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285,227篇文章
< 1 2 … 250 >
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：
Efficient Algorithms for Steiner k-eccentricity on Graphs Similar to Trees 认领 引用
1
作者 LI Xingfu 《数学进展》 CSCD 北大核心 2026年第2期281-291,共11页
The Steiner k-eccentricity of a vertex is the maximum Steiner distance over all k-sets each of which contains the given vertex,where the Steiner distance of a vertex set is the size of a minimum Steiner tree on this s... The Steiner k-eccentricity of a vertex is the maximum Steiner distance over all k-sets each of which contains the given vertex,where the Steiner distance of a vertex set is the size of a minimum Steiner tree on this set.Since the minimum Steiner tree problem is well-known NP-hard,the Steiner k-eccentricity is not so easy to compute.This paper attempts to efficiently solve this problem on block graphs and general graphs with limited cycles.A block graph is a graph in which each block is a clique,and is also called a clique-tree.On block graphs,we propose an O(k(n+m))-time algorithm to compute the Steiner k-eccentricity of a vertex where n and m are respectively the order and size of a block graph.On general graphs with limited cycles,we take the cyclomatic numberν(G)as a parameter which is the minimum number of edges of G whose removal makes G acyclic,and devise an O(nν(G+1)(n(G)+m(G)+k))-time algorithm. 展开更多
关键词 Steiner eccentricity algorithm complexity
暂未订购 下载PDF
Modularized Graph Convolutional Network 认领 引用
2
作者 Tiantian He Zhixuan Duan Xin Luo 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第3期737-739,共3页
Dear Editor,This letter presents a novel graph neural network, namely modularized graph convolution network(MGCN), to address the underexplored issue in graph convolution networks(GCNs), wherein the weights for neighb... Dear Editor,This letter presents a novel graph neural network, namely modularized graph convolution network(MGCN), to address the underexplored issue in graph convolution networks(GCNs), wherein the weights for neighbor aggregation are fixed, leading to the limited capability of capturing diverse relationships among nodes for representation learning. Conventional GCNs always learn node representations in the graph according to the weights computed from the graph Laplacian, consequently overlooking the similarity and group cohesiveness of node features. 展开更多
关键词 graph convolution networks gcns capturing diverse relationships nodes representation learning modularized graph convolution network neighbor aggregation graph neural network modularized graph convolution network mgcn graph convolutional network
暂未订购 下载PDF
Adaptive preprocessing algorithms of corneal topography in polar coordinate system 认领 引用 被引量：1
3
作者 郭雁文 《Journal of Central South University》 SCIE EI CAS 2014年第12期4571-4576,共6页
New adaptive preprocessing algorithms based on the polar coordinate system were put forward to get high-precision corneal topography calculation results. Adaptive locating algorithms of concentric circle center were c... New adaptive preprocessing algorithms based on the polar coordinate system were put forward to get high-precision corneal topography calculation results. Adaptive locating algorithms of concentric circle center were created to accurately capture the circle center of original Placido-based image, expand the image into matrix centered around the circle center, and convert the matrix into the polar coordinate system with the circle center as pole. Adaptive image smoothing treatment was followed and the characteristics of useful circles were extracted via horizontal edge detection, based on useful circles presenting approximate horizontal lines while noise signals presenting vertical lines or different angles. Effective combination of different operators of morphology were designed to remedy data loss caused by noise disturbances, get complete image about circle edge detection to satisfy the requests of precise calculation on follow-up parameters. The experimental data show that the algorithms meet the requirements of practical detection with characteristics of less data loss, higher data accuracy and easier availability. 展开更多
关键词 corneal topography Placido disk polar coordinate self-adoption preprocessing algorithms
暂未订购 下载PDF
Constructing Three-Dimension Space Graph for Outlier Detection Algorithms in Data Mining 认领 引用 被引量：1
4
作者 ZHANG Jing 1,2 , SUN Zhi-hui 1 1.Department of Computer Science and Engineering, Southeast University, Nanjing 210096, Jiangsu, China 2.Department of Electricity and Information Engineering, Jiangsu University, Zhenjiang 212001, Jiangsu, China 《Wuhan University Journal of Natural Sciences》 EI CAS 2004年第5期585-589,共5页
