期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到21篇文章
< 1 2 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
On-demand multicast routing protocol based on node classification in MANET 认领 引用 被引量：3
1
作者 邓霞 孙利民 +2 位作者 王建新 罗玉宏 陈建二 《Journal of Central South University of Technology》 2006年第2期190-195,共6页
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
关键词 mobile ad hoc networks multicast forwarding group（FG） node classification
暂未订购 下载PDF
Unbalanced Graph Multi-Scale Fusion Node Classification Method 认领 引用
2
作者 张静克 何新林 +2 位作者 戚宗锋 马超 李建勋 《Journal of Shanghai Jiaotong university(Science)》 EI 2024年第3期557-565,共9页
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
关键词 node classification unbalanced learning text classification
暂未订购 下载PDF
Variational Gridded Graph Convolution Network for Node Classification 认领 引用 被引量：10
3
作者 Xiaobin Hong Tong Zhang +1 位作者 Zhen Cui Jian Yang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2021年第10期1697-1708,共12页
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
关键词 Graph coarsening gridding node classification random walk variational convolution
暂未订购 下载PDF
Research on Node Classification Based on Joint Weighted Node Vectors 认领 引用
4
作者 Li Dai 《Journal of Applied Mathematics and Physics》 2024年第1期210-225,共16页
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
关键词 Node Classification Network Embedding Representation Learning Weighted Vectors Training
暂未订购 下载PDF
D2-GCN:a graph convolutional network with dynamic disentanglement for node classification 认领 引用 被引量：1
5
作者 Shangwei WU Yingtong XIONG +1 位作者 Hui LIANG Chuliang WENG 《Frontiers of Computer Science》 SCIE EI CSCD 2025年第1期145-161,共17页
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 D2-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 D2-GCN outperforms the baseline models concerning node classification results in both single- and multi-label tasks. 展开更多
关键词 graph convolutional networks dynamic disentanglement label entropy node classification
暂未订购 下载PDF
Few-shot node classification via local adaptive discriminant structure learning 认领 引用 被引量：2
6
作者 Zhe XUE Junping DU +3 位作者 Xin XU Xiangbin LIU Junfu WANG Feifei KOU 《Frontiers of Computer Science》 SCIE EI CSCD 2023年第2期135-143,共9页
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
关键词 few-shot learning node classification graph neural network adaptive structure learning attention strategy
暂未订购 下载PDF
SNCA:Semi-Supervised Node Classification for Evolving Large Attributed Graphs 认领 引用 被引量：1
7
作者 Faima Abbasi Muhammad Muzammal +2 位作者 Qiang Qu Farhan Riaz Jawad Ashraf 《Big Data Mining and Analytics》 EI CSCD 2024年第3期794-808,共15页
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
关键词 attributed networks node classification recommender systems
Vulnerability2Vec:A Graph-Embedding Approach for Enhancing Vulnerability Classification 认领 引用
8
作者 Myoung-oh Choi Mincheol Shin +2 位作者 Hyonjun Kang Ka Lok Man Mucheol Kim 《Computer Modeling in Engineering & Sciences》 SCIE EI 2025年第9期3191-3212,共22页
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
关键词 Security vulnerability graph representation graph-embedding deep learning node classification
暂未订购 下载PDF
SubPFed:A Personalized Federated Learning Approach with Subgraphs 认领 引用
9
作者 Jianbin Li Hang Bao Xin Tong 《Computers, Materials & Continua》 SCIE EI 2026年第7期839-860,共22页
The proliferation of large-scale graph data has enabled Graph Neural Networks (GNNs) to achieve significant success in domains such as recommender systems, social network analysis, and biomedicine. However, in practic... The proliferation of large-scale graph data has enabled Graph Neural Networks (GNNs) to achieve significant success in domains such as recommender systems, social network analysis, and biomedicine. However, in practical networked environments, particularly in distributed service infrastructures, graph data is often isolated between multiple edge smart devices and cannot be shared due to privacy, making GNN models weak in generalization. Subgraph Federated Learning (SFL) mitigates this challenge by treating local client data as subgraphs of the global graph to decentralized GNN training. Unfortunately, client-side missing edges make GNN model difficult to capture dependency information between subgraphs, and local heterogeneous data hinders global model convergence, thereby limiting the performance of federated GNN model. To address this, we