The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security threats.Intrusion detection systems are cr...The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security threats.Intrusion detection systems are crucial to network security,playing a pivotal role in safeguarding networks from potential threats.However,in the context of an evolving landscape of sophisticated and elusive attacks,existing intrusion detection methodologies often overlook critical aspects such as changes in network topology over time and interactions between hosts.To address these issues,this paper proposes a real-time network intrusion detection method based on graph neural networks.The proposedmethod leverages the advantages of graph neural networks and employs a straightforward graph construction method to represent network traffic as dynamic graph-structured data.Additionally,a graph convolution operation with a multi-head attention mechanism is utilized to enhance the model’s ability to capture the intricate relationships within the graph structure comprehensively.Furthermore,it uses an integrated graph neural network to address dynamic graphs’structural and topological changes at different time points and the challenges of edge embedding in intrusion detection data.The edge classification problem is effectively transformed into node classification by employing a line graph data representation,which facilitates fine-grained intrusion detection tasks on dynamic graph node feature representations.The efficacy of the proposed method is evaluated using two commonly used intrusion detection datasets,UNSW-NB15 and NF-ToN-IoT-v2,and results are compared with previous studies in this field.The experimental results demonstrate that our proposed method achieves 99.3%and 99.96%accuracy on the two datasets,respectively,and outperforms the benchmark model in several evaluation metrics.展开更多
The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to u...The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.展开更多
Recent advances in statistical physics highlight the significant potential of machine learning for phase transition recognition.This study introduces a deep learning framework based on graph neural network to investig...Recent advances in statistical physics highlight the significant potential of machine learning for phase transition recognition.This study introduces a deep learning framework based on graph neural network to investigate non-equilibrium phase transitions,specifically focusing on the directed percolation process.By converting lattices with varying dimensions and connectivity schemes into graph structures and embedding the temporal evolution of the percolation process into node features,our approach enables unified analysis across diverse systems.The framework utilizes a multi-layer graph attention mechanism combined with global pooling to autonomously extract critical features from local dynamics to global phase transition signatures.The model successfully predicts percolation thresholds without relying on lattice geometry,demonstrating its robustness and versatility.Our approach not only offers new insights into phase transition studies but also provides a powerful tool for analyzing complex dynamical systems across various domains.展开更多
The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oi...The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism.Based on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.展开更多
Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean...Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.展开更多
With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engi...With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engineering. As one of the high-precision representative algorithms, the high-order Discontinuous Galerkin Method (DGM) has not only attracted widespread attention from scholars in the CFD research community, but also received strong development. However, when DGM is extended to high-speed aerodynamic flow field calculations, non-physical numerical Gibbs oscillations near shock waves often significantly affect the numerical accuracy and even cause calculation failure. Data driven approaches based on machine learning techniques can be used to learn the characteristics of Gibbs noise, which motivates us to use it in high-speed DG applications. To achieve this goal, labeled data need to be generated in order to train the machine learning models. This paper proposes a new method for denoising modeling of Gibbs phenomenon using a machine learning technique, the zero-shot learning strategy, to eliminate acquiring large amounts of CFD data. The model adopts a graph convolutional network combined with graph attention mechanism to learn the denoising paradigm from synthetic Gibbs noise data and generalize to DGM numerical simulation data. Numerical simulation results show that the Gibbs denoising model proposed in this paper can suppress the numerical oscillation near shock waves in the high-order DGM. Our work automates the extension of DGM to high-speed aerodynamic flow field calculations with higher generalization and lower cost.展开更多
Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning mode...Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.展开更多
We study a mathematical model of biological neuronal networks composed by any finite number N ≥ 2 of non-necessarily identical cells. The model is a deterministic dynamical system governed by finite-dimensional impul...We study a mathematical model of biological neuronal networks composed by any finite number N ≥ 2 of non-necessarily identical cells. The model is a deterministic dynamical system governed by finite-dimensional impulsive differential equations. The statical structure of the network is described by a directed and weighted graph whose nodes are certain subsets of neurons, and whose edges are the groups of synaptical connections among those subsets. First, we prove that among all the possible networks such as their respective graphs are mutually isomorphic, there exists a dynamical optimum. This optimal network exhibits the richest dynamics: namely, it is capable to show the most diverse set of responses (i.e. orbits in the future) under external stimulus or signals. Second, we prove that all the neurons of a dynamically optimal neuronal network necessarily satisfy Dale’s Principle, i.e. each neuron must be either excitatory or inhibitory, but not mixed. So, Dale’s Principle is a mathematical necessary consequence of a theoretic optimization process of the dynamics of the network. Finally, we prove that Dale’s Principle is not sufficient for the dynamical optimization of the network.展开更多
