Graph Convolutional Neural Networks with Geometric and Discrimination information

Cross-subject emotion recognition in brain-computer interface based on frequency band attention graph convolutional adversarial neural networks

Graph convolutional neural networks have difficulties in model training takes a lot of time and lack of universality in meta-path design when processing knowledge graphs. To solve these issues, this paper proposes an efficient recommendation algorithm integrating knowledge graphs with graph convolutional networks(EKG-GCN). The algorithm is mainly based on the graph convolution algorithm. Firstly, the relationship between users and entities is standardized and scored, then a new neighborhood aggregation method is proposed. Some nodes in the knowledge graph are set as central nodes. A distance-influence function is set up according to the distance from other nodes to the central node, and the feature extraction of information in the knowledge graph is completed according to the distance-influence function. Finally, the knowledge graph features are used as an auxiliary to complete the recommendation task. In the experiment, three data sets were selected to compare with other advanced models, and it was found that the model is in an advantageous position in terms of training time and recommendation effect, and has a certain degree of universality.

Video-based human action recognition is one of the most important and challenging areas of research in the field of computer vision. Human action recognition has found many pragmatic applications in video surveillance, human-computer interaction, entertainment, autonomous driving, etc. Owing to the recent development of deep learning methods for human action recognition, the performance of action recognition has significantly enhanced for challenging datasets. Deep learning techniques are mainly used for recognizing actions in images and videos comprising of Euclidean data. A recent development in deep learning methods is the extension of these techniques to non-Euclidean data or graph data with many nodes and edges. Human body skeleton resembles a graph, therefore, the graph convolutional network (GCN) is applicable to the non-Euclidean body skeleton. In the past few years, GCN has emerged as an important tool for skeleton-based action recognition. Therefore, we conduct a survey using GCN methods for action recognition. Herein, we present a comprehensive overview of recent GCN techniques for action recognition, propose a taxonomy for the categorization of GCN techniques for action recognition, carry out a detailed study of the benchmark datasets, enlist relevant resources and open-source codes, and finally provide an outline for future research directions and trends. To the best of authors' knowledge, this is the first survey for action recognition using GCN techniques.

Intracranial arteries are critical blood vessels that supply the brain with oxygenated blood. Intracranial artery labels provide valuable guidance and navigation to numerous clinical applications and disease diagnoses. Various machine learning algorithms have been carried out for automation in the anatomical labeling of cerebral arteries. However, the task remains challenging because of the high complexity and variations of intracranial arteries. This study investigates a novel graph convolutional neural network with deep feature fusion for cerebral artery labeling. We introduce stacked graph convolutions in an encoder-core-decoder architecture, extracting high-level representations from graph nodes and their neighbors. Furthermore, we efficiently aggregate intermediate features from different hierarchies to enhance the proposed model's representation capability and labeling performance. We perform extensive experiments on public datasets, in which the results prove the superiority of our approach over baselines by a clear margin. Clinical relevance- The graph convolutions and feature fusion in our approach effectively extract graph information, which provides more accurate intracranial artery label predictions than existing methods and better facilitates medical research and disease diagnosis.

As a current research hotspot, graph convolution networks (GCNs) have provided new opportunities for tree species classification in multi-source remote sensing images. To solve the challenge of limited label information, a new tree species classification model was proposed by using the semi-supervised graph convolution fusion method for hyperspectral images (HSIs) and multispectral images (MSIs). In the model, the graph-based attribute features and pixel-based features are fused to deepen the correlation of multi-source images to improve accuracy. Firstly, the model employs the canonical correlation analysis (CCA) method to maximize the correlation of multi-source images, which explores the relationship between information from various sources further and offers more valuable insights. Secondly, convolution calculations were made to extract features and then map graph node fusion, which not only reduces redundancy features but also enhances compelling features. Finally, the relationship between representative descriptors is captured through the use of hyperedge convolution in the training process, and the dominant features on the graph are fully mined. The tree species are classified through two fusion feature operations, leading to improved classification performance compared to state-of-the-art methods. The fusion strategy can produce a complete classification map of the study areas.