propose SubPFed, a personalized federated learning approach tailored for subgraph-based training. SubPFed computes the functional embeddings of local GNNs using random graph inputs. It then estimates subgraph similarity by weighting these embeddings and the structural information of the overlapping nodes. Finally, a personalized weighted aggregation strategy is designed based on the similarity to enhance representation consistency across clients and mitigate data heterogeneity. Experiments on three real-world graph datasets show that SubPFed consistently outperforms state-of-the-art baselines, improving node classification accuracy by 4.28% to 26.50%. Furthermore, SubPFed demonstrates strong robustness under varying subgraph overlap ratios, underscoring its adaptability and scalability in federated graph learning scenarios. 展开更多
关键词 Federated learning graph neural networks node classification
暂未订购 下载PDF
Training Robust Graph Completion Networks With Extremely Weak Supervision on Graphs With Incomplete Features and Structure 认领 引用
10
作者 Chengxiang Lei Sichao Fu +4 位作者 Qinmu Peng Yiyang Zhang Bin Zou Xiao-Yuan Jing Xinge You 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第7期1707-1720,共14页
Graph neural networks(GNNs)often suffer from performance degradation due to the incompleteness of node features and structure relationships in the real world.Recently emerged graph completion learning(GCL)enhances the... Graph neural networks(GNNs)often suffer from performance degradation due to the incompleteness of node features and structure relationships in the real world.Recently emerged graph completion learning(GCL)enhances the generalization of GNNs by reconstructing the missing node features or structure relationships.Nevertheless,these proposed GCL methods are supervised by a large number of labeled nodes,which limits their applications in extremely limited labeled nodes.Moreover,the existing GCL methods either focus on feature missing or structure missing tasks,and little effort was paid to more challenging scenarios where both node features and structure relationships are simultaneously missing.In this paper,a general GCL framework with the aid of multi-level contrast graph mask autoencoders(EWS-RGCN)is proposed to improve the generalization of GNNs guided by extremely weak supervision on graphs with features and structure missing.Specifically,to alleviate the mutual interference between missing node features and structure relationships caused by message passing of GNNs,we separate the feature and structure completion into two channels.Then,a multi-level contrastive loss is introduced to simultaneously maximize the mutual information between nodes from the encoding and decoding stage,which can discover more effective supervision information from the data itself for EWS-RGCN optimization,apart from label information.To further enhance the space consistency between reconstructed node features and structure relationships,the inter-channel information cooperation module is introduced to enhance the mutual learning of feature and structure completion channels.Extensive experiments on six benchmarks demonstrate the effectiveness of our EWS-RGCN. 展开更多
关键词 Extremely weak supervision features missing graph neural networks(GNNs) node classification structure missing
暂未订购 下载PDF
DyG-Hyena:Lightweight Temporal Modeling and Efficient Information Enhancement for Continuous-Time Dynamic Graph 认领 引用
11
作者 Suchang Yang Hongtao Yu +3 位作者 Ruiyang Huang Huansha Wang Ran Li Junzheng Li 《Computers, Materials & Continua》 SCIE EI 2026年第9期945-984,共40页
Modeling dynamic graphs in continuous time is critical for applications such as user behavior prediction and recommendation systems.These models can effectively capture fine-grained and long-term temporal dependencies... Modeling dynamic graphs in continuous time is critical for applications such as user behavior prediction and recommendation systems.These models can effectively capture fine-grained and long-term temporal dependencies.However,existing approaches often suffer from high computational costs and optimization difficulties,especially when handling time-sorted neighborhood sequences over long horizons.In this work,we propose DyG-Hyena,a novel continuous-time dynamic graph learning framework that combines conditional variational autoencoder(CVAE)-assisted temporal modeling with efficient feature fusion.Our approach has two main innovations:(i)Efficient temporal fusion—we replace the Transformer with an improved,lightweight Hyena module to model and fuse time-sorted neighborhood feature sequences,reducing computation of this process while maintaining accuracy.A CVAE layer is added before Hyena to capture relative time constraints,enhancing generalization for link prediction.