Multi-objective Community Detection Research Articles

A Multi-Objective Pigeon-Inspired Optimization Algorithm for Community Detection in Complex Networks

Community structure is a very interesting attribute and feature in complex networks, which has attracted scholars’ attention and research on community detection. Many single-objective optimization algorithms have been migrated and modified to serve community detection problems. Due to the limitation of resolution, the final algorithm implementation effect is not ideal. In this paper, a multi-objective community detection method based on a pigeon-inspired optimization algorithm, MOPIO-Net, is proposed. Firstly, the PIO algorithm is discretized in terms of the solution space representation, position, and velocity-updating strategies to adapt to discrete community detection scenarios. Secondly, by minimizing the two objective functions of community score and community fitness at the same time, the community structure with a tight interior and sparse exterior is obtained. Finally, for the misclassification caused by boundary nodes, a mutation strategy is added to improve the accuracy of the final community recognition. Experiments on synthetic and real networks verify that the proposed algorithm is more accurate in community recognition compared to 11 benchmark algorithms, confirming the effectiveness of the proposed method.

A fast variable neighborhood search approach for multi-objective community detection

Community detection in social networks is becoming one of the key tasks in social network analysis, since it helps analyzing groups of users with similar interests. This task is also useful in different areas, such as biology (interactions of genes and proteins), psychology (diagnostic criteria), or criminology (fraud detection). This paper presents a metaheuristic approach based on Variable Neighborhood Search (VNS) which leverages the combination of quality and diversity of a constructive procedure inspired in Greedy Randomized Adaptative Search Procedure (GRASP) for detecting communities in social networks. In this work, the community detection problem is modeled as a bi-objective optimization problem, where the two objective functions to be optimized are the Negative Ratio Association (NRA) and Ratio Cut (RC), two objectives that have already been proven to be in conflict. To evaluate the quality of the obtained solutions, we use the Normalized Mutual Information (NMI) metric for the instances under evaluation whose optimal solution is known, and modularity for those in which the optimal solution is unknown. Furthermore, we use metrics widely used in multi-objective optimization community to evaluate solutions, such as coverage, ε-indicator, hypervolume, and inverted generational distance. The obtained results outperform the state-of-the-art method for community detection over a set of real-life instances in both, quality and computing time.

Balancing topology structure and node attribute in evolutionary multi-objective community detection for attributed networks

The task of community detection in attributed networks is to find a good community partition in terms of both topology structure and node attribute. Despite that a number of algorithms have been suggested for community detection in attributed networks, most of them suffer from considerable performance deterioration when the community structure is not clear or the attributes of nodes in one community are not homogeneous. In this paper, we suggest a dual-population-based multi-objective evolutionary algorithm, called DP-MOEA, for balancing topology structure and node attribute in community detection of attributed networks. In DP-MOEA, one population takes charge of community detection according to the topology structure, whereas the other population is responsible for community detection based on the node attribute information. The two populations evolve independently by different genetic operations and interact with each other at every certain number of generations to utilize the good individuals obtained in the other population. Moreover, a node attribute similarity-based local search strategy and a community merging strategy are designed in the procedure of population interaction to enable the generation of high-quality individuals. Experimental results on synthetic and real-world attributed networks demonstrate the superiority of the proposed DP-MOEA over eight state-of-art evolutionary algorithms for community detection in attributed networks, especially when the community structure is unclear or the node attributes in one community are not homogeneous.

A decomposition-based ant colony optimization algorithm for the multi-objective community detection

Community structure is an important feature of complex network and detecting community can help us understand the function of networks very well. Community detection can be considered as a multi-objective optimization problem and the heuristic operators have shown promising results in dealing with this problem. In this paper, a multi-objective community detection algorithm named MOCD-ACO is proposed by combining the heuristic operator of ant colony optimization (ACO) and the multi-objective evolutionary algorithmbased on decomposition (MOEA/D). MOCD-ACO can simultaneously decompose two objective functions, i.e., Negative Ratio Association and Ratio Cut, into a number of single-objective optimization problems. Each ant is responsible for searching for a solution to a sub-problem. All ants are divided into some groups, each group sharing a pheromone matrix. The ants use pseudo-random probability selection models to construct solutions. An ant updates its current solution if it has found a better one in terms of its own objective. To make the algorithm not easy to fall into the local optimal solution, the weighted simulated annealing local search operator is integrated into the framework to expand the search range. In the experiments, synthetic network datasets and real network datasets are used to evaluate the performance of MOCD-ACO. Compared with five state-of-the-art methods, our algorithm proves to be effective in terms of normalized mutual information and modularity.

