Overlapping community detection with a novel hybrid metaheuristic optimisation algorithm

Community detection is an effective approach to unveil relationships among individuals in online social networks. In the literature, quite a few algorithms have been proposed to conduct community detection by exploiting the topology of social networks and the attributes of social actors. In practice, community detection is usually conducted by third parties, such as advertisement companies and hospitals, with access to social networks for different purposes, which can easily lead to a privacy breach. In this paper, we investigate community detection in social networks aiming to protect the privacy of both the network topology and the users' attributes. We show that with additional prior knowledge, community detection can be performed by querying the information of only a fraction of instead of the entire population. In particular, we first propose a new scheme called differentially private community detection (DPCD). DPCD detects communities in social networks via a probabilistic generative model, which can be decomposed into subproblems solved by individual users. The private social relationships and attributes of each user are protected by objective perturbation with differential privacy guarantees. Then, we propose a parsimonious node affiliation recovery (NAR) algorithm, which is also differentially private, to unveil the community affiliation information of the whole population based on that of the limited number of queried individuals by solving a sparse optimization problem. Through both theoretical analysis and experimental validation using synthetic and real-world social networks, we demonstrate that the proposed DPCD scheme detects social communities under the modest privacy budget. In addition, we show the effectiveness of NAR to perform community detection by querying a limited number of individuals in social networks.

With the rapid increase in popularity of online social networks, community detection in these networks has become a key aspect of research field. Overlapping community detection is an important NP-hard problem of social network analysis. Modularity-based community detection is one of the most widely used approaches for social network analysis. However, modularity-based community detection technique may fail to resolve small-size communities. Hence, we propose a novel two-step approach for overlapping community detection in social networks. In the first step, modularity density-based hybrid meta-heuristics approach is used to find the disjoint communities and the quality of these disjoint communities can be verified using Silhouette coefficient. In the second step, the quality disjoint communities with low computation cost are used to detect overlapping nodes based on Min-Max Ratio of minimum(indegree, outdegree) to the maximum(indegree, outdegree) values of nodes. We tested the proposed algorithm based on 10 standard community quality metrics along with Silhouette score using seven standard datasets. Experimental results demonstrate that the proposed approach outperforms the current state-of-the-art works in terms of quality and scalability.

Traditional community detection methods in attributed networks (eg, social network) usually disregard abundant node attribute information and only focus on structural information of a graph. Existing community detection methods in attributed networks are mostly applied in the detection of nonoverlapping communities and cannot be directly used to detect the overlapping structures. This article proposes an overlapping community detection algorithm in attributed networks. First, we employ the modified X‐means algorithm to cluster attributes to form different themes. Second, we employ the label propagation algorithm (LPA), which is based on neighborhood network conductance for priority and the rule of theme weight, to detect communities in each theme. Finally, we perform redundant processing to form the final community division. The proposed algorithm improves the X‐means algorithm to avoid the effects of outliers. Problems of LPA such as instability of division and adjacent communities being easily merged can be corrected by prioritizing the node neighborhood network conductance. As the community is detected in the attribute subspace, the algorithm can find overlapping communities. Experimental results on real‐attributed and synthetic‐attributed networks show that the performance of the proposed algorithm is excellent with multiple evaluation metrics.

Complex networks represent various real‐world systems. Overlapping community detection is one of the critical tasks in studying these networks and has significance to a wide variety of applications, including the exploration of online social networks because of the natural attitude of persons to participate in multiple communities at the same time. Despite a large number of existing community detection algorithms for detecting disjoint communities, the efficient and fast uncovering of overlapping communities has remained a challenging problem. To provide an efficient solution, on the one hand, the balanced link density label propagation (BLDLP) algorithm, proposed by the authors of the current study, is a fast, stable, and efficient method for disjoint community detection. On the other hand, the fuzzy theory is a worthwhile approach for overlapping community detection since it provides the membership rate of the overlapping nodes as well as the detection of overlapping communities. Hence, in this paper, based on the synergy of the BLDLP algorithm and the fuzzy theory, a novel method, called fuzzy BLDLP, for overlapping community detection is proposed. Fuzzy BLDLP is fast and efficient. The proposed method needs no prior information about the number of network communities to discover them. The experiments on both synthetic and real‐world known networks, including Zachary, Dolphins, and COVID‐19 Co‐authorship, have revealed that the proposed method successfully detects the overlapping nodes and communities and hence is comparable with the state‐of‐the‐art overlapping community detection algorithms in terms of recall, precision, F‐score and overlapping normalized mutual information.