(ii)Task-specific multi-dimensional information enhancement—for link prediction,we incorporate cross-order neighborhood intersection encoding;for node classification,we introduce statistical encoding of node features.Extensive experiments on benchmark dynamic graph datasets demonstrate that DyG-Hyena achieves excellent performance while substantially reducing temporal modeling complexity.Our code is available at[http://gffzz188fe103f8f1460as66cxnfv9cqx669uu.ffgz.tsg.suse.edu.cn/yangchang666/DyG](http://gffzz4a6a5b3de6d54e8ds66cxnfv9cqx669uu.ffgz.tsg.suse.edu.cn/?target=https%3A%2F%2Fgithub.com%2Fyangchang666%2FDyG&scene=im&aid=497858&lang=zh)-Hyena. 展开更多
关键词 Continuous-time dynamic graph dynamic link prediction dynamic node classification Hyena
暂未订购 下载PDF
RGS-PBFT:A Reputation-Based Grouping and Supervision PBFT 认领 引用
12
作者 Xiangyuan Qi Guanglei Qiang +2 位作者 Qianxiang Zhang Zhuokun Fan Yu Du 《Journal of Electronic Research and Application》 2026年第2期21-31,共11页
To address the problems of high communication overhead,insufficient robustness in master node election,and difficulty in timely management of faulty nodes in large-scale networks,the traditional PBFT consensus algorit... To address the problems of high communication overhead,insufficient robustness in master node election,and difficulty in timely management of faulty nodes in large-scale networks,the traditional PBFT consensus algorithm is proposed as a reputation-based grouping and supervision PBFT(RGS-PBFT).This method constructs a dynamic reputation score model based on the behavioral characteristics of nodes during the consensus process,such as verification correctness,voting participation,and operational stability.Based on this model,nodes are divided into consensus groups,candidate node groups,and ordinary node groups,enabling adaptive adjustment of node roles.During the master node election phase,the top 5%of nodes with the highest reputation scores from the consensus groups are selected as the candidate set.The ordinary node group and the candidate node group elect the master node through reputation-weighted voting,thus balancing the reliability of the master node with the decentralized nature of the election process.During the consensus process,only the consensus group participates in the core voting and confirmation process of PBFT to reduce communication complexity,while the remaining nodes mainly undertake verification and supervision responsibilities.Simultaneously,a monitoring and punishment mechanism for low-reputation nodes is introduced to limit,downgrade,and isolate faulty and abnormal nodes.Experimental results show that this mechanism,while maintaining Byzantine fault tolerance,can effectively reduce consensus communication overhead and improve master node election stability and overall system performance. 展开更多
关键词 PBFT Blockchain Reputation score Consensus algorithm Node classification
暂未订购 下载PDF
Assessment of lymph node involvement in colorectal cancer 认领 引用 被引量：14
13
作者 Mark L H Ong John B Schofield 《World Journal of Gastrointestinal Surgery》 2016年第3期179-192,共14页
Lymph node metastasis informs prognosis and is a key factor in deciding further management,particularly adjuvant chemotherapy.It is core to all contemporary staging systems,including the widely used tumor node metasta... Lymph node metastasis informs prognosis and is a key factor in deciding further management,particularly adjuvant chemotherapy.It is core to all contemporary staging systems,including the widely used tumor node metastasis staging system.Patients with nodenegative disease have 5-year survival rates of 70%-80%,implying a significant minority of patients with occult lymph node metastases will succumb to disease recurrence.Enhanced staging techniques may help to identify this subset of patients,who might benefit from further treatment.Obtaining adequate numbers of lymph nodes is essential for accurate staging.Lymph node yields are affected by numerous factors,many inherent to the patient and the