A Multi-Objective Community Detection Algorithm for Directed Network Based on Random Walk

A Multi-Objective Community Detection Algorithm for Directed Network Based on Random Walk

Multi-objective community detection algorithm with node importance analysis in attributed networks

Community detection is the act of grouping similar nodes while separating dissimilar ones. The utility of conventional algorithms are limited as they consider a structure based, single objective formulation in which, nodes are treated with the same importance. However, in real networks such as LinkedIn, nodes are not only connected through their structural properties, but also using their associated attributes. In addition, in real networks nodes interact, and this interaction causes some nodes be more important than others. However, conventional algorithms for community detection, do not consider the interactions exists amongst nodes and therefore their utility is limited. To overcome such limitations, this paper introduces a novel Multi-objective Attributed community detection algorithm with Node Importance Analysis (MANIA). The proposed algorithm considers, (i) two objective functions to evaluate the suitability of communities from structure and attribute perspectives, (ii) incorporates nodes’ attribute information to benefit from their stronger discrimination power and (iii) estimates nodes’ importance using, convergence degree and topology potential field. To prove the efficiency of MANIA, its performance is experimentally tested and compared against other novel community detection algorithms using five real-world datasets in terms of homogeneity and modularity objective functions. The comparisons indicate that MANIA detects more meaningful and interpretable communities and significantly outperforms the rivals.

A multi-objective particle swarm optimization algorithm for community detection in complex networks

Abstract Community structure is an interesting feature of complex networks. The problem of community detection has attracted many research efforts in recent years. Most of the algorithms developed for this purpose take advantage of single-objective optimization methods which may be ineffective for complex networks. In this article, a novel multi-objective community detection method based on a modified version of particle swarm optimization, named MOPSO-Net is proposed. Kernel k-means (KKM) and ratio cut (RC) are employed as objective criteria to be minimized. Our innovation in PSO algorithm is changing the moving strategy of particles. Experiments on synthetic and real-world networks confirm a significant improvement in terms of normalized mutual information (NMI) and modularity in comparison with recent similar approaches.

Multi-objective community detection method by integrating users' behavior attributes

Social networks usually have abundant attributes associated with users to describe their features. Behavior attribute is one of the most important types of attribute which can better reflect users' intrinsic interests. In practice, many network applications prefer communities that not only are densely intra-connected, but also have homogeneous attribute value on specific behavior attributes. Structure clustering and attribute categorization are two types of method which can take full advantage of structure information and attribute information to partition the network, respectively. In this paper, we propose a novel community detection method by realizing structure clustering technology and attribute categorization technology simultaneously. Specifically, structure clustering is realized by optimizing modularity which captures densely intra-connected nature of communities. As for attribute categorization, a new metric named as homogeneity is defined to achieve the goal that nodes within each community have homogeneous attribute value, while in different communities have diverse attribute values. A multi-objective optimization evolutionary mechanism is adopted to optimize modularity and homogeneity simultaneously. Extensive experiments on several real-world networks demonstrate that our method can get a set of community structures corresponding to different trade-offs between structure clustering and attribute categorization.

Multi-objective community detection based on memetic algorithm.

Community detection has drawn a lot of attention as it can provide invaluable help in understanding the function and visualizing the structure of networks. Since single objective optimization methods have intrinsic drawbacks to identifying multiple significant community structures, some methods formulate the community detection as multi-objective problems and adopt population-based evolutionary algorithms to obtain multiple community structures. Evolutionary algorithms have strong global search ability, but have difficulty in locating local optima efficiently. In this study, in order to identify multiple significant community structures more effectively, a multi-objective memetic algorithm for community detection is proposed by combining multi-objective evolutionary algorithm with a local search procedure. The local search procedure is designed by addressing three issues. Firstly, nondominated solutions generated by evolutionary operations and solutions in dominant population are set as initial individuals for local search procedure. Then, a new direction vector named as pseudonormal vector is proposed to integrate two objective functions together to form a fitness function. Finally, a network specific local search strategy based on label propagation rule is expanded to search the local optimal solutions efficiently. The extensive experiments on both artificial and real-world networks evaluate the proposed method from three aspects. Firstly, experiments on influence of local search procedure demonstrate that the local search procedure can speed up the convergence to better partitions and make the algorithm more stable. Secondly, comparisons with a set of classic community detection methods illustrate the proposed method can find single partitions effectively. Finally, the method is applied to identify hierarchical structures of networks which are beneficial for analyzing networks in multi-resolution levels.