Outlier detection has very important applied value in data mining literature. Different outlier detection algorithms based on distinct theories have different definitions and mining processes. The three-dimensional sp... Outlier detection has very important applied value in data mining literature. Different outlier detection algorithms based on distinct theories have different definitions and mining processes. The three-dimensional space graph for constructing applied algorithms and an improved GridOf algorithm were proposed in terms of analyzing the existing outlier detection algorithms from criterion and theory. Key words outlier - detection - three-dimensional space graph - data mining CLC number TP 311. 13 - TP 391 Foundation item: Supported by the National Natural Science Foundation of China (70371015)Biography: ZHANG Jing (1975-), female, Ph. D, lecturer, research direction: data mining and knowledge discovery. 展开更多
关键词 outlier detection three-dimensional space graph data mining
暂未订购 下载PDF
Voxel event graph neural network for event-based human gait recognition 认领 引用
5
作者 Guangyuan MA Xiaolin GONG +2 位作者 Jiangtao XU Jiandong GAO Zhaoxuan GUO 《Optoelectronics Letters》 EI 2026年第3期167-173,共7页
To improve the accuracy of event-based gait recognition,a method called voxel event graph neural network(VEGNN)is proposed.This method voxelizes the event stream and selects representative voxels as vertices of the gr... To improve the accuracy of event-based gait recognition,a method called voxel event graph neural network(VEGNN)is proposed.This method voxelizes the event stream and selects representative voxels as vertices of the graph.Then the edges are constructed based on spatio-temporal distance and temporal order constraints so that the event stream is constructed as a graph structure.Finally,a lightweight feature extraction network based on graph neural networks(GNNs)is used to efficiently capture spatio-temporal information and motion cues from the event graph.To evaluate our method,an event-based gait recognition dataset called Celex-Gait is created.Experimental results show that VEGNN achieves a gait recognition accuracy of 95.8%and 93.9%on the Celex-Gait dataset and the DVS128-Gait-Day dataset,respectively.Furthermore,compared to the state-of-the-art methods,VEGNN reduces the number of model parameters by 30%.This indicates that VEGNN achieves higher recognition accuracy with lower model complexity. 展开更多
关键词 selects representative voxels voxel event graph neural network vegnn event stream lightweight feature extraction network voxel event graph neural network graph structurefinallya graph neural networks gnns gait recognitiona
暂未订购 下载PDF
Graphical representations and worm algorithms for the O(N) spin model 认领 引用
6
作者 Longxiang Liu Lei Zhang +1 位作者 Xiaojun Tan Youjin Deng 《Communications in Theoretical Physics》 SCIE CAS CSCD 2023年第11期152-161,共10页
We present a family of graphical representations for the O(N)spin model,where N≥1 represents the spin dimension,and N=1,2,3 corresponds to the Ising,XY and Heisenberg models,respectively.With an integer parameter 0≤... We present a family of graphical representations for the O(N)spin model,where N≥1 represents the spin dimension,and N=1,2,3 corresponds to the Ising,XY and Heisenberg models,respectively.With an integer parameter 0≤ℓ≤N/2,each configuration is the coupling of ℓ copies of subgraphs consisting of directed flows and N−2ℓ copies of subgraphs constructed by undirected loops,which we call the XY and Ising subgraphs,respectively.On each lattice site,the XY subgraphs satisfy the Kirchhoff flow-conservation law and the Ising subgraphs obey the Eulerian bond condition.Then,we formulate worm-type algorithms and simulate the O(N)model on the simple-cubic lattice for N from 2 to 6 at all possibleℓ.It is observed that the worm algorithm has much higher efficiency than the Metropolis method,and,for a given N,the efficiency is an increasing function ofℓ.Besides Monte Carlo simulations,we expect that these graphical representations would provide a convenient basis for the study of the O(N)spin model by other state-of-the-art methods like the tensor network renormalization. 展开更多
关键词 Markov-chain Monte Carlo algorithms continuous spin models graphical representations
暂未订购 下载PDF
Personalized Differential Privacy Graph Neural Network 认领 引用
7
作者 Yanli Yuan Dian Lei +3 位作者 Chuan Zhang Zehui Xiong Chunhai Li Liehuang Zhu 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第2期498-500,共3页
Dear Editor,This letter addresses the critical challenge of preserving privacy in graph learning without compromising on data utility.Differential privacy(DP)is emerging as an effective method for privacy-preserving g... Dear Editor,This letter addresses the critical challenge of preserving privacy in graph learning without compromising on data utility.Differential privacy(DP)is emerging as an effective method for privacy-preserving graph learning.However,its application often diminishes data utility,especially for nodes with fewer neighbors in graph neural networks(GNNs). 展开更多
