Graph Convolutional Network Model Research Articles

Automatic road network selection method considering functional semantic features of roads with graph convolutional networks

Road network selection plays a key role in map generalization for creating multi-scale road network maps. Existing methods usually determine road importance based on road geometric and topological features, few evaluate road importance from the perspective of road utilization based on human travel data, ignoring the functional values of roads, which leads to a mismatch between the generated results and people’s needs. This paper develops two functional semantic features (i.e. travel path selection probability and regional attractiveness) to measure the functional importance of roads and proposes an automatic road network selection method based on graph convolutional networks (GCN), which models road network selection as a binary classification. Firstly, we create a dual graph representing the source road network and extract road features including six graphical and two functional semantic features. Then, we develop an extended GCN model with connectivity loss for generating multi-scale road networks and propose a refinement strategy based on the road continuity principle to ensure road topology. Experiments demonstrate the proposed model with functional features improves the quality of selection results, particularly for large and medium scale maps. The proposed method outperforms state-of-the-art methods and provides a meaningful attempt for artificial intelligence models empowering cartography.

Automatically Extracting and Utilizing EEG Channel Importance Based on Graph Convolutional Network for Emotion Recognition.

Graph convolutional network (GCN) based on the brain network has been widely used for EEG emotion recognition. However, most studies train their models directly without considering network dimensionality reduction beforehand. In fact, some nodes and edges are invalid information or even interference information for the current task. It is necessary to reduce the network dimension and extract the core network. To address the problem of extracting and utilizing the core network, a core network extraction model (CWGCN) based on channel weighting and graph convolutional network and a graph convolutional network model (CCSR-GCN) based on channel convolution and style-based recalibration for emotion recognition have been proposed. The CWGCN model automatically extracts the core network and the channel importance parameter in a data-driven manner. The CCSR-GCN model innovatively uses the output information of the CWGCN model to identify the emotion state. The experimental results on SEED show that: 1) the core network extraction can help improve the performance of the GCN model; 2) the models of CWGCN and CCSR-GCN achieve better results than the currently popular methods. The idea and its implementation in this paper provide a novel and successful perspective for the application of GCN in brain network analysis of other specific tasks.

A graph convolutional network model based on regular equivalence for identifying influential nodes in complex networks

The identification of influential nodes in complex networks is an interesting problem. Traditional approaches, such as metric- and machine learning-based approaches, often fail to adequately consider the network structure or node features, limiting their applications in certain scenarios. Deep learning-based methods, particularly those using graph neural networks (GNNs), have yielded remarkable results in this field. However, there is a lack of utilization of the regular equivalence-based similarity between nodes to feature construction, which is critical to deep learning-based methods. Nevertheless, regular equivalence-based similarity is extremely suitable to the quantification of the similarity between influential nodes, as these nodes usually have similar structural properties but do not require common neighbors. Building upon graph convolutional network (GCN, a specific type of GNN) and the regular equivalence-based similarity, this study proposes a novel method for identifying influential nodes in complex networks. Particularly, the regular equivalence-based similarities between nodes are considered to construct node features; a GCN is enhanced to improve the identification of influential nodes. Experiments on several datasets indicate that the proposed method is superior to state-of-the-art methods, demonstrating the advantages of the proposed feature construction based on regular equivalence-based similarity over the identification of influential nodes.

Graph-Based Traffic Forecasting with the Dynamics of Road Symmetry and Capacity Performance

Symmetry in traffic patterns is a fundamental aspect of intelligent transportation systems, aiming to precisely predict traffic flow in real time despite the complex interplay of spatial and temporal factors. This paper presents a novel method of traffic forecasting that incorporates parameters related to road symmetry into a Graph Convolution Network model. Our model is crafted to dynamically adjust to real-time changes in road conditions, including the presence of symmetric and asymmetric road layouts, which substantially influence traffic flow. We have developed a GCN model that not only accounts for standard traffic flow metrics but also integrates a matrix representing road symmetry. The model undergoes training and validation on the METR-LA dataset, showcasing a significant enhancement in prediction accuracy. In the comparative analysis of state-of-the-art methods, our model demonstrated a significant enhancement in performance, achieving 30.68% improvement in Mean Squared Error (MSE) and a 24.28% improvement in Mean Absolute Error (MAE) over the best-performing method. The implications of our research are profound for urban planners, traffic management systems, and navigation service providers, as it offers a more dependable tool for forecasting traffic conditions, aiding in road design, and refining route planning strategies based on the symmetry of road networks.

