共查询到20条相似文献，搜索用时 0 毫秒
1.
目前很多处理图数据的图神经网络方法被提出,然而大多数研究侧重于对特征聚合的卷积层的研究而不是进行下采样的池化层.此外,形成聚类簇的池化方式需要额外计算分配矩阵;节点得分的池化方式排名方式单一.为解决上述问题,提高图分类任务的准确性,本文提出了一种新的基于多维度信息的图池化算子MDPool.该模型使用节点特征信息以及图拓扑结构信息,获取不同维度下的节点得分.使用注意力机制归纳不同维度下的得分权重,生成更为健壮的节点排名,基于节点排名自适应选择节点集合生成诱导子图.提出的MDPool可以集成到多种的图神经网络结构,将MDPool池化算子与图神经网络卷积层堆叠形成编码解码模型EDMDPool.在4个公开数据集的图分类任务中, EDMDPool均高于现有基线模型. 相似文献
2.
How to evaluate the importance of nodes in networks and detect the centrality has become a vital problem in improving the
efficiency of telecommunication and making a disease immunity strategy. We consider the mechanisms of real networks, and define
a cost function to describe different hierarchies of networks to measure node importance. This method takes up a node’s regional
influence as well as its global influence to evaluate its importance. The results of simulation prove that this method is
proper to describe effectively and detect node discrepancies in a network. 相似文献
3.
在复杂网络中,核心节点的损坏可能会影响到整个网络的稳定性。基于节点重要性研究了网络抗毁性度量和抗毁性能。综合考虑节点度值和介数对节点重要性的影响,提出了局部介-度中心性指标。兼顾节点的聚集系数,提出节点抗毁性度量方法。为了估量网络的抗毁性能,提出了介-度熵度量及其算法。仿真攻击实验结果表明,基于介-度中心性的攻击策略移除约20%的节点后,可将网络近似地分割为孤立节点集合,它优于传统的攻击策略,表明介-度中心性指标可以更准确地刻画节点重要性。对不同模拟网络的抗毁性评估计算结果则表明,介-度熵度量对网络抗毁性能的排序符合实际情况,在衡量网络抗毁性方面是完全合理的。 相似文献
4.
以无标度网络为工具探究软件耦合度的度量.在无标度网络凝聚度的基础上,通过构建软件系统的关系依赖图模型,定义了软件的凝聚度,并给出相应算法. 相似文献
5.
以无标度网络为工具探究软件耦合度的度量。在无标度网络凝聚度的基础上,通过构建软件系统的关系依赖图模型,定义了软件的凝聚度,并给出相应算法。 相似文献
6.
Determining the centrality of nodes in complex networks provides practical benefits in many areas such as detecting influencer nodes, viral marketing, and preventing the spread of rumors. On the other hand, there is no consensus for the definition of centrality. Therefore, different centrality measures such as degree, closeness, and betweenness have been developed to measure the centrality of a node. However, each centrality measure highlights the various characteristics of the nodes in the network from its own point of view. This causes each centrality measure to rank the nodes in a different order. In recent years, researchers have focused on approaches that combine multiple centrality measures. Thus, the perspectives of different centrality measures can be considered simultaneously. In this study, we have proposed a fast and efficient method using the analytic hierarchy process and entropy weighting to combine multiple centrality measures. We tested the proposed method with synthetic and real datasets and compared the results with those of state-of-the-art methods. The experimental results showed the proposed method to be competitive with these advanced methods, whereas it performed much better than the other methods in terms of computational speed. This indicated that our proposed method could be applied to large and dynamic complex networks. 相似文献
7.
复杂网络主要面临随机攻击和选择性攻击,在不同的攻击方式下复杂网络的抗毁性有很大差异。综合考虑复杂网络的抗毁性参数,以节点的度和介数中心性为度量参数,通过5种不同攻击方式对无标度网络的抗毁性进行测试,得到度和介数的实时测量值,动态分析攻击下无标度网络的介度相关性。实验结果表明,无标度网络在ID、RD攻击下介度满足幂律关系,而在IB、RB和随机攻击下不严格满足幂律关系。 相似文献
8.
Zihou WANG Yanni HAN Tao LIN Yuemei XU Song CI Hui TANG 《Frontiers of Computer Science》2013,7(3):446-457
Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks: mapping virtual nodes and virtual edges onto substrate networks. Previous research has presented several heuristic algorithms, which fail to consider that the attributes of the substrate topology and virtual networks affect the embedding process. In this paper, for the first time, we introduce complex network centrality analysis into the virtual network embedding, and propose virtual network embedding algorithms based on closeness centrality. Due to considering of the attributes of nodes and edges in the topology, our studies are more reasonable than existing work. In addition, with the guidance of topology quantitative evaluation, the proposed network embedding approach largely improves the network utilization efficiency and decreases the embedding complexity. We also investigate our algorithms on real network topologies (e.g., AT&T, DFN) and random network topologies. Experimental results demonstrate the usability and capability of the proposed approach. 相似文献
9.