Session-based Recommendation(SBR)aims to accurately recom-mend a list of items to users based on anonymous historical session sequences.Existing methods for SBR suffer from several limitations:SBR based on Graph Neura...Session-based Recommendation(SBR)aims to accurately recom-mend a list of items to users based on anonymous historical session sequences.Existing methods for SBR suffer from several limitations:SBR based on Graph Neural Network often has information loss when constructing session graphs;Inadequate consideration is given to influencing factors,such as item price,and users’dynamic interest evolution is not taken into account.A new session recommendation model called Price-aware Session-based Recommendation(PASBR)is proposed to address these limitations.PASBR constructs session graphs by information lossless approaches to fully encode the original session information,then introduces item price as a new factor and models users’price tolerance for various items to influence users’preferences.In addition,PASBR proposes a new method to encode user intent at the item category level and tries to capture the dynamic interest of users over time.Finally,PASBR fuses the multi-perspective features to generate the global representation of users and make a prediction.Specifically,the intent,the short-term and long-term interests,and the dynamic interests of a user are combined.Experiments on two real-world datasets show that PASBR can outperform representative baselines for SBR.展开更多
Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics s...Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics simulations. Here,we present a physical information-enhanced graph neural network(PIENet) to simulate and predict the evolution of phase separation. The accuracy of our model in predicting particle positions is improved by 40.3% and 51.77% compared with CNN and SVM respectively. Moreover, we design an order parameter based on local density to measure the evolution of phase separation and analyze the systematic changes with different repulsion coefficients and different Schmidt numbers.The results demonstrate that our model can achieve long-term accurate predictions of order parameters without requiring complex handcrafted features. These results prove that graph neural networks can become new tools and methods for predicting the structure and properties of complex physical systems.展开更多
Accurate significant wave height(SWH)prediction is essential for the development and utilization of wave energy.Deep learning methods such as recurrent and convolutional neural networks have achieved good results in S...Accurate significant wave height(SWH)prediction is essential for the development and utilization of wave energy.Deep learning methods such as recurrent and convolutional neural networks have achieved good results in SWH forecasting.However,these methods do not adapt well to dynamic seasonal variations in wave data.In this study,we propose a novel method—the spatiotemporal dynamic graph(STDG)neural network.This method predicts the SWH of multiple nodes based on dynamic graph modeling and multi-characteristic fusion.First,considering the dynamic seasonal variations in the wave direction over time,the network models wave dynamic spatial dependencies from long-and short-term pattern perspectives.Second,to correlate multiple characteristics with SWH,the network introduces a cross-characteristic transformer to effectively fuse multiple characteristics.Finally,we conducted experiments on two datasets from the South China Sea and East China Sea to validate the proposed method and compared it with five prediction methods in the three categories.The experimental results show that the proposed method achieves the best performance at all predictive scales and has greater advantages for extreme value prediction.Furthermore,an analysis of the dynamic graph shows that the proposed method captures the seasonal variation mechanism of the waves.展开更多
Graph neural networks(GNNs)have emerged as a powerful tool for effectively mining and learning from graphstructured data,with applications spanning numerous domains.However,most research focuses on static graphs,negle...Graph neural networks(GNNs)have emerged as a powerful tool for effectively mining and learning from graphstructured data,with applications spanning numerous domains.However,most research focuses on static graphs,neglecting the dynamic nature of real-world networks where topologies and attributes evolve over time.By integrating sequence modeling modules into traditional GNN architectures,dynamic GNNs aim to bridge this gap,capturing the inherent temporal dependencies of dynamic graphs for a more authentic depiction of complex networks.This paper provides a comprehensive review of the fundamental concepts,key techniques,and stateof-the-art dynamic GNN models.We present the mainstream dynamic GNN models in detail and categorize models based on how temporal information is incorporated.We also discuss large-scale dynamic GNNs and pre-training techniques.Although dynamic GNNs have shown superior performance,challenges remain in scalability,handling heterogeneous information,and lack of diverse graph datasets.The paper also discusses possible future directions,such as adaptive and memory-enhanced models,inductive learning,and theoretical analysis.展开更多
