Graph Convolutional Network Research Articles

AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing.

Graph convolutional network (GCN) with the powerful capacity to explore graph-structural data has gained noticeable success in recent years. Nonetheless, most of the existing GCN-based models suffer from the notorious over-smoothing issue, owing to which shallow networks are extensively adopted. This may be problematic for complex graph datasets because a deeper GCN should be beneficial to propagating information across remote neighbors. Recent works have devoted effort to addressing over-smoothing problems, including establishing residual connection structure or fusing predictions from multilayer models. Because of the indistinguishable embeddings from deep layers, it is reasonable to generate more reliable predictions before conducting the combination of outputs from various layers. In light of this, we propose an alternating graph-regularized neural network (AGNN) composed of graph convolutional layer (GCL) and graph embedding layer (GEL). GEL is derived from the graph-regularized optimization containing Laplacian embedding term, which can alleviate the over-smoothing problem by periodic projection from the low-order feature space onto the high-order space. With more distinguishable features of distinct layers, an improved Adaboost strategy is utilized to aggregate outputs from each layer, which explores integrated embeddings of multi-hop neighbors. The proposed model is evaluated via a large number of experiments including performance comparison with some multilayer or multi-order graph neural networks, which reveals the superior performance improvement of AGNN compared with the state-of-the-art models.

Dynamic mode decomposition and short-time prediction of PM2.5 using the graph Neural Koopman network

Analyzing and accurately predicting the spatiotemporal dynamics of PM2.5 remain challenging. The existing spatiotemporal prediction approaches are associated with high model complexity and limited interpretability. Conventional methods combining Koopman theory and deep learning often neglect spatial correlations in spatiotemporal data. This study used the hourly PM2.5 dataset of the Beijing-Tianjin-Hebei region to reveal its spatiotemporal hierarchy using Koopman mode decomposition to identify the key dynamic modes. Furthermore, a Spatial Physics Constrained Learning (SPCL) model utilizing a graph representation learning method was proposed to combine the graph topological information of the PM2.5 spatial features with the Koopman feature function. The results showed that PM2.5 has growth, decay, and oscillation modes as well as daily, weekly, monthly, and yearly periods. SPCL achieved mean absolute error, root mean square error (RMSE), correlation r, and index of agreement values of 9.678, 13.922, 0.864, and 0.921, respectively. The average RMSE at 12 h improved by 16.1%, 12.7%, 0.9%, and 3.5% compared with using Long short-term Memory, Graph Convolutional Networks and Long Short-Term Memory Networks, Spatio-Temporal Graph Convolutional Networks, and Dynamic Spatiotemporal Graph Convolution Network, respectively. By discretizing the neural network hidden layers, the explanatory key of PM2.5 modes was elucidated, which demonstrated enhanced stability.

A geographic-semantic context-aware urban commuting flow prediction model using graph neural network

Urban commuting flow prediction is crucial for urban planning, transportation optimization, and supply chain management. Traditional models and machine learning solutions often fall short in capturing the complex dynamics of urban mobility, overlooking factors like spatial correlation and human mobility patterns. Recent deep learning advancements have shown promise by integrating spatial correlation through incorporating geographical adjacency. However, this approach may not fully capture spatial correlation, particularly the semantic adjacency effect of zones connected via public transportation lines, such as metro networks—a novel dimension overlooked in prior research. The metro station serves as a major transit hub, attracting passengers from various origins and destinations and correlating the flow between the connected zones and other zones within the metro network. Devising an optimized model to encapsulate these spatial correlations is another crucial area of research where scientists are actively seeking the most effective solutions. We propose a novel sequential hybrid approach leveraging graph-based learning, focusing on the underexplored impact of metro networks on commuting flow prediction. Our model integrates two types of adjacency—geographic and semantic—using Graph Convolutional Networks (GCNs) to embed geographic correlations among proximate zones and Graph Attention Networks (GATs) to incorporate semantic adjacency defined by metro line connectivity. Furthermore, our approach innovatively incorporates features directly from online maps, eliminating reliance on third-party resources and enhancing scalability and efficiency. We validate our model using real-world datasets from Montreal, Canada, comprising travel surveys and GPS trajectory types, totaling nearly 900,000 trip records. Through evaluation using established performance metrics such as MAE, RMSE, MAPE, and CPC, we demonstrate significant improvement in predictive accuracy compared to existing state-of-the-art models. Our research has practical implications for urban planning and infrastructure development, aiding policymakers and urban planners in analyzing the impact of new urban infrastructure on commuting flow dynamics and facilitating informed decisions regarding transportation and infrastructure planning.

