Robust network community detection using balanced propagation

Label propagation has proven to be an extremely fast method for detecting communities in large complex networks. Furthermore, due to its simplicity, it is also currently one of the most commonly adopted algorithms in the literature. Despite various subsequent advances, an important issue of the algorithm has not yet been properly addressed. Random (node) update orders within the algorithm severely hamper its robustness, and consequently also the stability of the identified community structure. We note that an update order can be seen as increasing propagation preferences from certain nodes, and propose a balanced propagation that counteracts for the introduced randomness by utilizing node balancers. We have evaluated the proposed approach on synthetic networks with planted partition, and on several real-world networks with community structure. The results confirm that balanced propagation is significantly more robust than label propagation, when the performance of community detection is even improved. Thus, balanced propagation retains high scalability and algorithmic simplicity of label propagation, but improves on its stability and performance.     

Detecting community structure using label propagation with weighted coherent neighborhood propinquity

Community detection has become an important methodology to understand the organization and function of various real-world networks. The label propagation algorithm (LPA) is an almost linear time algorithm proved to be effective in finding a good community structure. However, LPA has a limitation caused by its one-hop horizon. Specifically, each node in LPA adopts the label shared by most of its one-hop neighbors; much network topology information is lost in this process, which we believe is one of the main reasons for its instability and poor performance. Therefore in this paper we introduce a measure named weighted coherent neighborhood propinquity (weighted-CNP) to represent the probability that a pair of vertices are involved in the same community. In label update, a node adopts the label that has the maximum weighted-CNP instead of the one that is shared by most of its neighbors. We propose a dynamic and adaptive weighted-CNP called entropic-CNP by using the principal of entropy to modulate the weights. Furthermore, we propose a framework to integrate the weighted-CNP in other algorithms in detecting community structure. We test our algorithm on both computer-generated networks and real-world networks. The experimental results show that our algorithm is more robust and effective than LPA in large-scale networks.     

LPA-MNI: An Improved Label Propagation Algorithm Based on Modularity and Node Importance for Community Detection

Community detection is of great significance in understanding the structure of the network. Label propagation algorithm (LPA) is a classical and effective method, but it has the problems of randomness and instability. An improved label propagation algorithm named LPA-MNI is proposed in this study by combining the modularity function and node importance with the original LPA. LPA-MNI first identify the initial communities according to the value of modularity. Subsequently, the label propagation is used to cluster the remaining nodes that have not been assigned to initial communities. Meanwhile, node importance is used to improve the node order of label updating and the mechanism of label selecting when multiple labels are contained by the maximum number of nodes. Extensive experiments are performed on twelve real-world networks and eight groups of synthetic networks, and the results show that LPA-MNI has better accuracy, higher modularity, and more reasonable community numbers when compared with other six algorithms. In addition, LPA-MNI is shown to be more robust than the traditional LPA algorithm.     

Overlapping Community Detection Based on Membership Degree Propagation

A community in a complex network refers to a group of nodes that are densely connected internally but with only sparse connections to the outside. Overlapping community structures are ubiquitous in real-world networks, where each node belongs to at least one community. Therefore, overlapping community detection is an important topic in complex network research. This paper proposes an overlapping community detection algorithm based on membership degree propagation that is driven by both global and local information of the node community. In the method, we introduce a concept of membership degree, which not only stores the label information, but also the degrees of the node belonging to the labels. Then the conventional label propagation process could be extended to membership degree propagation, with the results mapped directly to the overlapping community division. Therefore, it obtains the partition result and overlapping node identification simultaneously and greatly reduces the computational time. The proposed algorithm was applied to a synthetic Lancichinetti–Fortunato–Radicchi (LFR) dataset and nine real-world datasets and compared with other up-to-date algorithms. The experimental results show that our proposed algorithm is effective and outperforms the comparison methods on most datasets. Our proposed method significantly improved the accuracy and speed of the overlapping node prediction. It can also substantially alleviate the computational complexity of community structure detection in general.     

Growth curve based label propagation algorithm for community detection

How to better and faster identify the community structure is a hot issue in complex networks. During the past decades, various attempts have been made to solve this issue. Amongst them, without doubt, label propagation algorithm (LPA) is one of the most satisfying answers, especially for large-scale networks. However, it has one major flaw that when the community structure is not clear enough, a monster community tends to form. To address this issue, we set a growth curve for communities, gradually increasing from a low capacity to a higher capacity over time. Further, we improve the mechanism of label choosing for small communities to escape from local maximum. The experimental results on both synthetic and real networks demonstrate that our algorithm not only enhances the detection ability of the traditional label propagation algorithm, but also improves the quality of the identified communities.     

The effect of weight on community structure of networks

The effect of weight on community structures is investigated in this paper. We use weighted modularity Q^w$Q^w$ to evaluate the partitions and weighted extremal optimization algorithm to detect communities. Starting from empirical and idealized weighted networks, the matching between weights and edges are disturbed. Then using similarity function S to measure the difference between community structures, it is found that the redistribution of weights does strongly affect the community structure especially in dense networks. This indicates that the community structure in networks is a suitable property to reflect the role of weight.     