Adaptive community detection incorporating topology and content in social networks✰

Community detection is of extraordinary significance in comprehending the structure and functions of complex networks. The particle competition algorithm is a quick and heuristic algorithm when applied to community detection. However, existing particle competition algorithms do not make full use of all information of networks and have several shortcomings such as poor robustness, weak stability, and low accuracy. In addition, it cannot be effectively applied to overlapping community detection. In this paper, a new particle propagation model with semi-supervised learning for community detection in social networks (SSPCO) is proposed. SSPCO divides the formation process of communities into the initialization phase, walking phase, restart phase, convergence phase and overlapping community detection phase. In the initialization phase, each team of labeled vertices generates a particle of this team. The domination level of each team particles at vertices and edges is also initialized in this phase. In the walking phase, the particle walks to one of the neighbors of the current vertex based on the proposed walking probability calculated by the proposed transfer acceptance probability and the proposed transfer proposal probability. In the process of particle walking, the particle has a possibility of entering the restart phase. The proposed restart probability determines whether the particle performs the restart mechanism. If the particle decides to restart, it will select a vertex for restart based on the domination level of this team particles at vertices. Otherwise, it continues to walk. After several particle walking and restart phases, the particle meets the convergence state. In the convergence phase, if all particles meet the proposed convergence condition, we will obtain community partition results based on the domination level of each team particles at the vertex. In the overlapping community detection phase, we can obtain overlapping community partition results based on the overlapping community detection mechanism. Experiment results reveal that SSPCO can improve the stability and accuracy of detecting communities. Moreover, SSPCO runs in near-linear time complexity, which allows it to be applied in large-sized networks.

Many famous online social networks, e.g., Facebook and Twitter, have achieved great success in the last several years. Users in these online social networks can establish various connections via both social links and shared attribute information. Discovering groups of users who are strongly connected internally is defined as the community detection problem. Community detection problem is very important for online social networks and has extensive applications in various social services. Meanwhile, besides these popular social networks, a large number of new social networks offering specific services also spring up in recent years. Community detection can be even more important for new networks as high quality community detection results enable new networks to provide better services, which can help attract more users effectively. In this paper, we will study the community detection problem for new networks, which is formally defined as the “New Network Community Detection” problem. New network community detection problem is very challenging to solve for the reason that information in new networks can be too sparse to calculate effective similarity scores among users, which is crucial in community detection. However, we notice that, nowadays, users usually join multiple social networks simultaneously and those who are involved in a new network may have been using other well-developed social networks for a long time. With full considerations of network difference issues, we propose to propagate useful information from other well-established networks to the new network with efficient information propagation models to overcome the shortage of information problem. An effective and efficient method, Cat (Cold stArT community detector), is proposed in this paper to detect communities for new networks using information from multiple heterogeneous social networks simultaneously. Extensive experiments conducted on real-world heterogeneous online social networks demonstrate that Cat can address the new network community detection problem effectively.

Community detection in complex networks has increasingly become an important topic in the network, but in most community detection methods, a single node only belongs to one community. In fact, there is often overlap among real-world online communities. In this paper, an overlapping community detection algorithm based on subgraph structure and multi-optimization method is designed. In this algorithm, the maximum clique mined by k-core decomposition is used as the clique node, thus the overlap characteristic is transformed into the inherent characteristic of the new graph. After that, a population initialization method based on k-core decomposition is designed, and the discrete framework of multi-objective particle swarm optimization algorithm is used to optimize the two objectives on the basis of maximal clique graph to solve the problem of overlapping community detection. In the real-world network, this algorithm is compared with similar community detection algorithms. The comparison of the evaluation indexe shows that the community detection effect of this algorithm is similar to that of similar algorithms, and has a good application prospect.