Mesozooplankton are critical components of marine ecosystems,acting as key intermediaries between primary producers and higher trophic levels by grazing on phytoplankton and influencing fish populations.They play pivo...Mesozooplankton are critical components of marine ecosystems,acting as key intermediaries between primary producers and higher trophic levels by grazing on phytoplankton and influencing fish populations.They play pivotal roles in the pelagic food web and export production,affecting the biogeochemical cycling of carbon and nutrients.Therefore,accurately modeling and visualizing mesozooplankton community dynamics is essential for understanding marine ecosystem patterns and informing effective management strategies.However,modeling these dynamics remains challenging due to the complex interplay among physical,chemical,and biological factors,and the detailed parameterization and feedback mechanisms are not fully understood in theory-driven models.Graph neural network(GNN)models offer a promising approach to forecast multivariate features and define correlations among input variables.The high interpretive power of GNNs provides deep insights into the structural relationships among variables,serving as a connection matrix in deep learning algorithms.However,there is insufficient understanding of how interactions between input variables affect model outputs during training.Here we investigate how the graph structure of ecosystem dynamics used to train GNN models affects their forecasting accuracy for mesozooplankton species.We find that forecasting accuracy is closely related to interactions within ecosystem dynamics.Notably,increasing the number of nodes does not always enhance model performance;closely connected species tend to produce similar forecasting outputs in terms of trend and peak timing.Therefore,we demonstrate that incorporating the graph structure of ecosystem dynamics can improve the accuracy of mesozooplankton modeling by providing influential information about species of interest.These findings will provide insights into the influential factors affecting mesozooplankton species and emphasize the importance of constructing appropriate graphs for forecasting these species.展开更多
Recommendation algorithms regard user-item interaction as a sequence to capture the user’s short-term preferences,but conventional algorithms cannot capture information of constantly-changing user interest in complex...Recommendation algorithms regard user-item interaction as a sequence to capture the user’s short-term preferences,but conventional algorithms cannot capture information of constantly-changing user interest in complex contexts.In these years,combining the knowledge graphwith sequential recommendation has gained momentum.The advantages of knowledge graph-based recommendation systems are that more semantic associations can improve the accuracy of recommendations,rich association facts can increase the diversity of recommendations,and complex relational paths can hence the interpretability of recommendations.But the information in the knowledge graph,such as entities and relations,often fails to be fully utilized and high-order connectivity is unattainable in graph modelling in knowledge graph-based sequential recommender systems.To address the above problems,a knowledge graph-based sequential recommendation algorithm that combines the gated recurrent unit and the graph neural network(KGSRGG)is proposed in the present work.Specifically,entity disambiguation in the knowledge graph is performed on the preprocessing layer;on the embedding layer,the TransR embedding technique is employed to process the user information,item information and the entities and relations in the knowledge graph;on the aggregation layer,the information is aggregated by graph convolutional neural networks and residual connections;and at last,on the sequence layer,a bi-directional gated recurrent unit(Bi-GRU)is utilized to model the user’s sequential preferences.The research results showed that this newalgorithm performed better than existing sequential recommendation algorithms on the MovieLens-1M and Book-Crossing datasets,as measured by five evaluation indicators.展开更多
Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,...Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.展开更多
Purpose-Human behavior recognition poses a pivotal challenge in intelligent computing and cybernetics,significantly impacting engineering and management systems.With the rapid advancement of autonomous systems and int...Purpose-Human behavior recognition poses a pivotal challenge in intelligent computing and cybernetics,significantly impacting engineering and management systems.With the rapid advancement of autonomous systems and intelligent manufacturing,there is an increasing demand for precise and efficient human behavior recognition technologies.However,traditional methods often suffer from insufficient accuracy and limited generalization ability when dealing with complex and diverse human actions.Therefore,this study aims to enhance the precision of human behavior recognition by proposing an innovative framework,dynamic graph convolutional networks with multi-scale position attention(DGCN-MPA)to sup.Design/methodology/approach-The primary applications are in autonomous systems and intelligent manufacturing.The main objective of this study is to develop an efficient human behavior recognition framework that leverages advanced techniques to improve the prediction and interpretation of human actions.This framework aims to address the shortcomings of existing methods in handling the complexity and variability of human actions,providing more reliable and precise solutions for practical applications.The proposed DGCN-MPA framework integrates the strengths of convolutional neural networks and graph-based models.It innovatively incorporates wavelet packet transform to extract time-frequency characteristics and a MPA module to enhance the representation of skeletal node positions.The core innovation lies in the fusion of dynamic graph convolution with hierarchical attention mechanisms,which selectively attend to relevant features and spatial relationships,adjusting their importance across scales to address the variability in human actions.Findings-To validate the effectiveness of the DGCN-MPA framework,rigorous evaluations were conducted on benchmark datasets such as NTU-RGBþD and Kinetics-Skeleton.The results demonstrate that the framework achieves an F1 score of 62.18%and an accuracy of 75.93%on NTU-RGBþD and an F1 score of 69.34%and an accuracy of 76.86%on Kinetics-Skeleton,outperforming existing models.These findings underscore the framework’s capability to capture complex behavior patterns with high precision.Originality/value-By introducing a dynamic graph convolutional approach combined with multi-scale position attention mechanisms,this study represents a significant advancement in human behavior recognition technologies.The innovative design and superior performance of the DGCN-MPA framework contribute to its potential for real-world applications,particularly in integrating behavior recognition into engineering and autonomous systems.In the future,this framework has the potential to further propel the development of intelligent computing,cybernetics and related fields.展开更多
Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has ...Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has a lower computational cost but requires accurate force fields to achieve chemical accuracy.In this work,we develop a symmetry-adapted graph neural network framework called the molecular dynamics graph neural network(MDGNN)to construct force fields automatically for molecular dynamics simulations for both molecules and crystals.This architecture consistently preserves translation,rotation,and permutation invariance in the simulations.We also propose a new feature engineering method that includes high-order terms of interatomic distances and demonstrate that the MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics.In addition,we demonstrate that force fields constructed by the proposed model have good transferability.The MDGNN is thus an efficient and promising option for performing molecular dynamics simulations of large-scale systems with high accuracy.展开更多
Dynamic graph neural networks(DGNNs)have demonstrated their extraordinary value in many practical applications.Nevertheless,the vulnerability of DNNs is a serious hidden danger as a small disturbance added to the mode...Dynamic graph neural networks(DGNNs)have demonstrated their extraordinary value in many practical applications.Nevertheless,the vulnerability of DNNs is a serious hidden danger as a small disturbance added to the model can markedly reduce its performance.At the same time,current adversarial attack schemes are implemented on static graphs,and the variability of attack models prevents these schemes from transferring to dynamic graphs.In this paper,we use the diffused attack of node injection to attack the DGNNs,and first propose the node injection attack based on structural fragility against DGNNs,named Structural Fragility-based Dynamic Graph Node Injection Attack(SFIA).SFIA firstly determines the target time based on the period weight.Then,it introduces a structural fragile edge selection strategy to establish the target nodes set and link them with the malicious node using serial inject.Finally,an optimization function is designed to generate adversarial features for malicious nodes.Experiments on datasets from four different fields show that SFIA is significantly superior to many comparative approaches.When the graph is injected with 1%of the original total number of nodes through SFIA,the link prediction Recall and MRR of the target DGNN link decrease by 17.4%and 14.3%respectively,and the accuracy of node classification decreases by 8.7%.展开更多
The integration of Dynamic Graph Neural Networks(DGNNs)with Smart Manufacturing is crucial as it enables real-time,adaptive analysis of complex data,leading to enhanced predictive accuracy and operational efficiency i...The integration of Dynamic Graph Neural Networks(DGNNs)with Smart Manufacturing is crucial as it enables real-time,adaptive analysis of complex data,leading to enhanced predictive accuracy and operational efficiency in industrial environments.To address the problem of poor combination effect and low prediction accuracy of current dynamic graph neural networks in spatial and temporal domains,and over-smoothing caused by traditional graph neural networks,a dynamic graph prediction method based on spatiotemporal binary-domain recurrent-like architecture is proposed:Binary Domain Graph Neural Network(BDGNN).The proposed model begins by utilizing a modified Graph Convolutional Network(GCN)without an activation function to extract meaningful graph topology information,ensuring non-redundant embeddings.In the temporal domain,Recurrent Neural Network(RNN)and residual systems are employed to facilitate the transfer of dynamic graph node information between learner weights,aiming to mitigate the impact of noise within the graph sequence.In the spatial domain,the AdaBoost(Adaptive Boosting)algorithm is applied to replace the traditional approach of stacking layers in a graph neural network.This allows for the utilization of multiple independent graph learners,enabling the extraction of higher-order neighborhood information and alleviating the issue of over-smoothing.The efficacy of BDGNN is evaluated through a series of experiments,with performance metrics including Mean Average Precision(MAP)and Mean Reciprocal Rank(MRR)for link prediction tasks,as well as metrics for traffic speed regression tasks across diverse test sets.Compared with other models,the better experiments results demonstrate that BDGNN model can not only better integrate the connection between time and space information,but also extract higher-order neighbor information to alleviate the over-smoothing phenomenon of the original GCN.展开更多
文摘The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security threats.Intrusion detection systems are crucial to network security,playing a pivotal role in safeguarding networks from potential threats.However,in the context of an evolving landscape of sophisticated and elusive attacks,existing intrusion detection methodologies often overlook critical aspects such as changes in network topology over time and interactions between hosts.To address these issues,this paper proposes a real-time network intrusion detection method based on graph neural networks.The proposedmethod leverages the advantages of graph neural networks and employs a straightforward graph construction method to represent network traffic as dynamic graph-structured data.Additionally,a graph convolution operation with a multi-head attention mechanism is utilized to enhance the model’s ability to capture the intricate relationships within the graph structure comprehensively.Furthermore,it uses an integrated graph neural network to address dynamic graphs’structural and topological changes at different time points and the challenges of edge embedding in intrusion detection data.The edge classification problem is effectively transformed into node classification by employing a line graph data representation,which facilitates fine-grained intrusion detection tasks on dynamic graph node feature representations.The efficacy of the proposed method is evaluated using two commonly used intrusion detection datasets,UNSW-NB15 and NF-ToN-IoT-v2,and results are compared with previous studies in this field.The experimental results demonstrate that our proposed method achieves 99.3%and 99.96%accuracy on the two datasets,respectively,and outperforms the benchmark model in several evaluation metrics.
文摘The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.