Multiscale graph based spatio-temporal graph convolutional network for energy consumption prediction of natural gas transmission process

Energy consumption prediction is crucial for planning and managing natural gas networks, enhancing transmission efficiency. However, most of relevant studies fail to consider the topology of natural gas network. Therefore, a multiscale graph based spatio-temporal graph convolutional network model (MG-STGCN) is proposed, which can extract the multi-scale relationship of data. Based on graph convolutional and temporal gated convolution network, data correlation, spatial dependence and time dependence are considered to improve the prediction effect. In order to verify the effect of the model, the model is tested based on two natural gas networks in different region of China. The single step prediction results of MG-STGCN are significantly better than spatio-temporal graph convolutional network (STGCN), long short-term memory (LSTM), gate recurrent unit (GRU) and temporal convolutional network (TCN), which proves the effectiveness and generalization ability of MG-STGCN. The training time of MG-STGCN is reduced by 20.8 % compared with STGCN. In different prediction time step, the average prediction effect of MG-STGCN is better than that of other methods, and the performance improvement rate is not less than 8.6 %. MG-STGCN can well capture the parameter correlation, spatial and temporal dependence of data, and achieve effective prediction of pipeline energy consumption.

A Relational Graph Convolution Network-Based Smart Risk Recognition Model for Financial Transactions

The financial transaction relationships between existing entities are complex and diverse. In this situation, traditional risk control methods mainly ignored such complex and implicit relationship characteristics, remaining difficult to cope with complex and ever-changing financial risks. To address this issue, this paper proposes a novel relational graph convolution network (GCN)-based smart risk recognition model for financial transactions. Firstly, the classic GCN is simplified based on spatiotemporal effect. Then, feature extraction is conducted for financial transaction data, and a transformer encoder-based GCN model is proposed for risk recognition. The proposed model in this work is named as graph transformer graph convolutional network (GT-GCN) for short. In addition, fuzzy evaluation method is added into it. Finally, some experiments are conducted on real-world financial transaction data to make validation for the proposed GT-GCN. The research results indicate that the GT-GCN can not only effectively identify risks in financial transactions, but also has high accuracy and predictive ability. The application of GT-GCN to actual datasets also has good scalability and adaptability, and it can be resiliently extended into many other fields.

Traffic Congestion Prediction Using Graph Convolution Networks

Traffic congestion is a critical issue in urban transportation systems, leading to increased travel times, fuel consumption, and air pollution. Furthermore, accurate prediction of traffic conditions is essential for effective traffic management and route planning. However, traditional approaches often fail to capture the complex spatiotemporal dependencies inherent in road networks. This study compares the performance of Graph Convolutional Networks (GCNs) for traffic congestion prediction using Amsterdam sensor location datasets from 13 locations (01-10-2023 to 31-10-2023) and 18 locations (01-01-2024 to 26-01-2024). The GCN model achieves an accuracy above 0.5, with a peak accuracy of 0.6 for the 18-location dataset and 0.55 for the 13-location dataset. Precision ranges from 0.5 to 0.8, while recall oscillates between 0.5 and 0.6. Also, the F1-score reaches 0.6 for the 18-location dataset and remains above 0.4 for the 13-location dataset. The results demonstrate the GCN's effectiveness in capturing spatial dependencies and achieving high-performance metrics, with better performance observed for larger datasets. Moreover, the findings contribute to the development of intelligent schemes for GCNs and the Internet of Vehicles in Intelligent Transportation Systems (ITS), advancing traffic congestion prediction capabilities.

