Evaluating Community Detection Research Articles

Evaluating Community Detection Algorithms for Multilayer Networks: Effectiveness of Link Weights and Link Direction

Analyzing the structures of multilayer networks (MLNs) has been a hot research topic in network science. Community detection algorithms are important tools for analyzing MLNs. In the literature, several community detection algorithms for MLNs have been proposed. Moreover, there are several options for the graph representation of an MLN: for example, directed or undirected, weighted or unweighted, and using information from all or only some layers. Although these options may affect the results of community detection in MLNs, representations that are effective for community detection have not yet been clarified. In this paper, we experimentally evaluate the effectiveness of three types of community detection algorithms for MLNs and examine how the graph representation of an MLN affects the results of these algorithms. Our main findings are as follows: (1) The flattening approach is particularly effective, whereas the layer-by-layer approach is not applicable to detecting communities in MLNs of Twitter users. (2) Using a directed graph for each layer of an MLN increases the accuracy of community detection. (3) The Leiden method, which is a community detection algorithm for single-layer networks, achieves comparable accuracy with the community detection algorithms for MLNs, which suggests that there exists room for improvement in multilayer community detection algorithms for effectively utilizing the multilayer structures of MLNs.

Deployment of Information Diffusion for Community Detection in Online Social Networks: A Comprehensive Review

The flow of information through active users in online social networks (OSNs) plays a major role in forming natural social groups, popularly known as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">communities</i> . Although structural and topological aspects of the network had been central to most of the community detection approaches, incorporation of information flow for community detection has been an emerging topic in the recent past. Often, the flow of information is studied as a traceable process called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">information diffusion</i> . The flow of information in the network affects various factors like temporal characteristics, network attributes, or social attributes. The information diffusion process helps to extract this information including where and when information is generated and in what fashion the dispersion occurs. Thus, it has the potential to aid the community detection process in social networks. In this article, the deployment of the information diffusion process for community detection has been studied extensively. The study is mainly focused on how information flow affects various network properties and social facets and explored the possibility of deployment for community detection. Various information diffusion models and community detection algorithms have been discussed in the context of network properties and social facets. Current challenges, future directions, and modalities for the deployment of information diffusion in community detection have been discussed. In addition, various widely used datasets, evaluation metrics as well as evaluation methods for evaluating community detection algorithms are also detailed.

Evaluating community detection algorithms for progressively evolving graphs

Abstract Many algorithms have been proposed in the last 10 years for the discovery of dynamic communities. However, these methods are seldom compared between themselves. In this article, we propose a generator of dynamic graphs with planted evolving community structure, as a benchmark to compare and evaluate such algorithms. Unlike previously proposed benchmarks, it is able to specify any desired evolving community structure through a descriptive language, and then to generate the corresponding progressively evolving network. We empirically evaluate six existing algorithms for dynamic community detection in terms of instantaneous and longitudinal similarity with the planted ground truth, smoothness of dynamic partitions and scalability. We notably observe different types of weaknesses depending on their approach to ensure smoothness, namely Glitches, Oversimplification and Identity loss. Although no method arises as a clear winner, we observe clear differences between methods, and we identified the fastest, those yielding the most smoothed or the most accurate solutions at each step.

HyGen: generating random graphs with hyperbolic communities

Random graph generators are necessary tools for many network science applications. For example, the evaluation of graph analysis algorithms requires methods for generating realistic synthetic graphs. Typically random graph generators are generating graphs that satisfy certain global criteria, such as degree distribution or diameter. If the generated graph is to be used to evaluate community detection and mining algorithms, however, the generator must produce realistic community structure, as well. Recent research has shown that a clique is not necessarily a realistic community structure, necessitating the development of new graph generators. We propose HyGen, a random graph generator that leverages the recent research on non-clique-like communities to produce realistic random graphs with hyperbolic community structure, degree distribution, and clustering coefficient. Our generator can also be used to accurately model time-evolving communities.