Extending cutting tool remaining life through deep learning and laser shock peening remanufacturing techniques

Predicting and extending the remaining life of cutting tools during machining processes is crucial for sustainable manufacturing. Traditional prognosis methods often struggle to adapt to diverse working conditions throughout the machining process lifecycle. This paper introduced a comprehensive framework that effectively addressed the challenges by integrating multi-source data and using deep learning techniques. The system integrated power and vibration data collected from LGMazak VTC-16A and IRON MAN QM200 machines with the following innovations: (1) A standardized data fusion method was developed to integrate multi-source data sources, the hybrid graph convolutional network (GCN) with attention mechanisms was employed to improve the prognosis accuracy of cutting tool remaining life, best accuracy of 98.56% and average accuracy of 97.71% were achieved. (2) The optimization of laser shock peening (LSP) remanufacturing parameters using the bees algorithm showed good performance, a fitness value of 0.95 was achieved with convergence within 15 iterations. (3) Monitoring of the LSP remanufacturing process was designed based on sound and vibration data for optimal remanufacturing performance. (4) The remanufacturing approach in extending the remaining life of cutting tool was validated through FEA analysis and experimental testing, cutting tool life was extended by 29.32% to achieve a sustainable manufacturing process.

A Dual-Masked Deep Structural Clustering Network With Adaptive Bidirectional Information Delivery.

Structured clustering networks, which alleviate the oversmoothing issue by delivering hidden features from autoencoder (AE) to graph convolutional networks (GCNs), involve two shortcomings for the clustering task. For one thing, they used vanilla structure to learn clustering representations without considering feature and structure corruption; for another thing, they exhibit network degradation and vanishing gradient issues after stacking multilayer GCNs. In this article, we propose a clustering method called dual-masked deep structural clustering network (DMDSC) with adaptive bidirectional information delivery (ABID). Specifically, DMDSC enables generative self-supervised learning to mine deeper interstructure and interfeature correlations by simultaneously reconstructing corrupted structures and features. Furthermore, DMDSC develops an ABID module to establish an information transfer channel between each pairwise layer of AE and GCNs to alleviate the oversmoothing and vanishing gradient problems. Numerous experiments on six benchmark datasets have shown that the proposed DMDSC outperforms the most advanced deep clustering algorithms.

GraphCVAE: Uncovering cell heterogeneity and therapeutic target discovery through residual and contrastive learning.

Advancements in Spatial Transcriptomics (ST) technologies in recent years have transformed the analysis of tissue structure and function within spatial contexts. However, accurately identifying spatial domains remains challenging due to data sparsity and noise. Traditional clustering methods often fail to capture spatial dependencies, while spatial clustering methods struggle with batch effects and data integration. We introduce GraphCVAE, a model designed to enhance spatial domain identification by integrating spatial and morphological information, correcting batch effects, and managing heterogeneous data. GraphCVAE employs a multi-layer Graph Convolutional Network (GCN) and a variational autoencoder to improve the representation and integration of spatial information. Through contrastive learning, the model captures subtle differences between cell types and states. Extensive testing on various ST datasets demonstrates GraphCVAE's robustness and biological contributions. In the dorsolateral prefrontal cortex (DLPFC) dataset, it accurately delineates cortical layer boundaries. In glioblastoma, GraphCVAE reveals critical therapeutic targets such as TF and NFIB. In colorectal cancer, it explores the role of the extracellular matrix in colorectal cancer. The model's performance metrics consistently surpass existing methods, validating its effectiveness. GraphCVAE's advanced visualization capabilities further highlight its precision in resolving spatial structures, making it a powerful tool for spatial transcriptomics analysis and offering new insights into disease studies.