Multi-relational community detection is a very important task in social network analysis because in the real world social networks are mostly multi-relational. In this paper, we propose a user-dependent method to detect communities in multi-relational social networks. We define a multi-relational community as a shared community over multiple single-relational graphs while the quality of a partitioning of nodes is assessed by a multi-relational modularity, and we design a desirable set of communities to represent the requests of users and use Normalized mutual information (NMI) between the desirable set of communities and the sets of communities detected in each single-relational graph as the weights for measuring the importance of all kinds of relationship types. We then use a greedy agglomerative manner to identify communities. Experiments have been conducted on synthetic networks to evaluate the effectiveness of the proposed approach.

During the last decade, the social networks have known a huge popularity due to their ease of connecting people. The community detection has been in the center of attention in the analysis of this kind of networks. However, this area is still a very active field of research; the majority of methods involving this problem suffers from the accuracy in the determination of meaningful modules or the computational complexity of the used algorithm. In this paper, our contribution is to propose a new method that reveals the communities in social networks based on an excellent similarity measure and the minimum spanning tree. Our approach guaranties both accuracy and efficiency of the resulted partitions when compared with the existing methods and considering five real world social networks with a very promising computational complexity.

This paper is focused on the detection of communities in social networks. We propose and describe a novel method for detecting local communities. We have used this method in an experiment on student social networks in order to prove our hypothesis about the nature of student communities. The results of the experiment rationalized our hypothesis and confirmed the effectiveness of the described method of local community detection.

A cascade information diffusion based label propagation algorithm for community detection in dynamic social networks

Parallel and distributed paradigms for community detection in social networks: A methodological review

Background/PurposeCommunity partition is of great importance in sociology, biology and computer science. Due to the exponentially increasing amount of social network applications, a fast and accurate method is necessary for community partition in social networks. In view of this, we investigate the social community partition problem from the perspective of influence propagation, which is one of the most important features of social communication.MethodsWe formulate social community partition as a combinatorial optimization problem that aims at partitioning a social network into K disjoint communities such that the sum of influence propagation within each community is maximized. When K=2 we develop an optimal algorithm that has a provable performance guarantee for a class of influence propagation models. For general K, we prove that it is NP-hard to find a maximum partition for social networks in the well-known linear threshold and independent cascade models. To get near-optimal solutions, we develop a greedy algorithm based on the optimal algorithm. We also develop a heuristic algorithm with a low computational complexity for large social networks.ResultsTo evaluate the practical efficiency of our algorithms, we do a simulation study based on real world scenarios. The experiments are conducted on three real-world social networks, and the experimental results show that more accurate partitions according to influence propagation can be obtained using our algorithms rather than using some classic community partition algorithms.ConclusionsIn this study, we investigate the community partition problem in social networks. It is formulated as an optimization problem and investigated both theoretically and practically. The results can be applied to find communities in social networks and are also useful for the influence propagation problem in social networks.

The detection of communities is an important problem in social network analysis, which has applications in various domains like sociology, biology, computer science, and marketing. In this context, genetic algorithms have proven to be effective in detecting communities by optimizing the modularity score of the network. The proposed work in this research paper uses an elitism-based genetic algorithm with some modified crossover and mutation techniques to detect communities in social networks. The proposed methodology incorporates the concepts of elitism, N-point crossover, and inverse mutation to enhance the effectiveness of genetic algorithms in solving optimization problems. The idea introduced in this article significantly extends the current understanding of optimization and evolutionary algorithms. We present an advanced methodology that leverages various genetic operators to improve the performance of a genetic algorithm in solving community detection problems in complex networks. Numerous research papers have extensively showcased the practicality of evolutionary and swarm-based algorithms in addressing real-world problems across diverse domains like viral marketing, link prediction, influence maximization, political polarization, etc. Hybridizing these algorithms with other optimization techniques has improved the performance and convergence speed, leading to enhanced optimization outcomes.