关键词 graph neural networks gnns personalized differential privacy graph learning privacy preservation data utility preserving privacy graph neural network
暂未订购 下载PDF
Dual Channel Graph Convolutional Networks via Personalized PageRank 认领 引用
8
作者 Longlong Lin Xin Luo 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第1期221-223,共3页
Dear Editor,D2This letter presents a node feature similarity preserving graph convolutional framework P G.Graph neural networks(GNNs)have garnered significant attention for their efficacy in learning graph representat... Dear Editor,D2This letter presents a node feature similarity preserving graph convolutional framework P G.Graph neural networks(GNNs)have garnered significant attention for their efficacy in learning graph representations across diverse real-world applications. 展开更多
关键词 convolutional node feature similarity graph convolutional framework learning graph representations neural networks gnns networks graph personalized
暂未订购 下载PDF
Evolutionary Graph Drawing Algorithms 认领 引用 被引量：2
9
作者 Huang Jing-wei, Wei Wen-fangSchool of Computer, Wuhan University, Wuhan 430072, Hubei, ChinaComputer Center, Yunyang Medical College, Shiyan 442000, Hubei, China 《Wuhan University Journal of Natural Sciences》 EI CAS 2003年第S1期212-216,共5页
In this paper, graph drawing algorithms based on genetic algorithms are designed for general undirected graphs and directed graphs. As being shown, graph drawing algorithms designed by genetic algorithms have the foll... In this paper, graph drawing algorithms based on genetic algorithms are designed for general undirected graphs and directed graphs. As being shown, graph drawing algorithms designed by genetic algorithms have the following advantages: the frames of the algorithms are unified, the method is simple, different algorithms may be attained by designing different objective functions, therefore enhance the reuse of the algorithms. Also, aesthetics or constrains may be added to satisfy different requirements. 展开更多
关键词 graph drawing algorithms genetic algorithms
暂未订购 下载PDF
Graphical model construction based on evolutionary algorithms 认领 引用
10
作者 Youlong YANG Yan WU Sanyang LIU 《控制理论与应用（英文版）》 2006年第4期349-354,共6页
Using Bayesian networks to model promising solutions from the current population of the evolutionary algorithms can ensure efficiency and intelligence search for the optimum. However, to construct a Bayesian network t... Using Bayesian networks to model promising solutions from the current population of the evolutionary algorithms can ensure efficiency and intelligence search for the optimum. However, to construct a Bayesian network that fits a given dataset is a NP-hard problem, and it also needs consuming mass computational resources. This paper develops a methodology for constructing a graphical model based on Bayesian Dirichlet metric. Our approach is derived from a set of propositions and theorems by researching the local metric relationship of networks matching dataset. This paper presents the algorithm to construct a tree model from a set of potential solutions using above approach. This method is important not only for evolutionary algorithms based on graphical models, but also for machine learning and data mining. The experimental results show that the exact theoretical results and the approximations match very well. 展开更多
关键词 Graphical model Evolutionary algorithms Bayesian network Tree models Bayesian Dirichlet metric
暂未订购 下载PDF
CGGM:a conditional graph generation model with adaptive sparsity for node anomaly detection in IoT networks 认领 引用
11
作者 Munan Li Xianshi Su +3 位作者 Runze Ma Tongbang Jiang Zijian Li Tony Q.S.Quek 《Digital Communications and Networks》 SCIE EI CSCD 2026年第4期686-697,共12页
Dynamic graphs are increasingly utilized for detecting anomalous behaviors in nodes within the Internet of Things(IoT). Graph generative models play a pivotal role in addressing the challenge of imbalanced node catego... Dynamic graphs are increasingly utilized for detecting anomalous behaviors in nodes within the Internet of Things(IoT). Graph generative models play a pivotal role in addressing the challenge of imbalanced node categories in dynamic graphs. However, these models encounter several limitations, including the monotonicity of adjacency relationships, the complexity in constructing multi-dimensional features for nodes, and the absence of an end-to-end method for generating multiple categories of nodes. In this study, we introduce a novel graph generation model, designated as Conditional Graph Generation Model(CGGM), aimed specifically at generating samples from minority classes. The architecture comprises two principal modules: a conditional graph generation module and a graph-based anomaly detection module. The generative module adjusts to matrix sparsity by downsampling a noise adjacency matrix and integrates a multi-dimensional feature encoder based on multihead self-attention to capture latent feature dependencies. Furthermore, a latent space constraint coupled with distribution distance is utilized to approximate the latent distribution of real data. The graph-based anomaly detection module employs the generated balanced dataset to predict node behaviors. Extensive experiments demonstrate that CGGM surpasses contemporary state-of-the-art methods in accuracy and divergence. The results further reveal that CGGM can produce diverse data categories, thereby enhancing the performance in multicategory classification tasks. 展开更多