MAS-DGAT-Net: A dynamic graph attention network with multibranch feature extraction and staged fusion for EEG emotion recognition

In recent years, with the rise of deep learning technologies, EEG-based emotion recognition has garnered significant attention. However, most existing methods tend to focus on the spatiotemporal information of EEG signals while overlooking the potential topological information of brain regions. To address this issue, this paper proposes a dynamic graph attention network with multi-branch feature extraction and staged fusion (MAS-DGAT-Net), which integrates graph convolutional neural networks (GCN) for EEG emotion recognition. Specifically, the differential entropy (DE) features of EEG signals are first reconstructed into a correlation matrix using the Spearman correlation coefficient. Then, the brain-region connectivity-feature extraction (BCFE) module is employed to capture the brain connectivity features associated with emotional activation states. Meanwhile, this paper introduces a dual-branch cross-fusion feature extraction (CFFE) module, which consists of an attention-based cross-fusion feature extraction branch (A-CFFEB) and a cross-fusion feature extraction branch (CFFEB). A-CFFEB efficiently extracts key channel-frequency information from EEG features by using an attention mechanism and then fuses it with the output features from the BCFE. The fused features are subsequently input into the proposed dynamic graph attention module with a broad learning system (DGAT-BLS) to mine the brain connectivity feature information further. Finally, the deep features output by DGAT-BLS and CFFEB are combined for emotion classification. The proposed algorithm has been experimentally validated on SEED, SEED-IV, and DEAP datasets in subject-dependent and subject-independent settings, with the results confirming the model's effectiveness. The source code is publicly available at: https://github.com/cvmdsp/MAS-DGAT-Net

Cellular Network Traffic Prediction with Hybrid Graph Convolutional Recurrent Network

Cellular Network Traffic Prediction with Hybrid Graph Convolutional Recurrent Network

An improved graph convolutional neural network for EEG emotion recognition

An improved graph convolutional neural network for EEG emotion recognition

From technology opportunities to solutions generation via patent analysis: Application of machine learning-based link prediction

Technology convergence represents a significant mode of technological innovation that is widely prevalent across various industries. This innovative approach integrates multiple technologies to develop new integrated solutions, thereby fostering a competitive advantage for enterprises. Anticipating future potential technology convergence is of paramount importance for businesses. However, previous research has predominantly relied on the topological information of convergence networks, overlooking the nodal attributes and inter-nodal relationships that have an impact on the emergence of technology convergence. To enhance existing studies, this paper employs three types of features: node attributes and inter-node relationships based on the drivers of technology convergence, along with link prediction similarity indices. Additionally, we utilize Graph Convolutional Neural Network (GCN) for node embedding to leverage node attributes. Machine learning models are utilized for link prediction based on these features to identify potential technology opportunities. To guide research and development (R&D) efforts, we recommend high-value patents for each node using entropy weighting across five metrics that objectively quantify patent value, and transform patent abstracts into vectors using Doc2Vec. Patents with high similarity in abstract text between nodes are utilized to extract technical solutions and fuse ideas for technology convergence. A case study is conducted within the autonomous driving industry, leveraging comprehensive information including node attributes, inter-node relationships, and topology-based similarities to identify technology opportunities and guide the generation of R&D ideas through the convergence of technical solutions.

Cognitive Assessment of Scientific Creative Skill by Brain-Connectivity Analysis Using Graph Convolutional Interval Type-2 Fuzzy Network

Cognitive Assessment of Scientific Creative Skill by Brain-Connectivity Analysis Using Graph Convolutional Interval Type-2 Fuzzy Network

Long Term 5G Base Station Traffic Prediction Method Based on Spatial-Temporal Correlations

In the domain of 5G network management, accurately predicting traffic volumes at base stations remains a critical yet challenging endeavor, primarily due to the complexities inherent in the spatial and temporal data interactions. Current methods often fall short in effectively harnessing long-term trends and spatial interconnections among base stations. To bridge these gaps, this paper introduces the GCformer model, a novel approach that capitalizes on both spatial relationships and temporal patterns for multi-base station traffic prediction. Spatially, the proposed model employs graph convolutional networks to integrate diverse spatial information and construct insightful adjacency matrices that includes Euclidean distances and non-Euclidean distances (area types of base station locations and similarities in traffic flow among various stations), thereby enhancing the predictability of traffic dynamics. Temporally, the application of the Transformer's attention mechanism enables better capture of long-term relational dependencies in the temporal domain of 5G base station traffic data. Additionally, a time-variant optimization module is designed to establish diurnal cycle data for each base station's traffic, replacing the traditional positional encoding with a more nuanced model that improves the learning of historical data correlations. Empirical results from exhaustive case studies confirm the superiority of the GCformer model in forecasting traffic volumes. The GCformer exhibits a 4.01% improvement in mean squared error and a 3.37% enhancement in mean absolute error compared to the best-performing baseline model, showcasing its potential to significantly improve operational strategies in 5G networks.