基金supported by the Fund from the Science and Technology Department of Henan Province,China(Grant Nos.222102210233 and 232102210064)the National Natural Science Foundation of China(Grant Nos.62373169 and 72474086)+5 种基金the Young and Midcareer Academic Leader of Jiangsu Province,China(Grant No.Qinglan Project in 2024)the National Statistical Science Research Project(Grant No.2022LZ03)Shaanxi Provincial Soft Science Project(Grant No.2022KRM111)Shaanxi Provincial Social Science Foundation(Grant No.2022R016)the Special Project for Philosophical and Social Sciences Research in Shaanxi Province,China(Grant No.2024QN018)the Fund from the Henan Office of Philosophy and Social Science(Grant No.2023CJJ112).
文摘Recent advances in statistical physics highlight the significant potential of machine learning for phase transition recognition.This study introduces a deep learning framework based on graph neural network to investigate non-equilibrium phase transitions,specifically focusing on the directed percolation process.By converting lattices with varying dimensions and connectivity schemes into graph structures and embedding the temporal evolution of the percolation process into node features,our approach enables unified analysis across diverse systems.The framework utilizes a multi-layer graph attention mechanism combined with global pooling to autonomously extract critical features from local dynamics to global phase transition signatures.The model successfully predicts percolation thresholds without relying on lattice geometry,demonstrating its robustness and versatility.Our approach not only offers new insights into phase transition studies but also provides a powerful tool for analyzing complex dynamical systems across various domains.
基金the support of the National Nature Science Foundation of China(No.52074336)Emerging Big Data Projects of Sinopec Corporation(No.20210918084304712)。
文摘The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism.Based on the material balance and physical information, the overall connectivity from the injection wells,through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.
基金The National Key R&D Program of China under contract No.2021YFC3101603.
文摘Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.
基金co-supported by the Aeronautical Science Foundation of China(Nos.2018ZA52002,2019ZA052011).
文摘With the availability of high-performance computing technology and the development of advanced numerical simulation methods, Computational Fluid Dynamics (CFD) is becoming more and more practical and efficient in engineering. As one of the high-precision representative algorithms, the high-order Discontinuous Galerkin Method (DGM) has not only attracted widespread attention from scholars in the CFD research community, but also received strong development. However, when DGM is extended to high-speed aerodynamic flow field calculations, non-physical numerical Gibbs oscillations near shock waves often significantly affect the numerical accuracy and even cause calculation failure. Data driven approaches based on machine learning techniques can be used to learn the characteristics of Gibbs noise, which motivates us to use it in high-speed DG applications. To achieve this goal, labeled data need to be generated in order to train the machine learning models. This paper proposes a new method for denoising modeling of Gibbs phenomenon using a machine learning technique, the zero-shot learning strategy, to eliminate acquiring large amounts of CFD data. The model adopts a graph convolutional network combined with graph attention mechanism to learn the denoising paradigm from synthetic Gibbs noise data and generalize to DGM numerical simulation data. Numerical simulation results show that the Gibbs denoising model proposed in this paper can suppress the numerical oscillation near shock waves in the high-order DGM. Our work automates the extension of DGM to high-speed aerodynamic flow field calculations with higher generalization and lower cost.
基金Youth Innovation Promotion Association CAS,Grant/Award Number:2021103Strategic Priority Research Program of Chinese Academy of Sciences,Grant/Award Number:XDC02060500。
文摘Appropriately characterising the mixed space-time relations of the contagion process caused by hybrid space and time factors remains the primary challenge in COVID-19 forecasting.However,in previous deep learning models for epidemic forecasting,spatial and temporal variations are captured separately.A unified model is developed to cover all spatio-temporal relations.However,this measure is insufficient for modelling the complex spatio-temporal relations of infectious disease transmission.A dynamic adaptive spatio-temporal graph network(DASTGN)is proposed based on attention mechanisms to improve prediction accuracy.In DASTGN,complex spatio-temporal relations are depicted by adaptively fusing the mixed space-time effects and dynamic space-time dependency structure.This dual-scale model considers the time-specific,space-specific,and direct effects of the propagation process at the fine-grained level.Furthermore,the model characterises impacts from various space-time neighbour blocks under time-varying interventions at the coarse-grained level.The performance comparisons on the three COVID-19 datasets reveal that DASTGN achieves state-of-the-art results with a maximum improvement of 17.092%in the root mean-square error and 11.563%in the mean absolute error.Experimental results indicate that the mechanisms of designing DASTGN can effectively detect some spreading characteristics of COVID-19.The spatio-temporal weight matrices learned in each proposed module reveal diffusion patterns in various scenarios.In conclusion,DASTGN has successfully captured the dynamic spatio-temporal variations of COVID-19,and considering multiple dynamic space-time relationships is essential in epidemic forecasting.
文摘We study a mathematical model of biological neuronal networks composed by any finite number N ≥ 2 of non-necessarily identical cells. The model is a deterministic dynamical system governed by finite-dimensional impulsive differential equations. The statical structure of the network is described by a directed and weighted graph whose nodes are certain subsets of neurons, and whose edges are the groups of synaptical connections among those subsets. First, we prove that among all the possible networks such as their respective graphs are mutually isomorphic, there exists a dynamical optimum. This optimal network exhibits the richest dynamics: namely, it is capable to show the most diverse set of responses (i.e. orbits in the future) under external stimulus or signals. Second, we prove that all the neurons of a dynamically optimal neuronal network necessarily satisfy Dale’s Principle, i.e. each neuron must be either excitatory or inhibitory, but not mixed. So, Dale’s Principle is a mathematical necessary consequence of a theoretic optimization process of the dynamics of the network. Finally, we prove that Dale’s Principle is not sufficient for the dynamical optimization of the network.
