Graphs are used as a data structure to describe complex relationships between things.The node classification method based on graph network plays an important role in practical applications.None of the existing graph n...Graphs are used as a data structure to describe complex relationships between things.The node classification method based on graph network plays an important role in practical applications.None of the existing graph node classification methods consider the uneven distribution of node labels.In this paper,a graph convolution algorithm on a directed graph is designed for the distribution of unbalanced graph nodes to realize node classification based on multi-scale fusion graph convolution network.This method designs different propagation depths for each class according to the unbalance ratio on the data set,and different aggregation functions are designed at each layer of the graph convolutional network based on the class propagation depth and the graph adjacency matrix.The scope of information dissemination of positive samples is expanded relatively,thereby improving the accuracy of classification of unbalanced graph nodes.Finally,the effectiveness of the algorithm is verified through experiments on the public text classification datasets.展开更多
Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. ...Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. However, this method actually obtains the performance by extending dimensions and considering that the text and structural information are one-to-one, which is obviously unreasonable. Regarding this issue, a method by weighting vectors is proposed in this paper. Three methods, negative logarithm, modulus and sigmoid function are used to weight-trained vectors, then recombine the weighted vectors and put them into the SVM classifier for evaluation output. By comparing three different weighting methods, the results showed that using negative logarithm weighting achieved better results than the other two using modulus and sigmoid function weighting, and was superior to directly concatenating vectors in the same dimension.展开更多
The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convoluti...The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned problems.To capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge encapsulation.The hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures well.To efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution networks.Instead of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational inference.We experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.展开更多
An improved on-demand multicast routing protocol(ODMRP), node classification on-demand multicast routing protocol(NC-ODMRP), which is based on node classification in mobile ad hoc networks was proposed. NC-ODMRP class...An improved on-demand multicast routing protocol(ODMRP), node classification on-demand multicast routing protocol(NC-ODMRP), which is based on node classification in mobile ad hoc networks was proposed. NC-ODMRP classifies nodes into such three categories as ordinary node, forwarding group(FG) node, neighbor node of FG node according to their history forwarding information. The categories are distinguished with different weights by a weight table in the nodes. NC-ODMRP chooses the node with the highest weight as an FG node during the setup of forwarding group, which reduces a lot of redundant FG nodes by sharing more FG nodes between different sender and receiver pairs. The simulation results show that NC-ODMRP can reduce more than 20% FG number of ODMRP, thus enhances nearly 14% data forwarding efficiency and 12% energy consumption efficiency when the number of multicast senders is more than 5.展开更多
Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation....Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation. Disentangled GCNs have been proposed to divide each node’s representation into several feature units. However, current disentangling methods do not try to figure out how many inherent factors the model should assign to help extract the best representation of each node. This paper then proposes D^(2)-GCN to provide dynamic disentanglement in GCNs and present the most appropriate factorization of each node’s mixed features. The convergence of the proposed method is proved both theoretically and experimentally. Experiments on real-world datasets show that D^(2)-GCN outperforms the baseline models concerning node classification results in both single- and multi-label tasks.展开更多
Attributed graphs have an additional sign vector for each node.Typically,edge signs represent like or dislike relationship between the node pairs.This has applications in domains,such as recommender systems,personalis...Attributed graphs have an additional sign vector for each node.Typically,edge signs represent like or dislike relationship between the node pairs.This has applications in domains,such as recommender systems,personalised search,etc.However,limited availability of edge sign information in attributed networks requires inferring the underlying graph embeddings to fill-in the knowledge gap.Such inference is performed by way of node classification which aims to deduce the node characteristics based on the topological structure of the graph and signed interactions between the nodes.The study of attributed networks is challenging due to noise,sparsity,and class imbalance issues.In this work,we consider node centrality in conjunction with edge signs to contemplate the node classification problem in attributed networks.We propose Semi-supervised Node Classification in Attributed graphs(SNCA).SNCA is robust to underlying network noise,and has in-built class imbalance handling capabilities.We perform an extensive experimental study on real-world datasets to showcase the efficiency,scalability,robustness,and pertinence of the solution.The performance results demonstrate the suitability of the solution for large attributed graphs in real-world settings.展开更多