关键词 Anomaly detection Graph neural network Temporal graph embedding Network traffic Graph generation
暂未订购 下载PDF
Dynamic Knowledge Graph Reasoning Based on Distributed Representation Learning 认领 引用
12
作者 Qiuru Fu Shumao Zhang +4 位作者 Shuang Zhou Jie Xu Changming Zhao Shanchao Li Du Xu 《Computers, Materials & Continua》 SCIE EI 2026年第2期1542-1560,共19页
Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowled... Knowledge graphs often suffer from sparsity and incompleteness.Knowledge graph reasoning is an effective way to address these issues.Unlike static knowledge graph reasoning,which is invariant over time,dynamic knowledge graph reasoning is more challenging due to its temporal nature.In essence,within each time step in a dynamic knowledge graph,there exists structural dependencies among entities and relations,whereas between adjacent time steps,there exists temporal continuity.Based on these structural and temporal characteristics,we propose a model named“DKGR-DR”to learn distributed representations of entities and relations by combining recurrent neural networks and graph neural networks to capture structural dependencies and temporal continuity in DKGs.In addition,we construct a static attribute graph to represent entities’inherent properties.DKGR-DR is capable of modeling both dynamic and static aspects of entities,enabling effective entity prediction and relation prediction.We conduct experiments on ICEWS05-15,ICEWS18,and ICEWS14 to demonstrate that DKGR-DR achieves competitive performance. 展开更多
关键词 Dynamic knowledge graph reasoning recurrent neural network graph convolutional network graph attention mechanism
暂未订购 下载PDF
Advanced High-Order Graph Convolutional Networks With Assorted Time-Frequency Transforms 认领 引用
13
作者 Ling Wang Ye Yuan Xin Luo 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第2期394-408,共15页
A dynamic graph(DG)is adopted to portray the evolving interplay between nodes in real-world scenarios prevalently.A high-order graph convolutional network(HGCN)is equipped with the ability to represent a DG by the spa... A dynamic graph(DG)is adopted to portray the evolving interplay between nodes in real-world scenarios prevalently.A high-order graph convolutional network(HGCN)is equipped with the ability to represent a DG by the spatial-temporal message passing mechanism built on tensor product.Concretely,an HGCN utilizes the discrete Fourier transform(DFT)to implement temporal message passing and then employs face-wise product to realize spatial message passing.However,DFT is only a special case of assorted time-frequency transforms,which considers the complex temporal patterns partially,thereby resulting in an inaccurate temporal message passing possibly.To address this issue,this study proposes six advanced time-frequency transform-incorporated HGCNs(TF-HGCNs)with discrete Fourier,discrete Hartley,discrete cosine,Haar wavelet,Walsh Hadamard,and slant transforms.In addition,a potent ensemble is built regarding the proposed six TF-HGCNs as the bases.Finally,the corresponding theoretical proof is presented.Empirical studies on six DG datasets demonstrate that owing to diverse time-frequency transforms,the proposed six TF-HGCNs significantly outperform state-of-the-art models in addressing the task of link weight estimation.Moreover,their ensemble outstrips each base's performance. 展开更多
关键词 Dynamic graph(DG)learning ensemble graph representation learning high-order graph convolution network(HGCN) time-frequency transform tensor product
暂未订购 下载PDF
Automatic Detection of Health-Related Rumors: A Dual-Graph Collaborative Reasoning Framework Based on Causal Logic and Knowledge Graph 认领 引用
14
作者 Ning Wang Haoran Lyu Yuchen Fu 《Computers, Materials & Continua》 SCIE EI 2026年第1期2163-2193,共31页