Messenger RNA (mRNA) has emerged as a critical global technology that requires global joint efforts from different entities to develop a COVID-19 vaccine. However, the chemical properties of RNA pose a challenge in utilizing mRNA as a vaccine candidate. For instance, the molecules are prone to degradation, which has a negative impact on the distribution of mRNA among patients. In addition, little is known of the degradation properties of individual RNA bases in a molecule. Therefore, this study aims to investigate whether a hybrid deep learning can predict RNA degradation from RNA sequences. Two deep hybrid neural network models were proposed, namely GCN_GRU and GCN_CNN. The first model is based on graph convolutional neural networks (GCNs) and gated recurrent unit (GRU). The second model is based on GCN and convolutional neural networks (CNNs). Both models were computed over the structural graph of the mRNA molecule. The experimental results showed that GCN_GRU hybrid model outperform GCN_CNN model by a large margin during the test time. Validation of proposed hybrid models is performed by well-known evaluation measures. Among different deep neural networks, GCN_GRU based model achieved best scores on both public and private MCRMSE test scores with 0.22614 and 0.34152, respectively. Finally, GCN_GRU pre-trained model has achieved the highest AuC score of 0.938. Such proven outperformance of GCNs indicates that modeling RNA molecules using graphs is critical in understanding molecule degradation mechanisms, which helps in minimizing the aforementioned issues. To show the importance of the proposed GCN_GRU hybrid model, in silico experiments has been contacted. The in-silico results showed that our model pays local attention when predicting a given position’s reactivity and exhibits interesting behavior on neighboring bases in the sequence.

Recently, sparse graph-based discriminant analysis (SGDA) and collaborative graph-based discriminant analysis (CGDA) have been developed for dimensionality reduction of hyperspectral imagery. In SGDA or CGDA, a graph is constructed by -norm minimization-based representation or -norm minimization-based representation, respectively, based on labeled samples. These two methods have shown success over traditional methods by reinforcing discriminative power, but are limited in within-class representation and distribution of representation coefficients. In order to preserve intrinsic geometrical structure of original data and improve the interpretability of the underlying graph, we propose an adaptive collaborative graph for discriminant analysis (ACGDA), which explicitly models the internal relationship among within-class pixels during graph construction. The proposed method couples distance-weighted Tikhonov regularization with -norm minimization-based representation, of which the coefficients are solutions to a closed-form expression. The graph adaptively adjusts the collaborative representation by using distance-weighted measurement, which produces stronger ability of discrimination. In addition, the graph weight matrix is designed in the form of a block-diagonal structure, reducing the computational cost and further improving discriminative power. The proposed approach is compared with several traditional and state-of-the-art methods on two benchmark datasets. Experimental results demonstrate that the proposed approach can yield superior classification performance.

Graph convolutional neural networks (GCNs) have demonstrated effectiveness in processing graph structure. Due to the diversity and complexity of real-world graph data, heterogeneous GCN have attracted significant attention. However, existing research predominantly relies on explicit connections to explore graph heterogeneity. In the case of edgeless graphs, such as information systems, the absence of direct edges poses a significant challenge for employing GCNs to analyze the latent heterogeneity within these graphs. Traditional approaches overlook the topological features of information systems, resulting in information loss. This article introduces a heterogeneous graph convolutional neural network based on shadowed deviation relationship (SDHGCN) to investigate the heterogeneity of information systems, thereby improving the generalizability of heterogeneous GCNs. First, shadow deviation relationship and attribute deviation relationship are constructed derived from shadow sets and information gain, respectively. Then, dexterously integrated with the feature matrix of the information system (the relationship between objects and attributes), a highly expressive heterogeneous graph is constructed. Second, by performing graph convolution operations on the heterogeneous graph, effective node representations can be obtained to complete node classification tasks. Finally, the effectiveness and nonrandomness of SDHGCN are validated by extensive comparison and ablation experiments.