Hybrid Self-Adaptive Algorithm for Community Detection in Complex Networks

The study of community detection algorithms in complex networks has been very active in the past several years. In this paper, a Hybrid Self-adaptive Community Detection Algorithm (HSCDA) based on modularity is put forward first. In HSCDA, three different crossover and two different mutation operators for community detection are designed and then combined to form a strategy pool, in which the strategies will be selected probabilistically based on statistical self-adaptive learning framework. Then, by adopting the best evolving strategy in HSCDA, a Multiobjective Community Detection Algorithm (MCDA) based on kernelk-means (KKM) and ratio cut (RC) objective functions is proposed which efficiently make use of recommendation of strategy by statistical self-adaptive learning framework, thus assisting the process of community detection. Experimental results on artificial and real networks show that the proposed algorithms achieve a better performance compared with similar state-of-the-art approaches.

An efficient multi-objective community detection algorithm in complex networks

An efficient multi-objective community detection algorithm in complex networks

Decomposition-based multiobjective evolutionary algorithm for community detection in dynamic social networks.

Community structure is one of the most important properties in social networks. In dynamic networks, there are two conflicting criteria that need to be considered. One is the snapshot quality, which evaluates the quality of the community partitions at the current time step. The other is the temporal cost, which evaluates the difference between communities at different time steps. In this paper, we propose a decomposition-based multiobjective community detection algorithm to simultaneously optimize these two objectives to reveal community structure and its evolution in dynamic networks. It employs the framework of multiobjective evolutionary algorithm based on decomposition to simultaneously optimize the modularity and normalized mutual information, which quantitatively measure the quality of the community partitions and temporal cost, respectively. A local search strategy dealing with the problem-specific knowledge is incorporated to improve the effectiveness of the new algorithm. Experiments on computer-generated and real-world networks demonstrate that the proposed algorithm can not only find community structure and capture community evolution more accurately, but also be steadier than the two compared algorithms.

COMPARISON AND SELECTION OF OBJECTIVE FUNCTIONS IN MULTIOBJECTIVE COMMUNITY DETECTION

Detecting communities of complex networks has been an effective way to identify substructures that could correspond to important functions. Conventional approaches usually consider community detection as a single‐objective optimization problem, which may confine the solution to a particular community structure property. Recently, a new community detection paradigm is emerging: multiobjective optimization for community detection, which means simultaneously optimizing multiple criteria and obtaining a set of community partitions. The new paradigm has shown its advantages. However, an important issue is still open: what type of objectives should be optimized to improve the performance of multiobjective community detection? To exploit this issue, we first proposed a general multiobjective community detection solution (called NSGA‐Net) and then analyzed the structural characteristics of communities identified by a variety of objective functions that have been used or can potentially be used for community detection. After that, we exploited correlation relations (i.e., positively correlated, independent, or negatively correlated) between any two objective functions. Extensive experiments on both artificial and real networks demonstrate that NSGA‐Net optimizing over a pair of negatively correlated objectives usually leads to better performances compared with the single‐objective algorithm optimizing over either of the original objectives, or even to other well‐established community detection approaches.

Community Detection in Complex Networks: Multi–objective Enhanced Firefly Algorithm

Studying the evolutionary community structure in complex networks is crucial for uncovering the links between structures and functions of a given community. Most contemporary community detection algorithms employs single optimization criteria (i.e.., modularity), which may not be adequate to represent the structures in complex networks. We suggest community detection process as a Multi-objective Optimization Problem (MOP) for investigating the community structures in complex networks. To overcome the limitations of the community detection problem, we propose a new multi-objective optimization algorithm based on enhanced firefly algorithm so that a set of non-dominated (Pareto-optimal) solutions can be achieved. In our proposed algorithm, a new tuning parameter based on a chaotic mechanism and novel self-adaptive probabilistic mutation strategies are used to improve the overall performance of the algorithm. The experimental results on synthetic and real world complex networks suggest that the multi-objective community detection algorithm provides useful paradigm for discovering overlapping community structures robustly.

Multi-objective community detection in complex networks

Community detection in social network analysis is usually considered as a single objective optimization problem, in which different heuristics or approximate algorithms are employed to optimize a objective function that capture the notion of community. Due to the inadequacy of those single-objective solutions, this paper first formulates a multi-objective framework for community detection and proposes a multi-objective evolutionary algorithm for finding efficient solutions under the framework. After analyzing and comparing a variety of objective functions that have been used or can potentially be used for community detection, this paper exploits the concept of correlation between objective which charcterizes the relationship between any two objective functions. Through extensive experiments on both artifical and real networks, this paper demonstrates that a combination of two negatively correlated objectives under the multi-objective framework usually leads to remarkably better performance compared with either of the orignal single objectives, including even many popular algorithms..