I/O-Efficient Generation of Massive Graphs Following the LFR Benchmark

LFR is a popular benchmark graph generator used to evaluate community detection algorithms. We present EM-LFR , the first external memory algorithm able to generate massive complex networks following the LFR benchmark. Its most expensive component is the generation of random graphs with prescribed degree sequences which can be divided into two steps: the graphs are first materialized deterministically using the Havel-Hakimi algorithm, and then randomized. Our main contributions are EM-HH and EM-ES , two I/O-efficient external memory algorithms for these two steps. We also propose EM-CM/ES , an alternative sampling scheme using the Configuration Model and rewiring steps to obtain a random simple graph. In an experimental evaluation, we demonstrate their performance; our implementation is able to handle graphs with more than 37 billion edges on a single machine, is competitive with a massively parallel distributed algorithm, and is faster than a state-of-the-art internal memory implementation even on instances fitting in main memory. EM-LFR ’s implementation is capable of generating large graph instances orders of magnitude faster than the original implementation. We give evidence that both implementations yield graphs with matching properties by applying clustering algorithms to generated instances. Similarly, we analyze the evolution of graph properties as EM-ES is executed on networks obtained with EM-CM/ES and find that the alternative approach can accelerate the sampling process.

Tracking community evolution in social networks: A survey

This paper presents a survey of previous studies done on the problem of tracking community evolution over time in dynamic social networks. This problem is of crucial importance in the field of social network analysis. The goal of our paper is to classify existing methods dealing with the issue. We propose a classification of various methods for tracking community evolution in dynamic social networks into four main approaches using as a criterion the functioning principle: the first one is based on independent successive static detection and matching; the second is based on dependent successive static detection; the third is based on simultaneous study of all stages of community evolution; finally, the fourth and last one concerns methods working directly on temporal networks. Our paper starts by giving basic concepts about social networks, community structure and strategies for evaluating community detection methods. Then, it describes the different approaches, and exposes the strengths as well as the weaknesses of each.

Comparison method for community detection on brain networks from neuroimaging data.

The brain is a complex system consisting of regions dedicated to different brain functions, and higher cognitive functions are realized via information flow between distant brain areas communicating with each other. As such, it is natural to shift towards brain network analysis from mapping of brain functions, for deeper understanding of the brain system. The graph theoretical network metrics measure global or local properties of network topology, but they do not provide any information about the intermediate scale of the network. Community structure analysis is a useful approach to investigate the mesoscale organization of brain network. However, the community detection schemes are yet to be established.In this paper, we propose a method to compare different community detection schemes for neuroimaging data from multiple subjects. To the best of our knowledge, our method is the first attempt to evaluate community detection from multiple-subject data without “ground truth” community and any assumptions about the original network features. To show its feasibility, three community detection algorithms and three different brain atlases were examined using resting-state fMRI functional networks. As it is crucial to find a single group-based community structure as a representative for a group of subjects to allow discussion about brain areas and connections in different conditions on common ground, a number of community detection schemes based on different approaches have been proposed. A non-parametric permutation test on similarity between group-based community structures and individual community structures was used to determine which algorithm or atlas provided the best representative structure of the group. The Normalized Mutual Information (NMI) was computed to measure the similarity between the community structures. We also discuss further issues on community detection using the proposed method.

Generalised measures for the evaluation of community detection methods

Community detection can be considered as a variant of cluster analysis applied to complex networks. For this reason, all existing studies have been using tools derived from this field when evaluating community detection algorithms. However, those are not completely relevant in the context of network analysis, because they ignore an essential part of the available information: the network structure. Therefore, they can lead to incorrect interpretations. In this article, we review these measures, and illustrate this limitation. We propose a modification to solve this problem, and apply it to the three most widespread measures: purity, Rand index and normalized mutual information (NMI). We then perform an experimental evaluation on artificially generated networks with realistic community structure. We assess the relevance of the modified measures by comparison with their traditional counterparts, and also relatively to the topological properties of the community structures. On these data, the modified NMI turns out to provide the most relevant results.