Graph convolutional neural networks (GCN) have been widely applied to many real-world problems and have achieved better results. To improve the accuracy of GCN in the three-dimensional human pose estimation (3D HPE) task, improved semantic GCNs (Simpre-RxSkip-NonCam-SemGCN and SPRA-SemGCN) are proposed. For the problem of insufficiently utilizing effective information in 3D HPE tasks, the dual-layer attention mechanism module (NonCam-attention) of extracting information is proposed. It establishes a spatial and channel-based fusion structure model by capturing the distance dependencies between different joint nodes of human poses and the associated features between different mapping channels. To reduce the training time and GPU memory for the preaggregated semantic graph convolutional networks (Pre-SemGCN) model, the simplified Pre-SemGCN module (Simpre-SemGCN) is suggested, which can accelerate the training speed of the model by eliminating the nonlinear activation layer. Further, a nested recursive expansion-based residual connection module (RxSkip + LN) is proposed to adjust the ratio of input and output with fewer parameters. To verify the effectiveness of the proposed model, we conduct experiments on the dataset Human 3.6M. The results show that the SPRA-SemGCN model proposed can effectively reduce the error of the 3D HPE task, and the mean per joint position error is finally reduced to 37.20 mm.

Contemporary deep learning approaches exhibit state-of-the-art performance in various areas. In healthcare, the application of deep learning remains limited since deep learning methods are often considered as non-interpretable black-box models. However, the Machine Learning (ML) community made recent elaborations to develop the methods of eXplainable Artificial Intelligence (XAI). The explanation methods explain single decisions of an ML model when a single data point is fed into the model’s input. In a clinical setup, a data point can represent a single patient. Data point-specific explanations could possibly assist the need in personalized precision medicine decisions via explaining patient-specific predictions. Convolutional Neural Networks (CNNs) as deep learning methods have been already applied to classify transformed into images gene expression profiles of patients. Gene expression data can be structured by a prior knowledge molecular network (encoded as a graph) representing connections between genes. Each vertex of a molecular network is assigned a gene expression value as an attribute. The set of the attributes creates a graph signal representing a patient. Emerging field of geometric deep learning deals with methods applicable to graph structured data and extends CNNs as Graph Convolutional Neural Networks (GCNNs) classifying graph signals. Layer-wise Relevance Propagation (LRP) is a method to explain decisions of CNNs classifying image data. I extended the LRP method to make it available for GCNNs. Graph Layer-wise Relevance Propagation (GLRP) is presented as a new method to explain single decisions made by a GCNN model. In this thesis, I present a novel methodology generating patient-specific molecular subnetworks as explanations for classification decisions of an ML approach utilizing prior knowledge of molecular networks. GCNN serves as a ML approach, and its decisions are explained by developed GLRP. A sanity check of the developed GLRP method was demonstrated on a hand-written digits dataset. The biological validation was performed by applying the developed methodology to gene expression data from Human Umbilical Vein Endothelial Cells (HUVEC) treated or not treated with tumor necrosis factor alpha. To show the utility of introduced methodology in the scopes of precision medicine, it was applied to a large breast cancer dataset. The generated patient-specific subnetworks largely agree with clinical knowledge and could assist precision medicine approaches by identifying common as well as novel, and potentially druggable, drivers of tumor progression. Apart from generating patient-specific subnetworks, the developed methodology can be used as a general feature selection approach. The outcome of a feature selection approach is a subset of important for classification genes corresponding to a whole dataset. It is essential to sustain stability of selected feature subsets across different datasets with the same clinical endpoint since the selected genes are possible candidates for prognostic biomarkers. I analysed the stability of feature selection performed by GCNN+LRP. I have implemented a graph convolutional layer of GCNN as a Keras layer so that the SHapley Additive exPlanations (SHAP) method could be also applied to a Keras version of a GCNN model. The stability of feature selection performed by GCNN+LRP was compared to the stability of GCNN+SHAP and other ML-based feature selection approaches. The GCNN+LRP approach shows the highest stability. GCNN+LRP subnetworks were compared to GCNN+SHAP subnetworks in terms of connectivity and permutation feature importance. While GCNN+SHAP subnetworks demonstrate higher permutation importance than GCNN+LRP subnetworks, a GCNN+LRP subnetwork of an individual patient is on average substantially more connected and, therefore more interpretable in the context of prior knowledge than a GCNN+SHAP subnetwork which consists mainly of single vertices.

