Applications Of Community Detection Research Articles

A Comprehensive Survey on Community Detection With Deep Learning.

Detecting a community in a network is a matter of discerning the distinct features and connections of a group of members that are different from those in other communities. The ability to do this is of great significance in network analysis. However, beyond the classic spectral clustering and statistical inference methods, there have been significant developments with deep learning techniques for community detection in recent years--particularly when it comes to handling high-dimensional network data. Hence, a comprehensive review of the latest progress in community detection through deep learning is timely. To frame the survey, we have devised a new taxonomy covering different state-of-the-art methods, including deep learning models based on deep neural networks (DNNs), deep nonnegative matrix factorization, and deep sparse filtering. The main category, i.e., DNNs, is further divided into convolutional networks, graph attention networks, generative adversarial networks, and autoencoders. The popular benchmark datasets, evaluation metrics, and open-source implementations to address experimentation settings are also summarized. This is followed by a discussion on the practical applications of community detection in various domains. The survey concludes with suggestions of challenging topics that would make for fruitful future research directions in this fast-growing deep learning field.

Towards a taxonomy of waste management research: An application of community detection in keyword network

Our global environment is facing significant waste and waste management challenges, despite minor differences in definitions and what constitutes waste. In recent decades, waste has been the subject of a great deal of research since civilized society needs to manage waste efficiently and effectively. As a result of all of these issues, researchers have focused on improving waste management. To do so, a taxonomy based on the research conducted on waste management will help them. Research taxonomies and visualizations help us find the most important areas of research in waste management. There are a few researchers who taxonomize research waste according to their methodology, but there is no quantitative and data-oriented approach. By using community detection and social network analysis, this study aims to quantify and systematize waste area taxonomy.There have been 9095 articles published on waste management since 2000, and these articles were retrieved from the WOS database to create a keyword network made up of 17,808 members (unique keywords) and 79,763 links in this study. To discover the research areas of waste management, the community detection technique was used in the keyword network, and 10 main communities that represent the main research areas of waste management were discovered and named based on waste management characteristics and waste types. These 10 communities include more than 90% of all waste management research.In the next step and to achieve a hierarchical taxonomy of waste management studies, the community detection algorithm was implemented in ten communities and by discovering sub-communities, a waste management taxonomy with 10 main branches and 26 sub-branches was presented.

Prediction of viscosity of biomass-based molecules using atom modules and modularity as descriptors in neural network models

This paper presents a new artificial neural network (ANN) model for viscosity prediction at different temperatures using atom modules identified on the molecular graphs and the corresponding modularity values from the application of community detection algorithms. The model is compared to an ANN model using functional group counts and modularity as inputs. A dataset covering 430 molecules and temperature range between 253 and 463 K was employed to develop the models. The application of community detection resulted into 177 modules, which captured a wide range of molecular fragments and features, including polyfunctional molecules. The model was then reduced to 158 modules to improve performance considering statistical significance, correlation among inputs, relative importance in the ANN model and identification of outliers. The final modules model demonstrated improved performance on the training and test sets compared to the functional groups ANN model and showed excellent predictions for all compound classes. The model was then used to predict the viscosity of molecules potentially derived from biomass used in existing models, which served for further model validation. The final modules model showed improved performance based on the root mean squared error in comparison to existing models. This demonstrates the advantage of employing modularity and the modules identified by the community detection algorithm as molecular descriptors. The approach extends the potential of the application of community detection to molecular graphs and modularity to capture structure-property relationships for predicting molecular properties.

Solving orthogonal group synchronization via convex and low-rank optimization: tightness and landscape analysis

Group synchronization aims to recover the group elements from their noisy pairwise measurements. It has found many applications in community detection, clock synchronization, and joint alignment problem. This paper focuses on the orthogonal group synchronization which is often used in cryo-EM and computer vision. However, it is generally NP-hard to retrieve the group elements by finding the least squares estimator. In this work, we first study the semidefinite programming (SDP) relaxation of the orthogonal group synchronization and its tightness, i.e., the SDP estimator is exactly equal to the least squares estimator. Moreover, we investigate the performance of the Burer-Monteiro factorization in solving the SDP relaxation by analyzing its corresponding optimization landscape. We provide deterministic sufficient conditions which guarantee: (i) the tightness of SDP relaxation; (ii) optimization landscape arising from the Burer-Monteiro approach is benign, i.e., the global optimum is exactly the least squares estimator and no other spurious local optima exist. Our result provides a solid theoretical justification of why the Burer-Monteiro approach is remarkably efficient and effective in solving the large-scale SDPs arising from orthogonal group synchronization. We perform numerical experiments to complement our theoretical analysis, which gives insights into future research directions.

Levy geometric graphs.