Overlapping community detection using weighted consensus clustering

Many overlapping community detection algorithms have been proposed. Most of them are unstable and behave non-deterministically. In this paper, we use weighted consensus clustering for combining multiple base covers obtained by classic non-deterministic algorithms to improve the quality of the results. We first evaluate a reliability measure for each community in all base covers and assign a proportional weight to each one. Then we redefine the consensus matrix that takes into account not only the common membership of nodes, but also the reliability of the communities. Experimental results on both artificial and real-world networks show that our algorithm can find overlapping communities accurately.     

基于多路可视图的健康与心梗患者心电图信号复杂网络识别

可视图(visibility graph, VG)算法已被证明是将时间序列转换为复杂网络的简单且高效的方法,其构成的复杂网络在拓扑结构中继承了原始时间序列的动力学特性.目前,单维时间序列的可视图分析已趋于成熟,但应用于复杂系统时,单变量往往无法描述系统的全局特征.本文提出一种新的多元时间序列分析方法,将心梗和健康人的12导联心电图(electrocardiograph, ECG)信号转换为多路可视图,以每个导联为一个节点,两个导联构成可视图的层间互信息为连边权重,将其映射到复杂网络.由于不同人群的全连通网络表现为完全相同的拓扑结构,无法唯一表征不同个体的动力学特征,根据层间互信息大小重构网络,提取权重度和加权聚类系数,实现对不同人群12导联ECG信号的识别.为判断序列长度对识别效果的影响,引入多尺度权重度分布熵.由于健康受试者拥有更高的平均权重度和平均加权聚类系数,其映射网络表现为更加规则的结构、更高的复杂性和连接性,可以与心梗患者进行区分,两个参数的识别准确率均达到93.3%.     

Detection of community overlap according to belief propagation and conflict

Most existing methods for detection of community overlap cannot balance efficiency and accuracy for large and densely overlapping networks. To quickly identify overlapping communities for such networks, we propose a new method that uses belief propagation and conflict (PCB) to occupy communities. We first identify triangles with maximal clustering coefficients as seed nodes and sow a new type of belief to the seed nodes. Then the beliefs explore their territory by occupying nodes with high assent ability. The beliefs propagate their strength along the graph to consolidate their territory, and conflict with each other when they encounter the same node simultaneously. Finally, the node membership is judged from the belief vectors. The PCB time complexity is nearly linear and its space complexity is linear. The algorithm was tested in extensive experiments on three real-world social networks and three computer-generated artificial graphs. The experimental results show that PCB is very fast and highly reliable. Tests on real and artificial networks give excellent results compared with three newly proposed overlapping community detection algorithms.     

Advanced modularity-specialized label propagation algorithm for detecting communities in networks

A modularity-specialized label propagation algorithm (LPAm) for detecting network communities was recently proposed. This promising algorithm offers some desirable qualities. However, LPAm favors community divisions where all communities are similar in total degree and thus it is prone to get stuck in poor local maxima in the modularity space. To escape local maxima, we employ a multistep greedy agglomerative algorithm (MSG) that can merge multiple pairs of communities at a time. Combining LPAm and MSG, we propose an advanced modularity-specialized label propagation algorithm (LPAm+). Experiments show that LPAm+ successfully detects communities with higher modularity values than ever reported in two commonly used real-world networks. Moreover, LPAm+ offers a fair compromise between accuracy and speed.     

有限步传播范围期望指标判别节点传播影响力

在线社交网络逐渐成为人们不可或缺的重要工具,识别网络中具有高影响力的节点作为初始传播源,在社会感知与谣言控制等方面具有重要意义.本文基于独立级联模型,给出了一个描述有限步传播范围期望的指标-传播度,并设计了一种高效的递推算法.该指标在局部拓扑结构信息的基础上融合了传播概率对影响力进行刻画,能够较好地反映单个节点的传播影响力.对于多传播源影响力极大化问题,本文提出了一种基于传播度的启发式算法-传播度折扣算法,使得多个传播源的联合影响力最大.最后,将上述方法应用到三个真实网络中,与经典指标和方法相比,该方法不需要知道网络的全局结构信息,而是充分了利用网络的局部结构信息,可以较快地筛选出高传播影响力的传播源.     

Detecting overlapping communities of weighted networks via a local algorithm

Identification of communities is significant in understanding the structures and functions of networks. Since some nodes naturally belong to several communities, the study of overlapping communities has attracted increasing attention recently, and many algorithms have been designed to detect overlapping communities. In this paper, an overlapping communities detecting algorithm is proposed whose main strategies are finding an initial partial community from a node with maximal node strength and adding tight nodes to expand the partial community. Seven real-world complex networks and one synthetic network are used to evaluate the algorithm. Experimental results demonstrate that the algorithm proposed is efficient for detecting overlapping communities in weighted networks.     