文摘Session-based Recommendation(SBR)aims to accurately recom-mend a list of items to users based on anonymous historical session sequences.Existing methods for SBR suffer from several limitations:SBR based on Graph Neural Network often has information loss when constructing session graphs;Inadequate consideration is given to influencing factors,such as item price,and users’dynamic interest evolution is not taken into account.A new session recommendation model called Price-aware Session-based Recommendation(PASBR)is proposed to address these limitations.PASBR constructs session graphs by information lossless approaches to fully encode the original session information,then introduces item price as a new factor and models users’price tolerance for various items to influence users’preferences.In addition,PASBR proposes a new method to encode user intent at the item category level and tries to capture the dynamic interest of users over time.Finally,PASBR fuses the multi-perspective features to generate the global representation of users and make a prediction.Specifically,the intent,the short-term and long-term interests,and the dynamic interests of a user are combined.Experiments on two real-world datasets show that PASBR can outperform representative baselines for SBR.
基金Project supported by the National Natural Science Foundation of China(Grant No.11702289)the Key Core Technology and Generic Technology Research and Development Project of Shanxi Province,China(Grant No.2020XXX013)。
文摘Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics simulations. Here,we present a physical information-enhanced graph neural network(PIENet) to simulate and predict the evolution of phase separation. The accuracy of our model in predicting particle positions is improved by 40.3% and 51.77% compared with CNN and SVM respectively. Moreover, we design an order parameter based on local density to measure the evolution of phase separation and analyze the systematic changes with different repulsion coefficients and different Schmidt numbers.The results demonstrate that our model can achieve long-term accurate predictions of order parameters without requiring complex handcrafted features. These results prove that graph neural networks can become new tools and methods for predicting the structure and properties of complex physical systems.
基金The National Key R&D Program of China under contract No.2021YFC3101604。
文摘Accurate significant wave height(SWH)prediction is essential for the development and utilization of wave energy.Deep learning methods such as recurrent and convolutional neural networks have achieved good results in SWH forecasting.However,these methods do not adapt well to dynamic seasonal variations in wave data.In this study,we propose a novel method—the spatiotemporal dynamic graph(STDG)neural network.This method predicts the SWH of multiple nodes based on dynamic graph modeling and multi-characteristic fusion.First,considering the dynamic seasonal variations in the wave direction over time,the network models wave dynamic spatial dependencies from long-and short-term pattern perspectives.Second,to correlate multiple characteristics with SWH,the network introduces a cross-characteristic transformer to effectively fuse multiple characteristics.Finally,we conducted experiments on two datasets from the South China Sea and East China Sea to validate the proposed method and compared it with five prediction methods in the three categories.The experimental results show that the proposed method achieves the best performance at all predictive scales and has greater advantages for extreme value prediction.Furthermore,an analysis of the dynamic graph shows that the proposed method captures the seasonal variation mechanism of the waves.
基金supported in part by National Science and Technology Major Project(2022ZD0114802)by National Natural Science Foundation of China(Grant Nos.U2241212,61932001)+4 种基金by Beijing Natural Science Foundation(No.4222028)by Beijing Outstanding Young Scientist Program(No.BJJWZYJH012019100020098)by Alibaba Group through Alibaba Innovative Research Program,and by Huawei-Renmin University joint program on Information Retrievalsupport provided by the fund for building world-class universities(disciplines)of Renmin University of China,by Engineering Research Center of Next-Generation Intelligent Search and Recommendation,Ministry of Education,Intelligent Social Governance Interdisciplinary Platform,Major Innovation&Planning Interdisciplinary Platform for the“Double-First Class”Initiative,Public Policy and Decision-making Research Lab,and Public Computing Cloud,Renmin University of ChinaBeijing Key Laboratory of Big Data Management and Analysis Methods,MOE Key Lab of Data Engineering and Knowledge Engineering,and Pazhou Laboratory(Huangpu),Guangzhou,Guangdong 510555,China.
文摘Graph neural networks(GNNs)have emerged as a powerful tool for effectively mining and learning from graphstructured data,with applications spanning numerous domains.However,most research focuses on static graphs,neglecting the dynamic nature of real-world networks where topologies and attributes evolve over time.By integrating sequence modeling modules into traditional GNN architectures,dynamic GNNs aim to bridge this gap,capturing the inherent temporal dependencies of dynamic graphs for a more authentic depiction of complex networks.This paper provides a comprehensive review of the fundamental concepts,key techniques,and stateof-the-art dynamic GNN models.We present the mainstream dynamic GNN models in detail and categorize models based on how temporal information is incorporated.We also discuss large-scale dynamic GNNs and pre-training techniques.Although dynamic GNNs have shown superior performance,challenges remain in scalability,handling heterogeneous information,and lack of diverse graph datasets.The paper also discusses possible future directions,such as adaptive and memory-enhanced models,inductive learning,and theoretical analysis.