A Fast and Robust Attention-Free Heterogeneous Graph Convolutional Network

A Fast and Robust Attention-Free Heterogeneous Graph Convolutional Network

Optimizing Hybrid Active–Passive Thermal Management of Prismatic Li‐Ion Batteries Using Phase Change Materials and Porous‐Filled Mini‐Channels

ABSTRACTTackling climate change is crucial, and electrifying the vehicular transportation sector is essential to reduce greenhouse gas emissions. Lithium‐ion (Li‐ion) batteries are highly efficient for electric vehicles (EVs) but face challenges such as thermal management, risk of thermal runaway, and high costs of lithium and cobalt. Overcoming these challenges is vital for the widespread adoption of hybrid and EVs. To overcome this drawback, this article proposed a large‐kernel attention graph convolutional network (LKAGCN) with leaf in wind optimization algorithm (LWOA) named as LKAGCN‐LWOA technique, which enhances the thermal management of prismatic Li‐ion batteries by integrating both active and passive cooling techniques. The system incorporates phase change materials (PCMs) with porous‐filled mini‐channels to regulate battery temperature effectively. The LKAGCN analyze thermal properties, battery conditions, and PCM characteristics to predict and optimize the thermal behavior of the battery pack using LWOA. The proposed methods tune the parameters of the hybrid thermal management system, ensuring efficient thermal regulation and improved performance. The proposed method is compared to various existing methods such as convolutional neural network (CNN), Taguchi method, and Finite element model (FEM).

A Controllability Reinforcement Learning Method for Pancreatic Cancer Biomarker Identification.

Pancreatic cancer is one of the most malignant cancers with rapid progression and poor prognosis. The use of transcriptional data can be effective in finding new biomarkers for pancreatic cancer. Many network-based methods used to identify cancer biomarkers are proposed, among which the combination of network controllability appears. However, most of the existing methods do not study RNA, rely on priori and mutations information, or can only achieve classification tasks. In this study, we propose a method combined Relational Graph Convolutional Network and Deep Q-Network called RDDriver to identify pancreatic cancer biomarkers based on multi-layer heterogeneous transcriptional regulation network. Firstly, we construct a regulation network containing long non-coding RNA, microRNA, and messenger RNA. Secondly, Relational Graph Convolutional Network is used to learn the node representation. Finally, we use the idea of Deep Q-Network to build a model, which score and prioritize each RNA with the Popov-Belevitch-Hautus criterion. We train RDDriver on three small simulated networks, and calculate the average score after applying the model parameters to the regulation networks separately. To demonstrate the effectiveness of the method, we perform experiments for comparison between RDDriver and other eight methods based on the approximate benchmark of three types cancer drivers RNAs.

D-MHGCN: An End-to-End Individual Behavioral Prediction Model Using Dual Multi-Hop Graph Convolutional Network.

Predicting individual behavior is a crucial area of research in neuroscience. Graph Neural Networks (GNNs), as powerful tools for extracting graph-structured features, are increasingly being utilized in various functional connectivity (FC) based behavioral prediction tasks. However, current predictive models primarily focus on enhancing GNNs' ability to extract features from FC networks while neglecting the importance of upstream individual network construction quality. This oversight results in constructed functional networks that fail to adequately represent individual behavioral capacity, thereby affecting the subsequent prediction accuracy. To address this issue, we proposed a new GNN-based behavioral prediction framework, named Dual Multi-Hop Graph Convolutional Network (D-MHGCN). Through the joint training of two GCNs, this framework integrates individual functional network construction and behavioral prediction into a unified optimization model. It allows the model to dynamically adjust the individual functional cortical parcellation according to the downstream tasks, thus creating task-aware, individual-specific FCNs that largely enhance its ability to predict behavior scores. Additionally, we employed multi-hop graph convolution layers instead of traditional single-hop methods in GCN to capture complex hierarchical connectivity patterns in brain networks. Our experimental evaluations, conducted on the large, public Human Connectome Project dataset, demonstrate that our proposed method outperforms existing methods in various behavioral prediction tasks. Moreover, it produces more functionally homogeneous cortical parcellation, showcasing its practical utility and effectiveness. Our work not only enhances the accuracy of individual behavioral prediction but also provides deeper insights into the neural mechanisms underlying individual differences in behavior.