The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability cla...The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability classification.To address this challenge,we propose Vulnerability2Vec,a graph-embedding-based framework designed to enhance the automated classification of security vulnerabilities that threaten energy system resilience.Vulnerability2Vec converts Common Vulnerabilities and Exposures(CVE)text explanations to semantic graphs,where nodes represent CVE IDs and key terms(nouns,verbs,and adjectives),and edges capture co-occurrence relationships.Then,it embeds the semantic graphs to a low-dimensional vector space with random-walk sampling and skip-gram with negative sampling.It is possible to identify the latent relationships and structural patterns that traditional sparse vector methods fail to capture.Experimental results demonstrate a classification accuracy of up to 80%,significantly outperforming baseline methods.This approach offers a theoretical basis for classifying vulnerability types as structured semantic patterns in complex software systems.The proposed method models the semantic structure of vulnerabilities,providing a theoretical foundation for their classification.展开更多
Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes....Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.展开更多
Graph Neural Networks(GNNs)have demonstrated outstanding capabilities in processing graph-structured data and are increasingly being integrated into large-scale pre-trained models,such as Large Language Models(LLMs),t...Graph Neural Networks(GNNs)have demonstrated outstanding capabilities in processing graph-structured data and are increasingly being integrated into large-scale pre-trained models,such as Large Language Models(LLMs),to enhance structural reasoning,knowledge retrieval,and memory management.The expansion of their application scope imposes higher requirements on the robustness of GNNs.However,as GNNs are applied to more dynamic and heterogeneous environments,they become increasingly vulnerable to real-world perturbations.In particular,graph data frequently encounters joint adversarial perturbations that simultaneously affect both structures and features,which are significantly more challenging than isolated attacks.These disruptions,caused by incomplete data,malicious attacks,or inherent noise,pose substantial threats to the stable and reliable performance of traditional GNN models.To address this issue,this study proposes the Dual-Shield Graph Neural Network(DSGNN),a defense model that simultaneously mitigates structural and feature perturbations.DSGNN utilizes two parallel GNN channels to independently process structural noise and feature noise,and introduces an adaptive fusion mechanism that integrates information from both pathways to generate robust node representations.Theoretical analysis demonstrates that DSGNN achieves a tighter robustness boundary under joint perturbations compared to conventional single-channel methods.Experimental evaluations across Cora,CiteSeer,and Industry datasets show that DSGNN achieves the highest average classification accuracy under various adversarial settings,reaching 81.24%,71.94%,and 81.66%,respectively,outperforming GNNGuard,GCN-Jaccard,GCN-SVD,RGCN,and NoisyGNN.These results underscore the importance of multi-view perturbation decoupling in constructing resilient GNN models for real-world applications.展开更多
With the rapid advancement of 5G technology,the Internet of Things(IoT)has entered a new phase of appli-cations and is rapidly becoming a significant force in promoting economic development.Due to the vast amounts of ...With the rapid advancement of 5G technology,the Internet of Things(IoT)has entered a new phase of appli-cations and is rapidly becoming a significant force in promoting economic development.Due to the vast amounts of data created by numerous 5G IoT devices,the Ethereum platform has become a tool for the storage and sharing of IoT device data,thanks to its open and tamper-resistant characteristics.So,Ethereum account security is necessary for the Internet of Things to grow quickly and improve people's lives.By modeling Ethereum trans-action records as a transaction network,the account types are well identified by the Ethereum account classifi-cation system established based on Graph Neural Networks(GNNs).This work first investigates the Ethereum transaction network.Surprisingly,experimental metrics reveal that the Ethereum transaction network is neither optimal nor even satisfactory in terms of accurately representing transactions per account.This flaw may significantly impede the classification capability of GNNs,which is mostly governed by their attributes.This work proposes an Adaptive Multi-channel Bayesian Graph Attention Network(AMBGAT)for Ethereum account clas-sification to address this difficulty.AMBGAT uses attention to enhance node features,estimate graph topology that conforms to the ground truth,and efficiently extract node features pertinent to downstream tasks.An extensive experiment with actual Ethereum transaction data demonstrates that AMBGAT obtains competitive performance in the classification of Ethereum accounts while accurately estimating the graph topology.展开更多
Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high performance.However,a major concern is their robustness,particularly when faced with g...Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high performance.However,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with noise.This presents a challenge in learning robust GNNs under noisy conditions.To address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in training.Our approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global deviation.By better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more robust.We evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.展开更多
Recently,graph neural networks(GNNs)have achieved remarkable performance in representation learning on graph-structured data.However,as the number of network layers increases,GNNs based on the neighborhood aggregation...Recently,graph neural networks(GNNs)have achieved remarkable performance in representation learning on graph-structured data.However,as the number of network layers increases,GNNs based on the neighborhood aggregation strategy deteriorate due to the problem of oversmoothing,which is the major bottleneck for applying GNNs to real-world graphs.Many efforts have been made to improve the process of feature information aggregation from directly connected nodes,i.e.,breadth exploration.However,these models perform the best only in the case of three or fewer layers,and the performance drops rapidly for deep layers.To alleviate oversmoothing,we propose a nested graph attention network(NGAT),which can work in a semi-supervised manner.In addition to breadth exploration,a k-layer NGAT uses a layer-wise aggregation strategy guided by the attention mechanism to selectively leverage feature information from the k;-order neighborhood,i.e.,depth exploration.Even with a 10-layer or deeper architecture,NGAT can balance the need for preserving the locality(including root node features and the local structure)and aggregating the information from a large neighborhood.In a number of experiments on standard node classification tasks,NGAT outperforms other novel models and achieves state-of-the-art performance.展开更多
Finance,supply chains,healthcare,and energy have an increasing demand for secure transactions and data exchange.Permissioned blockchains fulfilled this need thanks to the consensus protocol that ensures that participa...Finance,supply chains,healthcare,and energy have an increasing demand for secure transactions and data exchange.Permissioned blockchains fulfilled this need thanks to the consensus protocol that ensures that participants agree on a common value.One of the most widely used protocols in private blockchains is the Practical Byzantine Fault Tolerance(PBFT),which tolerates up to one-third of Byzantine nodes,performs within partially synchronous systems,and has superior throughput compared to other protocols.It has,however,an important bandwidth consumption:2N(N-1)messages are exchanged in a system composed of𝑁nodes to validate only one block.It is possible to reduce the number of consensus participants by restricting the validation process to nodes that have demonstrated high levels of security,rapidity,and availability.In this paper,we propose the first database that traces the behavior of nodes within a system that performs PBFT consensus.It reflects their level of security,rapidity,and availability throughout the consensus.We first investigate different Single-Task Learning(STL)techniques to classify the nodes within our dataset.Then,using Multi-Task Learning(MTL)techniques,the results are much more interesting,with classification accuracies over 98%.Integrating node classification as a preliminary step to the PBFT protocol optimizes the consensus.In the best cases,it is able to reduce the latency by up to 94%and the communication traffic by up to 99%.展开更多
基金the National Natural Science Foundation of China (No.61673265)the National Key Research and Development Program (No.2020YFC1512203)+1 种基金the Special Research Projects for Civil Aircraft (No.MJ-2017-S-38)the Project of CEMEE (No.2019K0302A)。
文摘Graphs are used as a data structure to describe complex relationships between things.The node classification method based on graph network plays an important role in practical applications.None of the existing graph node classification methods consider the uneven distribution of node labels.In this paper,a graph convolution algorithm on a directed graph is designed for the distribution of unbalanced graph nodes to realize node classification based on multi-scale fusion graph convolution network.This method designs different propagation depths for each class according to the unbalance ratio on the data set,and different aggregation functions are designed at each layer of the graph convolutional network based on the class propagation depth and the graph adjacency matrix.The scope of information dissemination of positive samples is expanded relatively,thereby improving the accuracy of classification of unbalanced graph nodes.Finally,the effectiveness of the algorithm is verified through experiments on the public text classification datasets.