复杂网络中的谣言溯源问题一直是学者们的研究重点,随着互联网技术和社交网络的发展,如何快速准确地确定网络中的谣言源以削减其不良影响显得尤为重要.考虑到谣言源是网络中最早感染的节点,即拥有最大的节点年龄,通过对节点的未受感染邻居所表现出的免责量进行研究,综合免责量与节点年龄之间的关系,提出基于有责量和免责量的谣言溯源算法,... 相似文献
10.
Xiangmao MENG Wenkai LI Xiaoqing PENG Yaohang LI Min LI 《Frontiers of Computer Science》2021,15(6):156902
In the post-genomic era, proteomics has achieved significant theoretical and practical advances with the development of high-throughput technologies. Especially the rapid accumulation of protein-protein interactions (PPIs) provides a foundation for constructing protein interaction networks (PINs), which can furnish a new perspective for understanding cellular organizations, processes, and functions at network level. In this paper, we present a comprehensive survey on three main characteristics of PINs: centrality, modularity, and dynamics. 1) Different centrality measures, which are used to calculate the importance of proteins, are summarized based on the structural characteristics of PINs or on the basis of its integrated biological information; 2) Different modularity definitions and various clustering algorithms for predicting protein complexes or identifying functional modules are introduced; 3) The dynamics of proteins, PPIs and sub-networks are discussed, respectively. Finally, the main applications of PINs in the complex diseases are reviewed, and the challenges and future research directions are also discussed. 相似文献
11.
复杂社会网络的介数性质近似计算方法研究 总被引：4，自引：0，他引：4
随着计算机和互联网的迅猛发展,面向互联网的社会网络挖掘和分析成为一个新的课题。从互联网挖掘的社会网络往往规模巨大,这对网络分析算法的性能提出了更高的要求 。介数值作为图的重要结构性质,广泛应用于基于图的聚类、分类算法,如何降低其计算的复杂性是急需解决的问题。目前,常用的方法是利用对最短路径长度的近似来降低低网络分析算法的复杂性,但已有的近似方法没有考虑现实大规模网络的复杂网络特性,对最短路径长度的近似方 近似计算方法,其基本思想是结合复杂网络的结构特性,利用通过网络中枢节点的路径来近似最短路径,以近似的最短路径求得介数的近似值。这为图的结构性质的近似估算算提供了一种新颖的思路。通过与传统的介数计算方法和近的分析得到了若干有益的结论,为进一步的研究工作奠定了基础。 相似文献
12.
网络中重要节点的发现是研究网络特性的重要方面之一;在复杂网络、系统科学、社会网分析和互联网搜索等领域中具有广泛的应用价值。为提高全网范围内重要节点发现的效率和有效性;提出了一种基于最短路径介数及节点中心接近度的重要节点发现算法;通过最短路径介数的方法确定全网内的重要节点;利用中心接近度分析重要节点的重要性。测试结果表明;与同类的系统比较起来;该方法具有比较好的性能。 相似文献
13.
In this article, neural networks are employed for fast and efficient calculation of Green's functions in a layered medium. Radial basis function networks (RBFNs) are effectively trained to estimate the coefficients and the exponents that represent a Green's function in the discrete complex image method (DCIM). Results show very good agreement with the DCIM, and the trained RBFNs are very fast compared with the corresponding DCIM. © 2003 Wiley Periodicals, Inc. Int J RF and Microwave CAE 13: 128–135, 2003. 相似文献
14.
We present a parallel toolkit for pairwise distance computation in massive networks. Computing the exact shortest paths between a large number of vertices is a costly operation, and serial algorithms are not practical for billion‐scale graphs. We first describe an efficient parallel method to solve the single source shortest path problem on commodity hardware with no shared memory. Using it as a building block, we introduce a new parallel algorithm to estimate the shortest paths between arbitrary pairs of vertices. Our method exploits data locality, produces highly accurate results, and allows batch computation of shortest paths with 7% average error in graphs that contain billions of edges. The proposed algorithm is up to two orders of magnitude faster than previously suggested algorithms and does not require large amounts of memory or expensive high‐end servers. We further leverage this method to estimate the closeness and betweenness centrality metrics, which involve systems challenges dealing with indexing, joining, and comparing large datasets efficiently. In one experiment, we mined a real‐world Web graph with 700 million nodes and 12 billion edges to identify the most central vertices and calculated more than 63 billion shortest paths in 6 h on a 20‐node commodity cluster. Copyright © 2014 John Wiley & Sons, Ltd. 相似文献
15.
