering molecule stability and topology. A graph convolutional neural network then predicts unknown patients based on known cases. StellarPath excels in classification performances and computational resources across sixteen datasets. It demonstrates proficiency in inferring the class of new patients described in external independent studies, following its initial training and testing phases on a local dataset. It advances the PSN paradigm and provides new markers, insights, and tools for in-depth patient profiling.

Novel GCN Model Using Dense Connection and Attention Mechanism for Text Classification

Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) based text classification algorithms currently in use can successfully extract local textual features but disregard global data. Due to its ability to understand complex text structures and maintain global information, Graph Neural Network (GNN) has demonstrated considerable promise in text classification. However, most of the GNN text classification models in use presently are typically shallow, unable to capture long-distance node information and reflect the various scale features of the text (such as words, phrases, etc.). All of which will negatively impact the performance of the final classification. A novel Graph Convolutional Neural Network (GCN) with dense connections and an attention mechanism for text classification is proposed to address these constraints. By increasing the depth of GCN, the densely connected graph convolutional network (DC-GCN) gathers information about distant nodes. The DC-GCN multiplexes the small-scale features of shallow layers and produces different scale features through dense connections. To combine features and determine their relative importance, an attention mechanism is finally added. Experiment results on four benchmark datasets demonstrate that our model’s classification accuracy greatly outpaces that of the conventional deep learning text classification model. Our model performs exceptionally well when compared to other text categorization GCN algorithms.

Simplified neural architecture for efficient human motion prediction in human-robot interaction

Human motion prediction is essential for safe and effective human-robot interaction, but modeling the intricate spatio-temporal dynamics inherent in human movement remains challenging. While recent methods have advanced motion prediction accuracy, they rely on complex neural architectures such as Graph Convolutional Networks and Recurrent Neural Networks, demanding extensive hyperparameter tuning. To overcome this limitation, we propose a streamlined multi-stage layer incremental perceptron (MSLP) architecture that achieves competitive results with far fewer parameters, improving efficiency. The MSLP eschews the complexity of prevalent networks and instead takes a stepped refinement approach to predict intricate motions using a lightweight model. This simplified yet effective design enables nuanced learning of spatio-temporal relationships without exhaustive tuning. Specifically, the MSLP incorporates two key components: a multi-channel feature extraction and enhancement block (MFE-block) and a temporal feature extraction module (TFE-block). The MFE-block strengthens the representation of each action node by integrating multi-dimensional action features. The TFE-block then captures the contextual relationships between actions over time. Together, the MFE-block and TFE-block allow the MSLP to model the complex spatial and temporal dynamics of human movement using a streamlined architecture and minimal parameter tuning. When evaluated on established datasets including Human3.6 M, CMU, 3DPW, and AMASS, the proposed MSLP method achieves improved accuracy gains of 16.7%-67.0% over existing state-of-the-art techniques. Additionally, the MSLP significantly reduces the number of parameters by 35.7%-99.5% compared to prior architectures. We find that the proposed MSLP significantly improves both long-term prediction and generalization capabilities of the model.