文摘Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. However, this method actually obtains the performance by extending dimensions and considering that the text and structural information are one-to-one, which is obviously unreasonable. Regarding this issue, a method by weighting vectors is proposed in this paper. Three methods, negative logarithm, modulus and sigmoid function are used to weight-trained vectors, then recombine the weighted vectors and put them into the SVM classifier for evaluation output. By comparing three different weighting methods, the results showed that using negative logarithm weighting achieved better results than the other two using modulus and sigmoid function weighting, and was superior to directly concatenating vectors in the same dimension.
基金supported by the Natural Science Foundation of Jiangsu Province(BK20190019,BK20190452)the National Natural Science Foundation of China(62072244,61906094)the Natural Science Foundation of Shandong Province(ZR2020LZH008)。
文摘The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned problems.To capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge encapsulation.The hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures well.To efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution networks.Instead of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational inference.We experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.
基金Project(90304010) supported by the National Natural Science Foundation of China project supported by the NewCentury Excellent Talents in University
文摘An improved on-demand multicast routing protocol(ODMRP), node classification on-demand multicast routing protocol(NC-ODMRP), which is based on node classification in mobile ad hoc networks was proposed. NC-ODMRP classifies nodes into such three categories as ordinary node, forwarding group(FG) node, neighbor node of FG node according to their history forwarding information. The categories are distinguished with different weights by a weight table in the nodes. NC-ODMRP chooses the node with the highest weight as an FG node during the setup of forwarding group, which reduces a lot of redundant FG nodes by sharing more FG nodes between different sender and receiver pairs. The simulation results show that NC-ODMRP can reduce more than 20% FG number of ODMRP, thus enhances nearly 14% data forwarding efficiency and 12% energy consumption efficiency when the number of multicast senders is more than 5.
基金supported by the National Natural Science Foundation of China(Grant Nos.62141214 and 62272171).
文摘Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation. Disentangled GCNs have been proposed to divide each node’s representation into several feature units. However, current disentangling methods do not try to figure out how many inherent factors the model should assign to help extract the best representation of each node. This paper then proposes D^(2)-GCN to provide dynamic disentanglement in GCNs and present the most appropriate factorization of each node’s mixed features. The convergence of the proposed method is proved both theoretically and experimentally. Experiments on real-world datasets show that D^(2)-GCN outperforms the baseline models concerning node classification results in both single- and multi-label tasks.
基金supported by the National Key Research and Development Program of China(No.2020YFA0909100).
文摘Attributed graphs have an additional sign vector for each node.Typically,edge signs represent like or dislike relationship between the node pairs.This has applications in domains,such as recommender systems,personalised search,etc.However,limited availability of edge sign information in attributed networks requires inferring the underlying graph embeddings to fill-in the knowledge gap.Such inference is performed by way of node classification which aims to deduce the node characteristics based on the topological structure of the graph and signed interactions between the nodes.The study of attributed networks is challenging due to noise,sparsity,and class imbalance issues.In this work,we consider node centrality in conjunction with edge signs to contemplate the node classification problem in attributed networks.We propose Semi-supervised Node Classification in Attributed graphs(SNCA).SNCA is robust to underlying network noise,and has in-built class imbalance handling capabilities.We perform an extensive experimental study on real-world datasets to showcase the efficiency,scalability,robustness,and pertinence of the solution.The performance results demonstrate the suitability of the solution for large attributed graphs in real-world settings.