基金supported by the Ministry of Science and ICT(MSIT)through a Sejong Science Fellowship funded by the National Research Foundation of Korea(NRF)(No.2022R1C1C2003649).
文摘Mesozooplankton are critical components of marine ecosystems,acting as key intermediaries between primary producers and higher trophic levels by grazing on phytoplankton and influencing fish populations.They play pivotal roles in the pelagic food web and export production,affecting the biogeochemical cycling of carbon and nutrients.Therefore,accurately modeling and visualizing mesozooplankton community dynamics is essential for understanding marine ecosystem patterns and informing effective management strategies.However,modeling these dynamics remains challenging due to the complex interplay among physical,chemical,and biological factors,and the detailed parameterization and feedback mechanisms are not fully understood in theory-driven models.Graph neural network(GNN)models offer a promising approach to forecast multivariate features and define correlations among input variables.The high interpretive power of GNNs provides deep insights into the structural relationships among variables,serving as a connection matrix in deep learning algorithms.However,there is insufficient understanding of how interactions between input variables affect model outputs during training.Here we investigate how the graph structure of ecosystem dynamics used to train GNN models affects their forecasting accuracy for mesozooplankton species.We find that forecasting accuracy is closely related to interactions within ecosystem dynamics.Notably,increasing the number of nodes does not always enhance model performance;closely connected species tend to produce similar forecasting outputs in terms of trend and peak timing.Therefore,we demonstrate that incorporating the graph structure of ecosystem dynamics can improve the accuracy of mesozooplankton modeling by providing influential information about species of interest.These findings will provide insights into the influential factors affecting mesozooplankton species and emphasize the importance of constructing appropriate graphs for forecasting these species.
文摘Recommendation algorithms regard user-item interaction as a sequence to capture the user’s short-term preferences,but conventional algorithms cannot capture information of constantly-changing user interest in complex contexts.In these years,combining the knowledge graphwith sequential recommendation has gained momentum.The advantages of knowledge graph-based recommendation systems are that more semantic associations can improve the accuracy of recommendations,rich association facts can increase the diversity of recommendations,and complex relational paths can hence the interpretability of recommendations.But the information in the knowledge graph,such as entities and relations,often fails to be fully utilized and high-order connectivity is unattainable in graph modelling in knowledge graph-based sequential recommender systems.To address the above problems,a knowledge graph-based sequential recommendation algorithm that combines the gated recurrent unit and the graph neural network(KGSRGG)is proposed in the present work.Specifically,entity disambiguation in the knowledge graph is performed on the preprocessing layer;on the embedding layer,the TransR embedding technique is employed to process the user information,item information and the entities and relations in the knowledge graph;on the aggregation layer,the information is aggregated by graph convolutional neural networks and residual connections;and at last,on the sequence layer,a bi-directional gated recurrent unit(Bi-GRU)is utilized to model the user’s sequential preferences.The research results showed that this newalgorithm performed better than existing sequential recommendation algorithms on the MovieLens-1M and Book-Crossing datasets,as measured by five evaluation indicators.
文摘Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.
基金supported by the Guangxi University Young and middle-aged Teachers Basic Ability Improvement Project(No.:2023KY1692)Guilin University of Information Technology 2022 Research Project(No.:XJ202207)。
文摘Purpose-Human behavior recognition poses a pivotal challenge in intelligent computing and cybernetics,significantly impacting engineering and management systems.With the rapid advancement of autonomous systems and intelligent manufacturing,there is an increasing demand for precise and efficient human behavior recognition technologies.However,traditional methods often suffer from insufficient accuracy and limited generalization ability when dealing with complex and diverse human actions.Therefore,this study aims to enhance the precision of human behavior recognition by proposing an innovative framework,dynamic graph convolutional networks with multi-scale position attention(DGCN-MPA)to sup.Design/methodology/approach-The primary applications are in autonomous systems and intelligent manufacturing.The main objective of this study is to develop an efficient human behavior recognition framework that leverages advanced techniques to improve the prediction and interpretation of human actions.This framework aims to address the shortcomings of existing methods in handling the complexity and variability of human actions,providing more reliable and precise solutions for practical applications.The proposed DGCN-MPA framework integrates the strengths of convolutional neural networks and graph-based models.It innovatively incorporates wavelet packet transform to extract time-frequency characteristics and a MPA module to enhance the representation of skeletal node positions.The core innovation lies in the fusion of dynamic graph convolution with hierarchical attention mechanisms,which selectively attend to relevant features and spatial relationships,adjusting their importance across scales to address the variability in human actions.Findings-To validate the effectiveness of the DGCN-MPA framework,rigorous evaluations were conducted on benchmark datasets such as NTU-RGBþD and Kinetics-Skeleton.The results demonstrate that the framework achieves an F1 score of 62.18%and an accuracy of 75.93%on NTU-RGBþD and an F1 score of 69.34%and an accuracy of 76.86%on Kinetics-Skeleton,outperforming existing models.These findings underscore the framework’s capability to capture complex behavior patterns with high precision.Originality/value-By introducing a dynamic graph convolutional approach combined with multi-scale position attention mechanisms,this study represents a significant advancement in human behavior recognition technologies.The innovative design and superior performance of the DGCN-MPA framework contribute to its potential for real-world applications,particularly in integrating behavior recognition into engineering and autonomous systems.In the future,this framework has the potential to further propel the development of intelligent computing,cybernetics and related fields.