Geometric deep learning provides a principled and universal way for the integration of imaging and non-imaging modes in the medical field. Graph Convolutional Networks (GCNs) have been widely explored in a variety of problems, such as disease prediction, segmentation, and matrix completion. Using large, multi-modal data sets, graphs can capture the interaction of individual elements represented as nodes in the graphs. In particular, in medical applications, nodes can represent individuals (patients or healthy controls) in a potentially large population and are accompanied by a set of features, while the edges of the graph contain the associations between subjects in an intuitive way. This representation allows the inclusion of rich imaging and non-imaging information as well as individual subject characteristics in the task of disease classification. This article gives an overview of graph convolutional neural networks, focusing on the application of graph convolutional neural networks in disease prediction, and discusses the challenges and prospects of graph convolutional neural networks in disease prediction.

This letter presents an adversarial knowledge distillation based on graph convolutional neural network. For knowledge distillation, many methods have been proposed in which the student model individually and independently imitates the output of the teacher model on the input data. Our method suggests the application of a similarity matrix to consider the relationship among output vectors, compared to the other existing approaches. The similarity matrix of the output vectors is calculated and converted into a graph structure, and a generative adversarial network using graph convolutional neural network is applied. We suggest similarity‐based knowledge distillation in which a student model simultaneously imitates both of output vector and similarity matrix of the teacher model. We evaluate our method on ResNet, MobileNet and Wide ResNet using CIFAR‐10 and CIFAR‐100 datasets, and our results outperform results of the baseline model and other existing knowledge distillations like KLD and DML.

Vehicle trajectory prediction is an important research basis for the decision making and path planning of the intelligent and connected vehicle. In the connected vehicle environment, vehicles share information and drive cooperatively, and the intelligent and connected vehicles are able to obtain more accurate and rich perception information, which provides a data basis for accurate prediction of vehicle trajectories. However, attaining accurate and effective vehicle trajectory predictions poses technical challenges due to insufficient extraction of vehicular spatial–temporal interaction features. In this paper, we propose a vehicle trajectory prediction model based on graph convolutional neural network (GCN) in a connected vehicle environment. Specifically, using the driving scene information obtained by the intelligent and connected vehicle, the spatial graph and temporal graph are constructed based on the spatial interaction coefficient (SIC) and self-attention mechanism, respectively. Then, the graph data are entered into the interaction extraction module, and the spatial interaction features and temporal interaction features are extracted separately using the graph convolutional networks, which are fused to obtain the spatial–temporal interaction information. Finally, the interaction features are learned based on the convolutional neural networks to output the future trajectory information of all vehicles in the scene by one forward operation rather than a step-by-step process. The ablation experiment results show that the method proposed in this study to model the spatiotemporal interaction among vehicles based on SIC and self-attention mechanism reduces the prediction error by 5% and 12%, respectively. The results from the model comparison experiment show that the proposed method engenders an 8% improvement in prediction accuracy over the state-of-the-art solution, providing technical and theoretical support for trajectory prediction research of intelligent and connected vehicles.

Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity of building shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet one central issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce a generic framework to overcome the issue, integrating the graph convolutional network (GCN) and deep structured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graph convolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification. Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architecture outperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, the proposed method can be generally applied to other binary or multi-label segmentation tasks.

In recent years, there has been a significant increase in the application of graph neural networks on a wide range of different problems. A specially promising direction of research is on graph convolutional neural networks (GCN). This work focuses on the application of GCNs to graph combinatorial optimization problems (GCOPs), specifically on their decision versions. GCNs are applied on the family of GCOPs in which the objective function is directly related to the number of vertices in a graph. The selected problems are the minimum vertex cover, maximum clique, minimum dominating set and graph coloring. In this work, a framework is proposed for solving problems of this type. The performance of this approach is explored for standard multi-layer GCNs using different types of convolutional layers. On top of this, we propose a new structure that is based on graph isomorphism networks. Computational experiments show that this new structure is significantly more efficient than basic structures. To further improve the performance of this method, the use of GCN ensembles is also explored. When using GCNs to generate solution values for GCOPs, they often correspond to non-feasible solutions because they violate the problem boundaries. This issue is addressed by defining an asymmetric loss function that is used during the GCN training. The proposed method is evaluated on a large set of training data consisting of graph solution pairs that can also be accessed online.