Accuracy and precision of methods for community identification in weighted networks

Different algorithms, which take both links and link weights into account for the community structure of weighted networks, have been reported recently. Based on the measure of similarity among community structures introduced in our previous work, in this paper, accuracy and precision of three algorithms are investigated. Results show that Potts model based algorithm and weighted extremal optimization (WEO) algorithm work well on both dense or sparse weighted networks, while weighted Girvan–Newman (WGN) algorithm works well only for relatively sparse networks.     

Synchronization speed of identical oscillators on community networks

Synchronizability of complex oscillators networks has attracted much research interest in recent years. In contrast, in this paper we investigate numerically the synchronization speed, rather than the synchronizability or synchronization stability, of identical oscillators on complex networks with communities. A new weighted community network model is employed here, in which the community strength could be tunable by one parameter δ. The results showed that the synchronization speed of identical oscillators on community networks could reach a maximal value when δ is around 0.1. We argue that this is induced by the competition between the community partition and the scale-free property of the networks. Moreover, we have given the corresponding analysis through the second least eigenvalue λ₂ of the Laplacian matrix of the network which supports the previous result that the synchronization speed is determined by the value of λ₂.     

Weighted Evolving Networks with Self-organized Communities

In order to describe the self-organization of communities in the evolution of weighted networks, we propose a new evolving model for weighted community-structured networks with the preferential mechanisms functioned in different levels according to community sizes and node strengths, respectively. Theoretical analyses and numerical simulations show that our model captures power-law distributions of community sizes, node strengths, and link weights, with tunable exponents of ν≥1, γ>2, and α>2, respectively, sharing large clustering coefficients and scaling clustering spectra, and covering the range from disassortative networks to assortative networks. Finally, we apply our new model to the scientific co-authorship networks with both their weighted and unweighted datasets to verify its effectiveness.     

一种能耗均衡的无线传感器网络加权无标度拓扑研究

针对无线传感器网络节点能耗不均衡问题,通过对节点生命期建模,得出节点生命期受节点剩余能量和通信距离的影响,进而将两端节点生命期作为构建拓扑时边权重的影响因子,通过边权重控制节点权重,最终得出了一种能耗均衡的无线传感器网络加权无标度拓扑模型,并理论证明了该模型的点权、边权和节点度均服从幂律分布.实验结果表明,该模型具有无标度拓扑的强容错性,并有效的均衡了网络中的节点能耗,延长了网络的生命期.     

基于联合矩阵分解的节点多属性网络社团检测

发现复杂网络中的社团结构在社会网络、生物组织网络和在线网络等复杂网络中具备十分重要的意义. 针对社交媒体网络的社团检测通常需要利用两种信息源: 网络拓扑结构特征和节点属性特征, 丰富的节点内容属性信息为社团检测的增加了灵活性和挑战. 传统方法是要么仅针对这两者信息之一进行单独挖掘, 或者将两者信息得到的社团结果进行线性叠加判决, 不能有效进行信息源的融合. 本文将节点的多维属性特征作为社团划分的一种有效协同学习项进行研究, 将两者信息源进行融合分析, 提出了一种基于联合矩阵分解的节点多属性网络社团检测算法CDJMF, 提高了社团检测的有效性和鲁棒性. 实验表明, 本文所提的方法能够有效利用节点的属性信息指导社团检测, 具备更高的社团划分质量.     

Research on Community Structure in Bus Transport Networks

We abstract the bus transport networks (BTNs) to two kinds of complex networks with space L and space P methods respectively. Using improved community detecting algorithm (PKM agglomerative algorithm), we analyze the community property of two kinds of BTNs graphs. The results show that the BTNs graph described with space L method have obvious community property, but the other kind of BTNs graph described with space P method have not. The reason is that the BTNs graph described with space P method have the intense overlapping community property and general community division algorithms can not identify this kind of community structure. To overcome this problem, we propose a novel community structure called N-depth community and present a corresponding community detecting algorithm, which can detect overlapping community. Applying the novel community structure and detecting algorithm to a BTN evolution model described with space P, whose network property agrees well with real BTNs', we get obvious community property.     

A validity index approach for network partitions

The validity index has been used to evaluate the fitness of partitions produced by clustering algorithms for points in Euclidean space. In this paper, we propose a new validity index for network partitions, which can provide a measure of goodness for the community structure of networks. It is defined as a product of two factors, and involves the compactness and separation for each partition. The simulated annealing strategy is used to minimize such a validity index function in coordination with our previous k-means algorithm based on the optimal reduction of a random walker Markovian dynamics on the network. It is demonstrated that the algorithm can efficiently find the community structure during the cooling process. The number of communities can be automatically determined without any prior knowledge of the community structure. Moreover, the algorithm is successfully applied to three real-world networks.