We present a family of graphs with remarkable properties. They are obtained by connecting the points of a random walk when their distance is smaller than a given scale. Their degree (number of neighbors) does not depend on the graph's size but only on the considered scale. It follows a gamma distribution and thus presents an exponential decay. Levy flights are particular random walks with some power-law increments of infinite variance. When building the geometric graphs from them, we show from dimensional arguments that the number of connected components (clusters) follows an inverse power of the scale. The distribution of the size of their components, properly normalized, is scale invariant, which reflects the self-similar nature of the underlying process. This allows to test if a graph (including nonspatial ones) could possibly result from an underlying Levy process. When the scale increases, these graphs never tend towards a single cluster, the giant component. In other words, while the autocorrelation of the process scales as a power of the distance, they never undergo a phase transition of percolation type. The Levy graphs may find applications in community detection and in the analysis of collective behaviors as in face-to-face interaction networks.

Identifying and Characterizing New Expressions of Community Framing during Polarization

Chile experienced a series of important protests between October and December 2019. This social unrest, as it was called, was fueled by social inequity and radically affected the nation's status quo. A large portion of the population demanded a new Constitution and changes to the current government, whereas another part of the population rejected these social demands. This created a highly polarized scenario evidenced through online social media interactions. Analyzing controversial issues that emerge naturally from conversations in online communities can offer a more wide-scale understanding of today's political and societal discussions. Here, we analyze group polarization in social networks by studying the 2019 Chilean social unrest. Specifically, we propose an unsupervised approach for identifying and characterizing community framing (i.e., discovering and understanding polarized concepts). Our approach is based on the sequential application of community detection, topic modeling, and word embedding methods. The novelty of having an unsupervised approach is that it facilitates the performance of scalable and objective framing analyses with minimal human intervention, as it does not require prior domain or network knowledge. Using this methodology, we observe that an apparently similar conversation topic across communities can actually have completely different meanings to each group. We noted, for instance, that while an online community linked the term gente (people) with communism and terrorism, the other associated it with police and military oppression. In this direction, our work can help to contextualize real-world social issues in online platforms, describing how users discuss similar concepts with opposing views.

Large deviations of semisupervised learning in the stochastic block model.

In semisupervised community detection, the membership of a set of revealed nodes is known in addition to the graph structure and can be leveraged to achieve better inference accuracies. While previous works investigated the case where the revealed nodes are selected at random, this paper focuses on correlated subsets leading to atypically high accuracies. In the framework of the dense stochastic block model, we employ statistical physics methods to derive a large deviation analysis of the number of these rare subsets, as characterized by their free energy. We find theoretical evidence of a nonmonotonic relationship between reconstruction accuracy and the free energy associated to the posterior measure of the inference problem. We further discuss possible implications for active learning applications in community detection.

Info2vec: An aggregative representation method in multi-layer and heterogeneous networks

Mapping nodes in multi-layer and heterogeneous networks to low-dimensional vectors has wide applications in community detection, node classification and link prediction, etc. In this paper, a generalized graph representation learning framework is proposed for information aggregation in various multi-layer and heterogeneous networks. Specifically, an aggregation network is firstly obtained by graph transformation, generating potential information links based on the network structure on different layers. A comprehensive measurement of the similarity between different nodes in the aggregation network is then carried out by aggregating the information of nodes’ identities of structure, nearness and attributes etc. Based on the comprehensive similarity values the nodes have, a context graph can be generated using a simple edge percolation method, which provides a basis facilitating some important downstream work such as classification, clustering and prediction etc. We demonstrate the effectiveness of the new framework in identifying subnetworks in a cyberspace network, where it significantly outperforms all the existing baselines.

Multiscale community detection in Cytoscape.

Detection of community structure has become a fundamental step in the analysis of biological networks with application to protein function annotation, disease gene prediction, and drug discovery. This recent impact creates a need to make these techniques and their accompanying visualization schemes available to a broad range of biologists. Here we present a service-oriented, end-to-end software framework, CDAPS (Community Detection APplication and Service), that integrates the identification, annotation, visualization, and interrogation of multiscale network communities, accessible within the popular Cytoscape network analysis platform. With novel design principles, CDAPS addresses unmet new challenges, such as identifying hierarchical community structures, comparison of outputs generated from diverse network resources, and easy deployment of new algorithms, to facilitate community-sourced science. We demonstrate that the CDAPS framework can be applied to high-throughput protein-protein interaction networks to gain novel insights, such as the identification of putative new members of known protein complexes.