A novel positive–negative graph convolutional network-based fault diagnosis method with application to complex systems

Fault diagnosis plays a crucial role in ensuring the safe and stable operation of complex industrial systems. Among various existing methods, graph convolutional network (GCN)-based methods can handle graph-structured data commonly found in industrial systems, due to their capability to capture complex relationships within datasets through association graphs. However, conventional GCN models exclusively consider positive association relationship between data, but do not account for the negative one, resulting in embedding vectors that exhibit clustering tendencies and the over-smoothing issue. To address these challenges, a positive–negative GCN-based fault diagnosis method is proposed in this paper. In the method, the conventional association graph is treated as a positive graph, and a corresponding negative one is constructed to capture negative relationships within the dataset. Furthermore, a graph-level data aggregation strategy is introduced to aggregate the information from both association graphs, and incorporate them into the forward propagation process. Fault diagnosis is achieved using a iteratively trained GCN model. Experimental results on two cases demonstrate that the proposed method outperforms existing fault diagnosis methods in terms of diagnostic performance.

A semantic backdoor attack against graph convolutional networks

Graph convolutional networks (GCNs) have been very effective in addressing the issue of various graph-structured related tasks, such as node classification and graph classification. However, recent research has shown that GCNs are vulnerable to a new type of threat called a backdoor attack, where the adversary can inject a hidden backdoor into GCNs so that the attacked model performs well on benign samples, but its prediction will be maliciously changed to the attacker-specified target class if the hidden backdoor is activated by the attacker-defined trigger. A semantic backdoor attack is a new type of backdoor attack on deep neural networks (DNNs), where a naturally occurring semantic feature of samples can serve as a backdoor trigger such that the infected DNNs models will misclassify testing samples containing the predefined semantic feature even without the requirement of modifying the testing samples. Since the backdoor trigger is a naturally occurring semantic feature of the samples, semantic backdoor attacks are more imperceptible and pose a new and serious threat. Existing research on semantic backdoor attacks focuses on the tasks of CNNs-based (Convolutional Neural Networks) image classification and LSTM-based (Long Short-Term Memory) text classification or word prediction. Little attention has been given to semantic backdoor attacks on GCNs models.In this paper, we investigate whether such semantic backdoor attacks are possible for GCNs and propose a semantic backdoor attack against GCNs (SBAG) under the context of graph classification to reveal the existence of this security vulnerability in GCNs. SBAG uses a certain type of nodes in the samples as a backdoor trigger and injects a hidden backdoor into GCNs models by poisoning training data. The backdoor will be activated, and the GCNs models will give malicious classification results specified by the attacker even on unmodified samples as long as the samples contain enough trigger nodes. We evaluate SBAG on five graph datasets. The experimental results indicate that SBAG can achieve attack success rates of approximately 99.9% on unmodified testing samples that naturally contain the trigger and attack success rates over 82% on testing samples modified to inject the trigger, respectively, both under poisoning rates of less than 5%. 11Our code is available at: github.

TVGCN: Time-varying graph convolutional networks for multivariate and multifeature spatiotemporal series prediction.

Spatiotemporal (ST) graph modeling has garnered increasing attention recently. Most existing methods rely on a predefined graph structure or construct a single learnable graph throughout training. However, it is challenging to use a predefined graph structure to capture dynamic ST changes effectively due to evolving node relationships over time. Furthermore, these methods typically utilize only the original data, neglecting external temporal factors. Therefore, we put forward a novel time-varying graph convolutional network model that integrates external factors for multifeature ST series prediction. Firstly, we construct a time-varying adjacency matrix using attention to capture dynamic spatial relationships among nodes. The graph structure adapts over time during training, validation, and testing phases. Then, we model temporal dependence by dilated causal convolution, leveraging gated activation unit and residual connection. Notably, the prediction accuracy is enhanced through the incorporation of embedding absolute time and the fusion of multifeature. This model has been applied to three real-world multifeature datasets, achieving state-of-the-art performance in all cases. Experiments show that the method has high accuracy and robustness when applied to multifeature and multivariate ST series problems.

Enhancing graph convolutional networks with progressive granular ball sampling fusion: A novel approach to efficient and accurate GCN training

Graph convolutional network (GCN) has gained considerable attention and has been widely utilized in graph data analytics. However, training large GCNs presents considerable challenges owing to the inherent complexity of graph-structured data. Previous training algorithms frequently struggle with slow convergence speed caused by full-batch gradient descent on entire graphs and reduced model performance due to inappropriate node sampling methods. To address these issues, we propose a novel framework called Progressive Granular Ball Sampling Fusion (PGBSF). PGBSF leverages granular ball sampling to partition the original graph into a collection of subgraphs, thereby enhancing both training efficiency and detail capture. Then, it applies a progressive approach accompanied by a parameter-sharing strategy for incremental GCN model training, which results in robust performance and rapid convergence speed. This simple yet effective strategy considerably enhances classification accuracy and memory efficiency. The experiment results show that our proposed architecture consistently outperforms other baseline models in terms of accuracy across almost all datasets with different label rates. In addition, PGBSF improves GCN performance significantly on large and complex datasets. Moreover, GCN+PGBSF reduces time complexity by training on subgraphs and achieves the fastest convergence speed among all models, with a relatively small variance in loss during training.