tumour,but others related to surgical and histopathological practice.Good lymph node recovery relies on close collaboration between surgeon and pathologist.The optimal extent of surgical resection remains a subject of debate.Extended lymphadenectomy,extra-mesenteric lymph node dissection,high arterial ligation and complete mesocolic excision are amongst the surgical techniques with plausible oncological bases,but which are not supported by the highest levels of evidence.With further development and refinement,intra-operative lymphatic mapping and sentinel lymph node biopsy may provide a guide to the optimum extent of lymphadenectomy,but in its present form,it is beset by false negatives,skip lesions and failures to identify a sentinel node.Once resected,histopathological assessment of the surgical specimen can be improved by thorough dissection techniques,step-sectioning of tissue blocks and immunohistochemistry.More recently,molecular methods have been employed.In this review,we consider the numerous factors that affect lymph node yields,including the impact of the surgical and histopathological techniques.Potential future strategies,including the use of evolving technologies,are also discussed. 展开更多
关键词 Colorectal cancer Lymphatic metastases Lymph node metastasis Neoplasm staging Tumor node metastasis classification Sentinel lymph node biopsy Lymph node excision Histopathological assessment Surgery
暂未订购 下载PDF
DSGNN:Dual-Shield Defense for Robust Graph Neural Networks 认领 引用
14
作者 Xiaohan Chen Yuanfang Chen +2 位作者 Gyu Myoung Lee Noel Crespi Pierluigi Siano 《Computers, Materials & Continua》 SCIE EI 2025年第10期1733-1750,共18页
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
关键词 Graph neural networks adversarial attacks dual-shield defense certified robustness node classification
暂未订购 下载PDF
Adaptive multi-channel Bayesian graph attention network for IoT transaction security 认领 引用 被引量：1
15
作者 Zhaowei Liu Dong Yang +1 位作者 Shenqiang Wang Hang Su 《Digital Communications and Networks》 SCIE CSCD 2024年第3期631-644,共14页
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
关键词 Internet of things Graph representation learning Node classification Security mechanism
暂未订购 下载PDF
A New Meta-path Monte Carlo Tree Search Algorithm for Heterogeneous Graph Neural Networks 认领 引用
16
作者 Bin Zhang Zhipeng Cheng +3 位作者 Chenglong Du Zhengganzhe Chen Chaoyang Chen Weihua Gui 《Machine Intelligence Research》 EI CSCD 2026年第3期647-661,共15页
Heterogeneous graph neural networks(HGNN)can capture heterogeneous semantic information in heterogeneous networks,learn the low-dimensional embedding vectors,and use them for downstream tasks.The selection of meta-pat... Heterogeneous graph neural networks(HGNN)can capture heterogeneous semantic information in heterogeneous networks,learn the low-dimensional embedding vectors,and use them for downstream tasks.The selection of meta-paths is always the focus of HGNN.Existing HGNN models often employ random selections of meta-paths or utilize all meta-paths with a fixed maximum number of hops,thereby overlooking significant heterogeneous semantic information of graphs and struggling to effectively leverage non-redundant information.To this end,a new Monte Carlo tree search-based heterogeneous graph neural network(MCTS-HGNN)model is developed to search for the appropriate set of meta-paths in heterogeneous graphs automatically,thus overcoming the difficulty of meta-path selection.Subsequently,the meta-path set is decomposed based on aggregation objects and independently applied to a subset of meta-paths by using a customized transformer-based semantic aggregation module,and then the diverse semantic information from meta-paths can be effectively utilized.Furthermore,the information from the meta-path subset is integrated by the graph-level transformer to achieve a comprehensive heterogeneous graph embedding.The learned embedding is evaluated via the downstream task of the heterogeneous graph.Finally,the ablation experiments validate the effectiveness of the module designed for the MCTS-HGNN.The experimental results demonstrate that the MCTS-HGNN outperforms state-of-the-art baselines across all evaluation metrics. 展开更多
关键词 Graph neural network heterogeneous network meta-path search node embedding node classification
FedSIN:information network representation based on federated self-adaptive learning 认领 引用
17