Ordering heuristics for k -clique listing

Listing all k -cliques in a graph is a fundamental graph mining problem that finds many important applications in community detection and social network analysis. Unfortunately, the problem of k -clique listing is often deemed infeasible for a large k , as the number of k -cliques in a graph is exponential in the size k. The state-of-the-art solutions for the problem are based on the ordering heuristics on nodes which can efficiently list all k -cliques in large real-world graphs for a small k (e.g., k ≤ 10). Even though a variety of heuristic algorithms have been proposed, there still lacks a thorough comparison to cover all the state-of-the-art algorithms and evaluate their performance using diverse real-world graphs. This makes it difficult for a practitioner to select which algorithm should be used for a specific application. Furthermore, existing ordering based algorithms are far from optimal which might explore unpromising search paths in the k -clique listing procedure. To address these issues, we present a comprehensive comparison of all the state-of-the-art k -clique listing and counting algorithms. We also propose a new color ordering heuristics based on greedy graph coloring techniques which is able to significantly prune the unpromising search paths. We compare the performance of 14 various algorithms using 17 large real-world graphs with up to 3 million nodes and 100 million edges. The experimental results reveal the characteristics of different algorithms, based on which we provide useful guidance for selecting appropriate techniques for different applications.

Text Semantic Annotation: A Distributed Methodology Based on Community Coherence

Text annotation is the process of identifying the sense of a textual segment within a given context to a corresponding entity on a concept ontology. As the bag of words paradigm’s limitations become increasingly discernible in modern applications, several information retrieval and artificial intelligence tasks are shifting to semantic representations for addressing the inherent natural language polysemy and homonymy challenges. With extensive application in a broad range of scientific fields, such as digital marketing, bioinformatics, chemical engineering, neuroscience, and social sciences, community detection has attracted great scientific interest. Focusing on linguistics, by aiming to identify groups of densely interconnected subgroups of semantic ontologies, community detection application has proven beneficial in terms of disambiguation improvement and ontology enhancement. In this paper we introduce a novel distributed supervised knowledge-based methodology employing community detection algorithms for text annotation with Wikipedia Entities, establishing the unprecedented concept of community Coherence as a metric for local contextual coherence compatibility. Our experimental evaluation revealed that deeper inference of relatedness and local entity community coherence in the Wikipedia graph bears substantial improvements overall via a focus on accuracy amelioration of less common annotations. The proposed methodology is propitious for wider adoption, attaining robust disambiguation performance.

A new application of community detection for identifying the real specialty of physicians

BackgroundThere is an increasing trend in using network science methods and algorithms, including community detection methods, in different areas of healthcare. These areas include protein networks, drug prescriptions, healthcare fraud detection, and drug abuse. Counterfeit drugs, off-label marketing issues, and finding the healthcare community structures in a network of hospitals, are examples of using community detection in healthcare. ObjectiveThis paper attempts to find physicians’ real medical specialties based on their prescription history. As a novel application of community detection in the healthcare field, this knowledge can be used as an alternative for missing values of the healthcare databases. Therefore, it could help scientists and researchers to obtain more accurate and more reliable results. MethodsThis research is done through the community detection method and applying big data tools as well as interviews with the field experts. The big data, which is used in this paper, includes 32 million written medical prescriptions in the year 2014, provided by the Health Insurance Organization. The results are validated both qualitatively and quantitatively. ResultsThe findings reveal nine major communities of physicians, and labeling these communities by experts presents almost every specialty in the drug prescriptions field. Some of these communities are labeled as a single well-known specialty, and some others are consist of two or more specialties that have overlap with each other. ConclusionAfter receiving the prescription data and getting the experts’ opinions, it was revealed that some physicians might persistently prescribe drugs that are not in their fields of expertise. Regarding the accuracy of community detection and the use of existing data values, we proved this hypothesis.

Bipartite communities via spectral partitioning

In this paper we are interested in finding communities with bipartite structure. A bipartite community is a pair of disjoint vertex sets S, $$S'$$ such that the number of edges with one endpoint in S and the other endpoint in $$S'$$ is “significantly more than expected.” This additional structure is natural to some applications of community detection. In fact, using other terminology, they have already been used to study correlation networks, social networks, and two distinct biological networks. In 2012 two groups independently [(1) Lee, Oveis Gharan, and Trevisan and (2) Louis, Raghavendra, Tetali, and Vempala] used higher eigenvalues of the normalized Laplacian to find an approximate solution to the k-sparse-cuts problem. In 2015 Liu generalized spectral methods for finding k communities to find k bipartite communities. Our approach improves the bounds on bipartite conductance (measure of strength of a bipartite community) found by Liu and also implies improvements to the original spectral methods by Lee et al. and Louis et al. We also highlight experimental results found when applying a practical algorithm derived from our theoretical results to three distinct real-world networks.