Maui: Black-Box Edge Privacy Attack on Graph Neural Networks

Graphs are ubiquitous data structures with nodes representing objects and edges representing relationships between them. Graph Neural Networks (GNNs) have recently been proposed to study graph-structured data, but unfortunately, are susceptible to privacy leakage. This issue becomes more urgent as GNNs gain wide deployment in many real-world settings including social network analysis, bioinformatics, and cybersecurity. In this paper, we propose the first link inference attack that can compromise user data under the most difficult security settings, which we call Maui. We demonstrate that private edge information can be inferred by a malicious user with a black-box approach. Extensive experiments on six real-world datasets show our attacks conduct effective link inference attacks in various scopes. Our attack achieves significant performance improvements over the current state-of-the-art. When targeting 2-layer Graph Convolution Networks, for inferring edges of a single node, our attack outperforms the best existing method by 12.0%, increasing from 83.7% to 95.7%; when inferring edges of the entire graph, our attack achieves a 19.6% improvement, from 67.7% to 87.3%. Our results underscore the need for countermeasures against privacy attacks in GNNs, as they can reveal rich information about graph structures.

Research on Graph Multi-Attention Neural Network for Power System Transient Stability Assessment

Abstract Diagnosing the stability of power grids based on artificial intelligence technology is a research trend. The existing artificial intelligence stability analysis methods rely on a large number of fault case data, while the graph neural network method ignores the correlation characteristics of nodes themselves and the correlation of long-distance nodes. In order to solve the problems, the graph multi-attention neural network (GMANN) was proposed. The self-attention, which characterizes the correlation between different state quantities of a single node, is proposed, firstly. Then, long-distance association attention, which represents the correlation of distant nodes in the power grid, was proposed. The long-distance correlation attention and the adjacent correlation attention in graph attention network are fused to form a global attention that reflects the global importance of the power grid. The channel attention that characterizes the importance of different pooling methods of graph convolutional network is extracted and used to obtain the importance of different convolution operations. Finally, based on the multi-source attention fusion strategy, global attention and channel attention are embedded in the graph attention neural network to form a multi-level evaluation model to achieve power grid stability evaluation efficiently guided by multiple attentions. The proposed GMANN is verified based on simulated fault cases obtained from the 10-machine 39-node system in New England. The results show that the accuracy of the GMANN can reach 97.34%, which is better than other methods. And the missed judgment rate of important indicators is significantly better than other methods.

EEG-Based Auditory Attention Detection With Spiking Graph Convolutional Network

EEG-Based Auditory Attention Detection With Spiking Graph Convolutional Network

Anti-symmetric framework for balanced learning of protein-protein interactions.

Protein-protein interactions (PPIs) are essential for the regulation and facilitation of virtually all biological processes. Computational tools, particularly those based on deep learning, are preferred for the efficient prediction of PPIs. Despite recent progress, two challenges remain unresolved: (i) the imbalanced nature of PPI characteristics is often ignored and (ii) there exists a high computational cost associated with capturing long-range dependencies within protein data, typically exhibiting quadratic complexity relative to the length of the protein sequence. Here, we propose an anti-symmetric graph learning model, BaPPI, for the balanced prediction of PPIs and extrapolation of the involved patterns in PPI network. In BaPPI, the contextualized information of protein data is efficiently handled by an attention-free mechanism formed by recurrent convolution operator. The anti-symmetric graph convolutional network is employed to model the uneven distribution within PPI networks, aiming to learn a more robust and balanced representation of the relationships between proteins. Ultimately, the model is updated using asymmetric loss. The experimental results on classical baseline datasets demonstrate that BaPPI outperforms four state-of-the-art PPI prediction methods. In terms of Micro-F1, BaPPI exceeds the second-best method by 6.5% on SHS27K and 5.3% on SHS148K. Further analysis of the generalization ability and patterns of predicted PPIs also demonstrates our model's generalizability and robustness to the imbalanced nature of PPI datasets. The source code of this work is publicly available at https://github.com/ttan6729/BaPPI.