Ronan Assumpção Silva Alceu de Souza Britto Jr Fabricio Enembreck Robert Sabourin Luiz E. S. de Oliveira 《Computational Intelligence》2020,36(2):522-556
Ensemble of classifiers can improve classification accuracy by combining several models. The fusion method plays an important role in the ensemble performance. Usually, a criterion for weighting the decision of each ensemble member is adopted. Frequently, this can be done using some heuristic based on accuracy or confidence. Then, the used fusion rule must consider the established criterion for providing a most reliable ensemble output through a kind of competition among the ensemble members. This article presents a new ensemble fusion method, named centrality score-based fusion, which uses the centrality concept in the context of social network analysis (SNA) as a criterion for the ensemble decision. Centrality measures have been applied in the SNA to measure the importance of each person inside of a social network, taking into account the relationship of each person with all others. Thus, the idea is to derive the classifier weight considering the overall classifier prominence inside the ensemble network, which reflects the relationships among pairs of classifiers. We hypothesized that the prominent position of a classifier based on its pairwise relationship with the other ensemble members could be its weight in the fusion process. A robust experimental protocol has confirmed that centrality measures represent a promising strategy to weight the classifiers of an ensemble, showing that the proposed fusion method performed well against the literature. 相似文献
16.
生物网络比对是分析不同生物间进化关系的重要手段,它可以揭示不同物种间的保守功能并为物种间的注释转移提供重要信息。网络比对与子图同构类似,是一个NP-hard问题。本文提出了一种新的分治与整合策略的生物网络比对算法。首先进行模块划分,并根据已有的比对信息计算模块相似性;然后根据模块间结点的子比对获取候选结果集,最终通过超图匹配获得比对结果。使用已有的比对信息的集体行为预估模块间的相似性,大大提高了模块匹配的效率。基于路径和结点的得分函数保证了模块内结点的相似性。对于不同网络间结点的相似性,分别从结点自身和结点间的差异进行相似性判断。与现有算法相比,本文算法在生物和拓扑指标上均表现最佳。 相似文献
17.
基于社团检测的复杂网络中心性方法 总被引：1，自引：0，他引：1
论证了社团检测函数模块密度的优化进程能转化为核矩阵的特征谱分.基于核矩阵最大特征值对应的特征向量,提出了一种新的中心性方法,称为模块密度中心性方法.与以往中心性度量方法不同,这种方法以模块密度检测复杂网络中的社团结构为基础,度量了第一个节点到它分配社团上的贡献,对社团的贡献越大,该节点的中心性值越高,反之亦然.通过合成网络和标准数据集网络,验证了该方法,并同其他中心性方法进行了比较,实验表明提出的模块密度中心性方法对网络中关键节点有更好的解和稳定性.进一步在计算机产生的两个大的随机网络和来自现实世界的两个大的复杂网络中,研究了模块密度中心性方法的统计分布.结果表明了提出的中心性方法能够刻画复杂网络的拓扑结构属性. 相似文献
18.
为研究神经元的放电时间序列随时间的演化特性,提出了一种将放电时间序列的时间域映射到网络域进行处理的方法,即研究基于神经元的复杂网络随时间的演化特征来刻画神经元放电时间序列的时变特性.通过构建滑动时间窗内复杂网络拓扑,并计算其局部可视图的统计特性来实现时间序列时变特征的描述.对神经元map模型三种簇放电时间序列进行复杂网络构建并实现网络拓扑可视化,同时分析网络的统计特性来验证方法的有效性.结果表明,网络的拓扑、平均路径长度和聚类系数均能反映原时间序列的时变形态特征,并对神经元簇放电具有参数敏感性;簇放电稀疏程度与社团大小存在相关性.神经元放电时间序列网络域的时变演化特征能刻画其时间域特性,为神经电信号的处理提供了新的思路. 相似文献
19.
基因序列数据中往往存在大量的非编码和缺失序列,现有的基因序列表示大多通过人工方法对高维的基因序列进行特征提取,不仅非常耗时且成功的预测很大程度依赖于生物学知识的正确利用.基于病毒传播网络构建了一种基于图上下文信息的基因序列表示方法,对目标节点病毒序列进行编码后,使用注意力机制对其邻居节点的序列信息进行聚合,从而得到目标节点病毒序列的新的低维表示.进而依据病毒传播网络中相邻节点的基因序列相似性高于不相邻节点的特征,对基因序列表示模型进行优化,训练后得到的新的表示不仅可以有效表达基因序列的特征,同时极大地降低了序列的维度,提高了计算效率.分别在仿真病毒传播网络、新型冠状病毒和艾滋病毒传播网络数据上训练基因序列表示模型,并在相应的网络上进行未采样感染者发现任务.实验结果充分验证了模型的有效性,与其他方法的比较证明了模型的高效性,模型可以有效地在病毒传播网络上发现未采样感染者,这在流行病调查领域也具有一定的实际意义. 相似文献
20.
随着复杂网络研究的兴起,随机图成为一种重要复杂网络模型。基于完全图的生成子图的思想,得到了生成随机图的一种新算法,即用去边的方法生成随机图的算法,并用数值实验验证了加边和去边生成的随机图的统计特性（最大度、最小度、聚集系数、平均最短路径和平均度）是相近的,用去边的方法得到的图的度分布曲线在其平均度处达到峰值,随后呈指数下降,这与随机图的度分布是相同的。为了得到稀疏连通的随机图,又提出了一个不去割边的近似随机图生成算法,并从理论上说明了该算法生成的图是连通的,同时通过数值实验验证了图的连通性,并与加边随机图的统计特性进行了比较。 相似文献