Analysis of patch-based GCN risk score distribution corresponding to gene mutations in colorectal cancer using whole slide images.

e15650 Background: Colorectal cancer (CRC) is one of the most common malignancies, with the third highest incidence and the second highest mortality in the world. Risk scores are typically employed to predict outcomes such as disease risk, prognosis, or treatment response. Risk scores are usually calculated by combining biomarkers or genetic variants with statistical models, such as logistic regression or Cox proportional hazards models, and then observe the relationship between genetic variations and survival time through survival analysis. We have constructed a deep learning model based on Graph Convolutional Networks (GCNs), which is capable of predicting risk scores using Whole Slide Images (WSIs). Statistical analyses were applied to explore the distribution of risk scores associated with different variants in colorectal cancer. Methods: We performed risk scores prediction on a total of 384 samples from TCGA-COAD and TCGA-READ using our patch-based GCN model. We analyzed the distribution of risk scores in colorectal cancer samples and investigated the effects of gene mutations in key pathways on these risk scores. Results: Risk score predictions by our patch-based GCN model were conducted on 384 samples, revealing that the maximum, minimum, median, mean, and standard deviation of risk scores were -0.78, -1.89, -1.34, -1.34, and 0.20, respectively. The data overall conformed to a normal distribution ( p < 0.05 ). We selected core genes in key pathways combined with top ten genes with the highest mutation frequency in colorectal cancer for statistical analysis to explore the correlation with the predicted risk scores. These gene mutations were found in a total of 346 patients. The results indicated that mutations in the TP53 and OBSCN genes led to significant differences in risk scores as predicted by our model ( p < 0.05 ). The risk scores based on gene mutations also have significant differences and consistent trend in these genes. Conclusions: Our results indicate the risk scores generated by the patch-based GCN model have the consistent trend with the risk scores generated by mutation information of core genes in colorectal cancer. Whether risk scores based on digital pathology prediction can replace mutation detection in predicting patient survival status requires further exploration.

Link Prediction in Dynamic Social Networks Combining Entropy, Causality, and a Graph Convolutional Network Model.

Link prediction is recognized as a crucial means to analyze dynamic social networks, revealing the principles of social relationship evolution. However, the complex topology and temporal evolution characteristics of dynamic social networks pose significant research challenges. This study introduces an innovative fusion framework that incorporates entropy, causality, and a GCN model, focusing specifically on link prediction in dynamic social networks. Firstly, the framework preprocesses the raw data, extracting and recording timestamp information between interactions. It then introduces the concept of "Temporal Information Entropy (TIE)", integrating it into the Node2Vec algorithm's random walk to generate initial feature vectors for nodes in the graph. A causality analysis model is subsequently applied for secondary processing of the generated feature vectors. Following this, an equal dataset is constructed by adjusting the ratio of positive and negative samples. Lastly, a dedicated GCN model is used for model training. Through extensive experimentation in multiple real social networks, the framework proposed in this study demonstrated a better performance than other methods in key evaluation indicators such as precision, recall, F1 score, and accuracy. This study provides a fresh perspective for understanding and predicting link dynamics in social networks and has significant practical value.