With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or p... With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or propagation structures,with only a few recent approaches attempting causal inference;however,these have not yet effectively integrated causal discovery with domain-specific knowledge graphs for detecting health rumors.In this study,we found that the combined use of causal discovery and domain-specific knowledge graphs can effectively identify implicit pseudo-causal logic embedded within texts,holding significant potential for health rumor detection.To this end,we propose CKDG—a dual-graph fusion framework based on causal logic and medical knowledge graphs.CKDG constructs a weighted causal graph to capture the implicit causal relationships in the text and introduces a medical knowledge graph to verify semantic consistency,thereby enhancing the ability to identify the misuse of professional terminology and pseudoscientific claims.In experiments conducted on a dataset comprising 8430 health rumors,CKDG achieved an accuracy of 91.28%and an F1 score of 90.38%,representing improvements of 5.11%and 3.29%over the best baseline,respectively.Our results indicate that the integrated use of causal discovery and domainspecific knowledge graphs offers significant advantages for health rumor detection systems.This method not only improves detection performance but also enhances the transparency and credibility of model decisions by tracing causal chains and sources of knowledge conflicts.We anticipate that this work will provide key technological support for the development of trustworthy health-information filtering systems,thereby improving the reliability of public health information on social media. 展开更多
关键词 Health rumor detection causal graph knowledge graph dual-graph fusion
暂未订购 下载PDF
Spatio-temporal feature extraction with a global-local Transformer model for video scene graph generation 认领 引用
15
作者 Rongsen Wu Jie Xu +4 位作者 Hao Zheng Zhiyuan Xu Zixuan Li Shixue Cheng Shumao Zhang 《Digital Communications and Networks》 SCIE EI CSCD 2026年第2期364-374,共11页
In the field of video scene graph generation,spatio-temporal feature extraction and the long-tail effect in relationship classification are core research issues.This paper proposes extracting spatio-temporal features ... In the field of video scene graph generation,spatio-temporal feature extraction and the long-tail effect in relationship classification are core research issues.This paper proposes extracting spatio-temporal features using the global-local Transformer model for video scene graph generation.Methods based on the Transformer architecture and attention mechanism enrich the semantic information of spatio-temporal features in videos,thereby improving the accuracy of relationship classification.In the feature processing module,pose features are introduced to strengthen the semantic representation of objects.In the spatial feature encoding module,a local spatial visibility matrix based on bounding boxes and key points of human pose features is proposed to add the issue of insufficient attention to local details in traditional Transformer encoders.In the temporal feature encoding module,a global random frame extraction strategy is proposed,which considers global temporal features while also taking computational complexity into account.In the relation classification module,to address the uneven distribution of object and relation categories in the Action Genome dataset,a relation classification loss function based on bipartite graph matching and Focal Loss is proposed,which alleviates the long-tail effect in relation classification and improves the accuracy. 展开更多
关键词 Video scene graph generation Transformer Pose features Visibility matrix Bipartite graph matching
暂未订购 下载PDF
Few-Shot Knowledge Graph Completion with Structure-Aware Graph Attention Network 认领 引用
16
作者 YANG Rongtai SHAO Yubin +2 位作者 DU Qingzhi ZHANG Feng QI Yuting 《Journal of Shanghai Jiaotong university(Science)》 EI 2026年第4期1024-1033,I0019,共10页
Few-shot knowledge graph completion refers to inferring missing entity using limited instances.A key challenge lies in entity representation,which is complicated by diverse neighbor attributes.Although the entity'... Few-shot knowledge graph completion refers to inferring missing entity using limited instances.A key challenge lies in entity representation,which is complicated by diverse neighbor attributes.Although the entity's neighborhood topology holds potential to address this,its significance is overlooked in current research.In this paper,we propose a structure-aware graph attention network for few-shot knowledge graph completion.Firstly,to enhance entity representations,we design a structure-aware graph attention encoder to capture the graph's structural features of nodes,generating embedding for entity pairs.Secondly,a semantic prototype matching network is employed to compute the prediction score.Experiments on the NELL-One and Wiki-One datasets show that our proposed model outperforms the best baseline models by 0.021,0.026,0.039,0.032 and 0.016,0.064,0.043,0.040 in terms of MRR,Hits@10,Hits@5,and Hits@1 metrics,respectively.This demonstrates that our model can effectively leverage neighborhood topological information to improve the accuracy of knowledge completion,and achieve a better generalization. 展开更多
