Community Structures In Large-scale Networks Research Articles

Subsampling spectral clustering for stochastic block models in large-scale networks

The rapid development of science and technology has generated large amounts of network data, leading to significant computational challenges for network community detection. A novel subsampling spectral clustering algorithm is proposed to address this issue, which aims to identify community structures in large-scale networks with limited computing resources. The algorithm constructs a subnetwork by simple random subsampling from the entire network, and then extends the existing spectral clustering to the subnetwork to estimate the community labels for entire network nodes. As a result, for large-scale datasets, the method can be realized even using a personal computer. Moreover, the proposed method can be generalized in a parallel way. Theoretically, under the stochastic block model and its extension, the degree-corrected stochastic block model, the theoretical properties of the subsampling spectral clustering method are correspondingly established. Finally, to illustrate and evaluate the proposed method, a number of simulation studies and two real data analyses are conducted.

Community Detection Based on DeepWalk Model in Large-Scale Networks

The large-scale and complex structure of real networks brings enormous challenges to traditional community detection methods. In order to detect community structure in large-scale networks more accurately and efficiently, we propose a community detection algorithm based on the network embedding representation method. Firstly, in order to solve the scarce problem of network data, this paper uses the DeepWalk model to embed a high-dimensional network into low-dimensional space with topology information. Then, low-dimensional data are processed, with each node treated as a sample and each dimension of the node as a feature. Finally, samples are fed into a Gaussian mixture model (GMM), and in order to automatically learn the number of communities, variational inference is introduced into GMM. Experimental results on the DBLP dataset show that the model method of this paper can more effectively discover the communities in large-scale networks. By further analyzing the excavated community structure, the organizational characteristics within the community are better revealed.

Large-scale community detection based on node membership grade and sub-communities integration

Community detection plays an important role in research on network characteristics and in the mining of network information. A variety of algorithms have previously been proposed, but with the continuous growth of network scale, few of them can detect community structure efficiently. Additionally, most of these algorithms only consider non-overlapping community structures in networks. This paper addresses these problems by proposing a new algorithm, based on node membership grade and sub-communities integration, to detect community structure in large-scale networks. The proposed algorithm firstly introduces two functions based on the local information of each node in networks, namely neighboring inter-nodes membership function fMS−NN and node-to-community membership function fMS−NC. Firstly, local potential’s complete sub-graphs are efficiently mined using the function fMS−NN, and then these small graphs are merged into larger ones in light of local modularity. Secondly, incorrectly divided nodes are modified according to function fMS−NN. Additionally, by adjusting the parameters in fMS−NC, we can accurately obtain both non-overlapping communities and overlapping communities. Furthermore, the proposed algorithm employs a framework resembling label propagation, which has low time complexity and is suitable for detecting communities in large-scale networks. Experimental results on both artificial networks and real networks indicate the accuracy and efficiency of the proposed algorithm.

Near linear time algorithm to detect community structures in large-scale networks

Community detection and analysis is an important methodology for understanding the organization of various real-world networks and has applications in problems as diverse as consensus formation in social communities or the identification of functional modules in biochemical networks. Currently used algorithms that identify the community structures in large-scale real-world networks require a priori information such as the number and sizes of communities or are computationally expensive. In this paper we investigate a simple label propagation algorithm that uses the network structure alone as its guide and requires neither optimization of a predefined objective function nor prior information about the communities. In our algorithm every node is initialized with a unique label and at every step each node adopts the label that most of its neighbors currently have. In this iterative process densely connected groups of nodes form a consensus on a unique label to form communities. We validate the algorithm by applying it to networks whose community structures are known. We also demonstrate that the algorithm takes an almost linear time and hence it is computationally less expensive than what was possible so far.