基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the Convergence Security Core Talent Training Business Support Program(IITP-2025-RS-2023-00266605,50%)in part by the Institute of Information&Communications Technology Planning&Evaluation(lITP)grant funded by the Korea government(MSIT)(RS-2025-02305436,Development of Digital Innovative Element Technologies for Rapid Prediction of Potential Complex Disasters and Continuous Disaster Prevention,30%)supported by the Chung-Ang University Graduate Research Scholar-ship in 2023(20%).
文摘The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability classification.To address this challenge,we propose Vulnerability2Vec,a graph-embedding-based framework designed to enhance the automated classification of security vulnerabilities that threaten energy system resilience.Vulnerability2Vec converts Common Vulnerabilities and Exposures(CVE)text explanations to semantic graphs,where nodes represent CVE IDs and key terms(nouns,verbs,and adjectives),and edges capture co-occurrence relationships.Then,it embeds the semantic graphs to a low-dimensional vector space with random-walk sampling and skip-gram with negative sampling.It is possible to identify the latent relationships and structural patterns that traditional sparse vector methods fail to capture.Experimental results demonstrate a classification accuracy of up to 80%,significantly outperforming baseline methods.This approach offers a theoretical basis for classifying vulnerability types as structured semantic patterns in complex software systems.The proposed method models the semantic structure of vulnerabilities,providing a theoretical foundation for their classification.
基金supported by the National Key R&D Program of China(2018YFB1402600)the National Natural Science Foundation of China(Grant Nos.61802028,62192784,61877006,and 62002027)。
文摘Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.
基金funded by the Key Research and Development Program of Zhejiang Province No.2023C01141the Science and Technology Innovation Community Project of the Yangtze River Delta No.23002410100suported by the Open Research Fund of the State Key Laboratory of Blockchain and Data Security,Zhejiang University.
文摘Graph Neural Networks(GNNs)have demonstrated outstanding capabilities in processing graph-structured data and are increasingly being integrated into large-scale pre-trained models,such as Large Language Models(LLMs),to enhance structural reasoning,knowledge retrieval,and memory management.The expansion of their application scope imposes higher requirements on the robustness of GNNs.However,as GNNs are applied to more dynamic and heterogeneous environments,they become increasingly vulnerable to real-world perturbations.In particular,graph data frequently encounters joint adversarial perturbations that simultaneously affect both structures and features,which are significantly more challenging than isolated attacks.These disruptions,caused by incomplete data,malicious attacks,or inherent noise,pose substantial threats to the stable and reliable performance of traditional GNN models.To address this issue,this study proposes the Dual-Shield Graph Neural Network(DSGNN),a defense model that simultaneously mitigates structural and feature perturbations.DSGNN utilizes two parallel GNN channels to independently process structural noise and feature noise,and introduces an adaptive fusion mechanism that integrates information from both pathways to generate robust node representations.Theoretical analysis demonstrates that DSGNN achieves a tighter robustness boundary under joint perturbations compared to conventional single-channel methods.Experimental evaluations across Cora,CiteSeer,and Industry datasets show that DSGNN achieves the highest average classification accuracy under various adversarial settings,reaching 81.24%,71.94%,and 81.66%,respectively,outperforming GNNGuard,GCN-Jaccard,GCN-SVD,RGCN,and NoisyGNN.These results underscore the importance of multi-view perturbation decoupling in constructing resilient GNN models for real-world applications.
基金supported in part by the National Natural Science Foundation of China under Grant 62272405,School and Locality Integration Development Project of Yantai City(2022)the Youth Innovation Science and Technology Support Program of Shandong Provincial under Grant 2021KJ080+2 种基金the Natural Science Foundation of Shandong Province,Grant ZR2022MF238Yantai Science and Technology Innovation Development Plan Project under Grant 2021YT06000645the Open Foundation of State key Laboratory of Networking and Switching Technology(Beijing University of Posts and Telecommunications)under Grant SKLNST-2022-1-12.