Graph convolutional network for lithological classification and mapping using stream sediment geochemical data and geophysical data

Lithological mapping plays a vital role in acquiring a comprehensive understanding of subsurface rocks and geological structures. Traditional lithological mapping relies heavily on manual field surveys, with the accuracy of the mapping greatly constrained by the expertise of mappers, and thus this process is commonly slow and costly. In the present study, the graph convolutional network (GCN) method was proposed for efficient and automatic lithological mapping, using various geological survey data (e.g. geochemical and geophysical data). The GCN is not limited by the spatial distribution of sampling data, and hence it can be directly applied to the integrated resampling data that do not adhere to the regular spatial distribution patterns of Euclidean space. To evaluate the potential application of the GCN method in lithological classification and mapping, a case study was conducted in the Maqin region (China). Geochemical and geophysical data were utilized as the basis for lithological classification, as they can provide valuable information on geochemical compositions and physical properties of geological bodies, respectively. The study process was primarily divided into three parts. First, basic pre-processing was conducted on the geochemical data and the geophysical data, including centred log-ratio transformation and resampling. Subsequently, the resampled points were divided into training and testing sets in the proportion of 5.5:1. In the training set, 20% of the points are randomly selected as the validation set. Ultimately, using each resampled point as a node and the integrated geochemical and geophysical data as features, a GCN model and an undirected graph were constructed based on an adjacency distance of 1 km. The graph was employed by the constructed GCN model for lithological classification. The results reveal that the majority of lithological units can be accurately classified with an overall accuracy of 86%, indicating that the GCN model exhibits good applicability in lithological classification.

Behaviour recognition of housed sheep based on spatio-temporal information

ABSTRACT Livestock behavior is related to the healthy breeding and welfare level. Therefore, monitoring the behavior of sheep is helpful to predict the health status of sheep and thus safeguard the production performance of sheep. Taking semi-housed sheep as the research object, a behavior identification method for housed sheep based on spatio-temporal information is proposed. Firstly, video acquisition of housed sheep is carried out, and sheep detection and tracking is implemented based on the YOLOv5 coupled with a Deep-SORT algorithm, which detects sheep from the flock and labels their identity information; then, sheep posture estimation is done based on the Alphapose algorithm, which estimates the keypoints in the skeleton; finally, the detected keypoints are inputted into the trained spatio-temporal graph convolutional network model, and the spatio-temporal graph constructed from the keypoints and edge information is used for sheep behavior recognition. In the study, two keypoints selection proposals were made to implement sheep behavior recognition for non-contacted detection of ruminating, lying down and other behaviors. The results show the feasibility of sheep behavior recognition based on spatio-temporal information in semi-housed farming. The method provides a new solution idea for intelligent monitoring of sheep behavior and health assessment.

Basketball Sports Posture Recognition Technology Based on Improved Graph Convolutional Neural Network

Basketball has rapidly developed in recent years. Analysis of various moves in basketball can provide technical references for professional players and assist referees in judging games. Traditional technology can no longer provide modern basketball players with theoretical support. Therefore, using intelligent methods to recognize human body postures in basketball was a relatively innovative approach. To be able to recognize the basketball sports posture of players more accurately, the experiment proposes a basketball stance recognition model based on enhanced graph convolutional networks (GCN), that is, the basketball stance recognition model based on enhanced GCN and spatial temporal graph convolutional network (ST-GCN) model. This model combines the respective advantages of the GCN and temporal convolutional network and can handle graph-structured data with time-series relationships. The ST-GCN can be further deduced by realizing the convolution operation of the graph structure and establishing a spatiotemporal graph convolution model for the posture sequence of a person’s body. A dataset of technical basketball actions is constructed to verify the effectiveness of the ST-GCN model. The final experimental findings indicated that the final recognition accuracy of the ST-GCN model for basketball postures was approximately 95.58%, whereas the final recognition accuracy of the long short term memory + multiview re-observation skeleton action recognition (LSTM+MV+AC) model was about 93.65%.

A self-attention dynamic graph convolution network model for traffic flow prediction

A self-attention dynamic graph convolution network model for traffic flow prediction

A knowledge-driven graph convolutional network for abnormal electrocardiogram diagnosis