基金This work was supported by the Basic Science Center Project of National Natural Science Foundation of China(Grant No.51788104)the Ministry of Science and Technology of China(Grant Nos.2016YFA0301001,and 2017YFB0701502)the Beijing Advanced Innovation Center for Materials Genome Engineering.
文摘Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has a lower computational cost but requires accurate force fields to achieve chemical accuracy.In this work,we develop a symmetry-adapted graph neural network framework called the molecular dynamics graph neural network(MDGNN)to construct force fields automatically for molecular dynamics simulations for both molecules and crystals.This architecture consistently preserves translation,rotation,and permutation invariance in the simulations.We also propose a new feature engineering method that includes high-order terms of interatomic distances and demonstrate that the MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics.In addition,we demonstrate that force fields constructed by the proposed model have good transferability.The MDGNN is thus an efficient and promising option for performing molecular dynamics simulations of large-scale systems with high accuracy.
基金supported by the National Natural Science Foundation of China(NSFC)(62172377,61872205)the Shandong Provincial Natural Science Foundation,China(ZR2019MF018)the Startup Research Foundation for Distinguished Scholars(202112016).
文摘Dynamic graph neural networks(DGNNs)have demonstrated their extraordinary value in many practical applications.Nevertheless,the vulnerability of DNNs is a serious hidden danger as a small disturbance added to the model can markedly reduce its performance.At the same time,current adversarial attack schemes are implemented on static graphs,and the variability of attack models prevents these schemes from transferring to dynamic graphs.In this paper,we use the diffused attack of node injection to attack the DGNNs,and first propose the node injection attack based on structural fragility against DGNNs,named Structural Fragility-based Dynamic Graph Node Injection Attack(SFIA).SFIA firstly determines the target time based on the period weight.Then,it introduces a structural fragile edge selection strategy to establish the target nodes set and link them with the malicious node using serial inject.Finally,an optimization function is designed to generate adversarial features for malicious nodes.Experiments on datasets from four different fields show that SFIA is significantly superior to many comparative approaches.When the graph is injected with 1%of the original total number of nodes through SFIA,the link prediction Recall and MRR of the target DGNN link decrease by 17.4%and 14.3%respectively,and the accuracy of node classification decreases by 8.7%.
基金funded by Guangdong Provincial Natural Science Foundation of China under Grant No.2021A1515011243Guangdong Provincial Science and Technology Plan Project under Grant No.2019B010139001Guangzhou Science and Technology Plan Project under Grant No.201902020016.
文摘The integration of Dynamic Graph Neural Networks(DGNNs)with Smart Manufacturing is crucial as it enables real-time,adaptive analysis of complex data,leading to enhanced predictive accuracy and operational efficiency in industrial environments.To address the problem of poor combination effect and low prediction accuracy of current dynamic graph neural networks in spatial and temporal domains,and over-smoothing caused by traditional graph neural networks,a dynamic graph prediction method based on spatiotemporal binary-domain recurrent-like architecture is proposed:Binary Domain Graph Neural Network(BDGNN).The proposed model begins by utilizing a modified Graph Convolutional Network(GCN)without an activation function to extract meaningful graph topology information,ensuring non-redundant embeddings.In the temporal domain,Recurrent Neural Network(RNN)and residual systems are employed to facilitate the transfer of dynamic graph node information between learner weights,aiming to mitigate the impact of noise within the graph sequence.In the spatial domain,the AdaBoost(Adaptive Boosting)algorithm is applied to replace the traditional approach of stacking layers in a graph neural network.This allows for the utilization of multiple independent graph learners,enabling the extraction of higher-order neighborhood information and alleviating the issue of over-smoothing.The efficacy of BDGNN is evaluated through a series of experiments,with performance metrics including Mean Average Precision(MAP)and Mean Reciprocal Rank(MRR)for link prediction tasks,as well as metrics for traffic speed regression tasks across diverse test sets.Compared with other models,the better experiments results demonstrate that BDGNN model can not only better integrate the connection between time and space information,but also extract higher-order neighbor information to alleviate the over-smoothing phenomenon of the original GCN.