文摘With the rapid advancement of 5G technology,the Internet of Things(IoT)has entered a new phase of appli-cations and is rapidly becoming a significant force in promoting economic development.Due to the vast amounts of data created by numerous 5G IoT devices,the Ethereum platform has become a tool for the storage and sharing of IoT device data,thanks to its open and tamper-resistant characteristics.So,Ethereum account security is necessary for the Internet of Things to grow quickly and improve people's lives.By modeling Ethereum trans-action records as a transaction network,the account types are well identified by the Ethereum account classifi-cation system established based on Graph Neural Networks(GNNs).This work first investigates the Ethereum transaction network.Surprisingly,experimental metrics reveal that the Ethereum transaction network is neither optimal nor even satisfactory in terms of accurately representing transactions per account.This flaw may significantly impede the classification capability of GNNs,which is mostly governed by their attributes.This work proposes an Adaptive Multi-channel Bayesian Graph Attention Network(AMBGAT)for Ethereum account clas-sification to address this difficulty.AMBGAT uses attention to enhance node features,estimate graph topology that conforms to the ground truth,and efficiently extract node features pertinent to downstream tasks.An extensive experiment with actual Ethereum transaction data demonstrates that AMBGAT obtains competitive performance in the classification of Ethereum accounts while accurately estimating the graph topology.
基金supported by the National Natural Science Foundation of China(Grant No.62127808).
文摘Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high performance.However,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with noise.This presents a challenge in learning robust GNNs under noisy conditions.To address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in training.Our approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global deviation.By better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more robust.We evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.
基金Project supptjrted by China Knowledge Centre for Engineering Sciences and Technology(CKCEST)。
文摘Recently,graph neural networks(GNNs)have achieved remarkable performance in representation learning on graph-structured data.However,as the number of network layers increases,GNNs based on the neighborhood aggregation strategy deteriorate due to the problem of oversmoothing,which is the major bottleneck for applying GNNs to real-world graphs.Many efforts have been made to improve the process of feature information aggregation from directly connected nodes,i.e.,breadth exploration.However,these models perform the best only in the case of three or fewer layers,and the performance drops rapidly for deep layers.To alleviate oversmoothing,we propose a nested graph attention network(NGAT),which can work in a semi-supervised manner.In addition to breadth exploration,a k-layer NGAT uses a layer-wise aggregation strategy guided by the attention mechanism to selectively leverage feature information from the k;-order neighborhood,i.e.,depth exploration.Even with a 10-layer or deeper architecture,NGAT can balance the need for preserving the locality(including root node features and the local structure)and aggregating the information from a large neighborhood.In a number of experiments on standard node classification tasks,NGAT outperforms other novel models and achieves state-of-the-art performance.
文摘Finance,supply chains,healthcare,and energy have an increasing demand for secure transactions and data exchange.Permissioned blockchains fulfilled this need thanks to the consensus protocol that ensures that participants agree on a common value.One of the most widely used protocols in private blockchains is the Practical Byzantine Fault Tolerance(PBFT),which tolerates up to one-third of Byzantine nodes,performs within partially synchronous systems,and has superior throughput compared to other protocols.It has,however,an important bandwidth consumption:2N(N-1)messages are exchanged in a system composed of𝑁nodes to validate only one block.It is possible to reduce the number of consensus participants by restricting the validation process to nodes that have demonstrated high levels of security,rapidity,and availability.In this paper,we propose the first database that traces the behavior of nodes within a system that performs PBFT consensus.It reflects their level of security,rapidity,and availability throughout the consensus.We first investigate different Single-Task Learning(STL)techniques to classify the nodes within our dataset.Then,using Multi-Task Learning(MTL)techniques,the results are much more interesting,with classification accuracies over 98%.Integrating node classification as a preliminary step to the PBFT protocol optimizes the consensus.In the best cases,it is able to reduce the latency by up to 94%and the communication traffic by up to 99%.