The electrocardiogram (ECG) signal comprising P-, Q-, R-, S-, and T-waves is an indispensable noninvasive diagnostic tool for analyzing physiological conditions of the heart. In general, traditional ECG intelligent diagnosis methods gradually extract features of the signal from input data until they can classify the ECG signal. However, the decision-making process of ECG intelligence models is implicit to clinicians. Clinical experts rely on clear and specific features extracted from ECG data to diagnose cardiac diseases effectively. Inspired by this clinical diagnosis mechanism, we propose an ECG knowledge graph (ECG-KG) framework primarily to improve ECG classification by presenting knowledge of ECG clinical diagnosis. In particular, the ECG-KG framework contains an ECG semantic feature extraction module, a knowledge graph construction module, and an ECG classification module. First, the ECG semantic feature extraction module locates the key points using the difference value method and further calculates the ECG attribute features. Further, the knowledge graph construction module utilizes attribute features to design entities and relationships for constructing abnormal ECG triples. The triples vectorize ECG abnormalities through the strategy of knowledge graph embedding strategy. Finally, the ECG classification module combines the ECG knowledge graph with the graph convolutional network model and adequately integrates expert knowledge to identify ECG abnormalities. Experiments conducted on the benchmark QT, the CPSC-2018, and the ZZU-ECG datasets show that the ECG-KG framework considerably outperforms other ECG diagnosis models, indicating the effectiveness of the ECG-KG framework for ECG abnormality diagnosis.

PMDAGS: Predicting miRNA-Disease Associations With Graph Nonlinear Diffusion Convolution Network and Similarities.

Many studies have proven that microRNAs (miRNAs) can participate in a wide range of biological processes and can be considered as potential noninvasive biomarkers for disease diagnosis and prognosis. Therefore, many computational methods have been developed to identifying miRNA-disease associations, ultimately enhancing the efficiency of disease diagnosis and treatment. In this study, we also introduced a new computational method called PMDAGS, which predicts miRNA-disease associations by utilizing graph nonlinear diffusion convolution network and similarities. PMDAGS first calculates miRNA similarity and disease similarity based on miRNA-target interactions, disease-gene associations and known miRNA-disease associations, respectively. Next, we construct the initial feature of each miRNA (disease) by concatenating its final similarity vector with its known association vector. Based on the known miRNA-disease association network and the initial feature vector of each node, we further apply nonlinear diffusion graph convolution network model to extract the feature embedding vectors. Finally, we concatenate the feature embedding vectors of miRNA and disease and input them into a multi-layer perceptron to identify potential miRNA-disease associations. We conduct 5-fold cross validation (5CV), 10-fold cross validation (10CV), and global leave-one-out cross validation (GLOOCV) on HMDD v2.0 and HMDD v3.2. PMDAGS achieves AUCs of 0.9222, 0.9228, and 0.9221 under 5CV, 10CV and GLOOCV on HMDD v2.0, respectively. In addition, PMDAGS also achieves AUC values of 0.9366, 0.9377, and 0.9376 under 5CV, 10CV and GLOOCV on HMDD v3.2, respectively. According to the experimental results, we can conclude that PMDAGS outperforms other compared methods and can effectively predict miRNA-disease associations.

Repurposing non-pharmacological interventions for Alzheimer's disease through link prediction on biomedical literature

Non-pharmaceutical interventions (NPI) have great potential to improve cognitive function but limited investigation to discover NPI repurposing for Alzheimer's Disease (AD). This is the first study to develop an innovative framework to extract and represent NPI information from biomedical literature in a knowledge graph (KG), and train link prediction models to repurpose novel NPIs for AD prevention. We constructed a comprehensive KG, called ADInt, by extracting NPI information from biomedical literature. We used the previously-created SuppKG and NPI lexicon to identify NPI entities. Four KG embedding models (i.e., TransE, RotatE, DistMult and ComplEX) and two novel graph convolutional network models (i.e., R-GCN and CompGCN) were trained and compared to learn the representation of ADInt. Models were evaluated and compared on two test sets (time slice and clinical trial ground truth) and the best performing model was used to predict novel NPIs for AD. Discovery patterns were applied to generate mechanistic pathways for high scoring candidates. The ADInt has 162,212 nodes and 1,017,284 edges. R-GCN performed best in time slice (MR = 5.2054, Hits@10 = 0.8496) and clinical trial ground truth (MR = 3.4996, Hits@10 = 0.9192) test sets. After evaluation by domain experts, 10 novel dietary supplements and 10 complementary and integrative health were proposed from the score table calculated by R-GCN. Among proposed novel NPIs, we found plausible mechanistic pathways for photodynamic therapy and Choerospondias axillaris to prevent AD, and validated psychotherapy and manual therapy techniques using real-world data analysis. The proposed framework shows potential for discovering new NPIs for AD prevention and understanding their mechanistic pathways.