作者 Ang LI Yawen LI Zhe XUE 《Frontiers of Computer Science》 SCIE EI CAS CSCD 2026年第1期101-111,共11页
Previous federated learning methods primarily addressed challenges involving Euclidean data,such as images and text,where relationships between data points are linear.However,information networks,as non-Euclidean data... Previous federated learning methods primarily addressed challenges involving Euclidean data,such as images and text,where relationships between data points are linear.However,information networks,as non-Euclidean data,inherently exhibit data heterogeneity.This heterogeneity is further amplified in federated learning environments,where data from multi-party information networks introduces even greater variability.It’s also worth noting that the contributions of multi-party information networks to federated learning process are dynamic.To address this challenge,we propose an Information Network representation method based on Federated Self-adaptive learning(FedSIN),which leverages the importance of neighboring nodes in the network to learn node representations and performs adaptive federated model aggregation.Specifically,FedSIN utilizes the self-attention mechanism of the graph attention network to capture the significance of neighbor nodes’influence on each node,enabling effective aggregation of neighbor node information for improved node representation.Additionally,FedSIN designs an adaptive federated model aggregation mechanism to evaluate and incorporate the contributions of different clients based on their performance in each communication round.Experimental results on three public datasets demonstrate the superiority of our proposed FedSIN over state-of-the-art information network representation methods. 展开更多
关键词 federated learning graph attention networks information network representation learning node classification
暂未订购 下载PDF
Soft-GNN:towards robust graph neural networks via self-adaptive data utilization 认领 引用 被引量：2
18
作者 Yao WU Hong HUANG +1 位作者 Yu SONG Hai JIN 《Frontiers of Computer Science》 SCIE EI CSCD 2025年第4期1-12,共12页
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
关键词 graph neural networks node classification label noise robustness
暂未订购 下载PDF
Learning Efficient Linear Graph Transformer via Graph-attention Distillation 认领 引用
19
作者 Haotian Tao Ziyan Zhang +1 位作者 Bo Jiang Bin Luo 《Machine Intelligence Research》 EI CSCD 2025年第6期1138-1152,共15页
In recent years,graph transformers have been demonstrated to be effective learning architectures for various graphbased learning tasks.However,their scalability on large-scale data is usually restricted due to the qua... In recent years,graph transformers have been demonstrated to be effective learning architectures for various graphbased learning tasks.However,their scalability on large-scale data is usually restricted due to the quadratic computational complexity of graph transformers when compared to graph convolutional network(GCN)models.To overcome this issue,in this work,we propose to learn an efficient linear graph transformer by employing graph attention distillation model.The proposed method provides a faster and lighter graph transformer framework for graph data learning tasks.The core of the proposed distillation model is to employ the kernel decomposition approach to rebuild the graph transformer architecture,thereby reducing the quadratic complexity to the linear complexity.Furthermore,to seamlessly transfer the rich learning capacity from the regular graph transformer of teacher branch to its linear student counterpart,we devise a novel graph-attention knowledge distillation strategy to enhance the capabilities of the student network.Empirical evaluations conducted on six commonly employed benchmark datasets validate our model′s superiority,as it consistently outperforms existing methods in terms of both effectiveness and efficiency. 展开更多
关键词 Graph neural network graph transformer knowledge distillation node classification graph representation learning
NGAT:attention in breadth and depth exploration for semi-supervised graph representation learning 认领 引用 被引量：2
20
作者 Jianke HU Yin ZHANG 《Frontiers of Information Technology & Electronic Engineering》 SCIE EI CSCD 2022年第3期409-421,共13页
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
关键词 Graph learning Semi-supervised learning Node classification Attention
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