关键词 knowledge graph completion neighborhood topology structure-aware graph attention entity representations semantic prototype
暂未订购 下载PDF
An intelligent injection-production model based on graph connection element driven by data and physics 认领 引用
17
作者 ZHAO Hui XU Yunfeng +3 位作者 JIA Deli RAO Xiang ZHOU Yuhui MENG Fankun 《Petroleum Exploration and Development》 SCIE 2026年第3期832-843,共12页
To address the challenges of connectivity characterization,dynamic prediction efficiency,and real-time optimization in complex reservoir injection-production systems,this study proposes a physics-and deep learning-int... To address the challenges of connectivity characterization,dynamic prediction efficiency,and real-time optimization in complex reservoir injection-production systems,this study proposes a physics-and deep learning-integrated intelligent injection-production modeling framework based on the graph connection element method.The method adopts the connection element method as the physical foundation and constructs a non-Euclidean graph representation to describe interwell connectivity,enabling characterization of the physical topology and dynamic interactions within the well pattern system.By incorporating an adaptive attention mechanism into a graph convolutional network and embedding time-dependent node attributes,a physics-consistent reservoir performance prediction model is developed.Furthermore,a hybrid optimization strategy integrating differential evolution and particle swarm optimization is employed to establish an intelligent optimization framework taking the economic net present value as the objective.Based on rapid prediction of injection and production behaviors,the proposed approach enables optimization of injection-production parameters and improvement of reservoir development economics.Field applications demonstrate that the proposed intelligent injection-production model based on graph connection element accurately reproduces water-cut behavior of producers and provides quantitative uncertainty estimation.It achieves rapid history matching and dynamic response forecasting for complex injection-production systems,exhibiting high accuracy and stability.It enables optimization of production strategies with NPV as the objective,demonstrating strong engineering applicability and scalability. 展开更多
关键词 non-Euclidean space graph neural networks graph connection element physics-constrained learning surrogate model differential evolution-particle swarm optimization production optimization
暂未订购 下载PDF
Spatial-Temporal Graph Fusion with Dual-Scale Convolution for Traffic Flow Prediction 认领 引用
18
作者 Dan Wang Mengyi Cui +1 位作者 Zhenhua Yu Yukang Liu 《Computers, Materials & Continua》 SCIE EI 2026年第6期1375-1396,共22页
Traffic flow prediction is of great importance in traffic planning,road resource management,and congestion mitigation.However,existing prediction have significant limitations in modeling multi-scale spatial-temporal f... Traffic flow prediction is of great importance in traffic planning,road resource management,and congestion mitigation.However,existing prediction have significant limitations in modeling multi-scale spatial-temporal features,particularly in capturing temporal periodicity and spatial dependency in dynamically evolving traffic networks.This paper proposes a novel framework of traffic flow prediction,referred to as Adaptive Graph Fusion Dual-scale Convolutional Network(AGFDCN),which integrates spatial-temporal dynamic graphs with dual-scale convolutional networks.Specifically,we introduce a Dual-Scale Temporal Network,which combines long-and short-term dilated causal convolutions with a temporal decay-aware attention mechanism to efficiently capture traffic patterns across multiple temporal scales.Furthermore,we design a Dynamic Adaptive Graph Module,which models complex spatial dependencies in traffic networks through an adaptive graph fusion mechanism and a dual-path attention-gated module.Finally,the temporal and spatial representations are integrated by employing a gated fusion mechanism,enhancing the overall prediction performance.Experimental results obtained based on three highway datasets(i.e.,PEMS04,PEMS07 and PEMS08)verify that the proposed model outperforms several state-of-the-art baselines in various evaluation metrics.Compared to the spatial-temporal graph model AGCRN with best performance in the baseline models,the proposed model exhibits significant improvements across all datasets:it achieves reduces of MAE by 42.07%and RMSE by 35.43%on PEMS04;MAE by 28.35%and RMSE by 29.28%on PEMS07;and MAE by 30.52%and RMSE by 30.73%on PEMS08,respectively,validating its effectiveness in modeling complex spatial-temporal traffic data and its robustness in handling sudden traffic changes. 展开更多
关键词 Dual-scale convolution dual-path attention-gated module adaptive graph fusion spatial-temporal dynamic graph traffic flow prediction
暂未订购 下载PDF
Experience replay with cohesive-subgraph awareness for continual graph learning in IoT 认领 引用
19
作者 Zhenzhen Xie Qi Luo +3 位作者 Yan Huang Yongqi Yin Jiaqi Zhang Junjie Pang 《Digital Communications and Networks》 SCIE EI CSCD 2026年第3期417-427,共11页
In the Internet-of-Things(IoT) scenarios, Continual Graph Learning(CGL) has become a key technique for capturing the complex relational structures underlying diverse applications including sensor networks, road system... In the Internet-of-Things(IoT) scenarios, Continual Graph Learning(CGL) has become a key technique for capturing the complex relational structures underlying diverse applications including sensor networks, road systems and biomedical networks. However, the structural changes in these evolving graphs introduce instability, making catastrophic forgetting a primary challenge for CGL. Experience replay is currently a promising method, as it strikes a balance between new and old knowledge. It also provides CGL models with a human-like memory capability. However, prior work rarely leverages the graph's intrinsic properties to proactively identify the critical patterns hiding in the evolving graphs. To this end, we propose a unified framework that integrates cohesionsubgraph awareness into existing CGL mechanisms. We propose a novel cohesive structure-aware experience replay framework that leverages intrinsic graph properties, such as k-core and k-truss metrics, to guide the selection of representative historical nodes for replay. Unlike conventional replay strategies that rely on random sampling or task-driven node selection, our approach systematically identifies structurally significant nodes that encapsulate the evolving patterns of streaming graphs. By integrating these cohesive subgraph properties into the experience replay process, our method effectively preserves critical historical knowledge while adapting to new graph structures with low computational overhead. The experimental results demonstrate that our method consistently outperforms existing replay strategies in mitigating catastrophic forgetting and maintaining classification performance. On the PubMed dataset, our k-core-based replay strategy improves the F1 score by 3.7% compared to random sampling, while reducing training time by up to 85% compared to full retraining. Similarly, on the Cora dataset, our approach achieves a 98.3% F1 score, surpassing baseline methods by 4.5%. 展开更多
关键词 Graph neural networks Continual learning Experience replay Cohesive subgraph
暂未订购 下载PDF
KIG:A Knowledge Graph-Guided Iterative-Updating Graph Neural Network for Multisensor Time Series Time-Delay Estimation 认领 引用
20
作者 Siyuan Xu Dong Pan +3 位作者 Zhaohui Jiang Zhiwen Chen Haoyang Yu Weihua Gui 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第2期327-345,共19页
Temporal alignment of multisensor time series(MTS)is a critical prerequisite for accurate modeling and optimal control in subsequent data-driven applications.Nevertheless,many approaches frequently neglect to consider... Temporal alignment of multisensor time series(MTS)is a critical prerequisite for accurate modeling and optimal control in subsequent data-driven applications.Nevertheless,many approaches frequently neglect to consider the complex interdependencies between different sensors in MTS,and temporal alignment in many methods is typically treated as an isolated task disconnected from the downstream objectives,leading to unsatisfactory performances in follow-up applications.To address these challenges,this paper proposes a novel knowledge graph(KG)-guided iterative-updating graph neural network(GNN)for time-delay estimation(TDE)in MTS.Initially,a domain-specific KG is constructed from domain mechanism knowledge,providing a foundation for GNN's initialization.Next,capitalizing on the inherent structure of the graph topology,a GNN-based TDE method is developed.Then,a customized loss function is constructed,which synthesizes both the performances of downstream tasks and graph-based constraints.Moreover,an innovative algorithm for GNN structure learning and iterative-updating is proposed to renovate the graph structure further.Finally,experimental results across various regression and classification tasks on numerical simulation,public datasets,and the real blast furnace ironmaking dataset demonstrate that the proposed method can achieve accurate temporal alignment of MTS. 展开更多
关键词 Blast furnace ironmaking process graph neural network(GNN) knowledge graph(KG) multisensor time series(MTS) temporal alignment time-delay estimation(TDE)
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 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