Community-Driven Collaborative Recommendation System

Recommendation systems (RSs) are an application of community detection, becoming more significant in our daily lives. They play a significant role in suggesting information to users such as products, services, friends and so on. A novel community driven collaborative recommendation system (CDCRS) has been proposed by the authors, in this particular paper. Furthermore, K means approach has been utilized to detect communities and extract the relationship among the users. The singular value decomposition method (SVD) is also applied. Issues of sparsity and scalability of the collaborative method are considered. Experiments were conducted on MovieLens datasets. Movie ratings were predicted and top-k recommendations for the user produced. The comparative study that was performed between the proposed as well as the collaborative filtering method dependent on SVD (CFSVD) as well as the results of experiments shows that CFSVD is outperformed by the proposed CDCRS method.

Application of community detection based on improved genetic algorithm in air pollutant propagation network

In order to analyze the propagation relationship of air pollutants in the Beijing-Tianjin-Hebei region, this paper applies the complex network to the air pollutant propagation model by analyzing the airborne pollutant propagation characteristics. A new community detection algorithm based on genetic algorithm is proposed to analyze the characteristics of air pollutant propagation network. The algorithm has combined the advantages of label propagation algorithm. The concept of community structure is added to the crossover operator, and the constrained mutation operator is used to carry out the mutation operation, so as to achieve the evolution of the population. The algorithm has found out that the air pollutant propagation network does have a community structure.

Community detection in large-scale social networks: state-of-the-art and future directions

Community detection is an important research area in social networks analysis where we are concerned with discovering the structure of the social network. Detecting communities is of great importance in sociology, biology and computer science, disciplines where systems are often represented as graphs. This problem is an NP-hard problem and not yet solved to a satisfactory level. This computational complexity is hampered by two major factors. The first factor is related to the huge size of nowadays social networks like Facebook and Twitter reaching billions of nodes. The second factor is related to the dynamic nature of social networks whose structure evolves over time. For this, community detection in social networks analysis is gaining increasing attention in the scientific community and a lot of research was done in this area. The main goal of this paper is to give a comprehensive survey of community detection algorithms in social graphs. For this, we provide a taxonomy of existing models based on the computational nature (either centralized or distributed) and thus in static and dynamic social networks. In addition, we provide a comprehensive overview of existing applications of community detection in social networks. Finally, we provide further research directions as well as some open challenges.

Accelerating GPU betweenness centrality

Graphs that model social networks, numerical simulations, and the structure of the Internet are enormous and cannot be manually inspected. A popular metric used to analyze these networks is Betweenness Centrality (BC), which has applications in community detection, power grid contingency analysis, and the study of the human brain. However, these analyses come with a high computational cost that prevents the examination of large graphs of interest. Recently, the use of Graphics Processing Units (GPUs) has been promising for efficient processing of unstructured data sets. Prior GPU implementations of BC suffer from large local data structures and inefficient graph traversals that limit scalability and performance. Here we present a hybrid GPU implementation that provides good performance on graphs of arbitrary structure rather than just scale-free graphs as was done previously. Our methods achieve up to 13× speedup on high-diameter graphs and an average of 2.71× speedup overall compared to the best existing GPU algorithm. We also observe near linear speedup when running BC on 192 GPUs.

Community detection in dynamic networks via adaptive label propagation.

An adaptive label propagation algorithm (ALPA) is proposed to detect and monitor communities in dynamic networks. Unlike the traditional methods by re-computing the whole community decomposition after each modification of the network, ALPA takes into account the information of historical communities and updates its solution according to the network modifications via a local label propagation process, which generally affects only a small portion of the network. This makes it respond to network changes at low computational cost. The effectiveness of ALPA has been tested on both synthetic and real-world networks, which shows that it can successfully identify and track dynamic communities. Moreover, ALPA could detect communities with high quality and accuracy compared to other methods. Therefore, being low-complexity and parameter-free, ALPA is a scalable and promising solution for some real-world applications of community detection in dynamic networks.

Efficient Detection of Communities in Biological Bipartite Networks.

Methods to efficiently uncover and extract community structures are required in a number of biological applications where networked data and their interactions can be modeled as graphs, and observing tightly-knit groups of vertices ("communities") can offer insights into the structural and functional building blocks of the underlying network. Classical applications of community detection have largely focused on unipartite networks - i.e., graphs built out of a single type of objects. However, due to increased availability of biological data from various sources, there is now an increasing need for handling heterogeneous networks which are built out of multiple types of objects. In this paper, we address the problem of identifying communities from biological bipartite networks - i.e., networks where interactions are observed between two different types of objects (e.g., genes and diseases, drugs and protein complexes, plants and pollinators, and hosts and pathogens). Toward detecting communities in such bipartite networks, we make the following contributions: i) (metric) we propose a variant of bipartite modularity; ii) (algorithms) we present an efficient algorithm called biLouvain that implements a set of heuristics toward fast and precise community detection in bipartite networks (https://github.com/paolapesantez/biLouvain); and iii) (experiments) we present a thorough experimental evaluation of our algorithm including comparison to other state-of-the-art methods to identify communities in bipartite networks. Experimental results show that our biLouvain algorithm identifies communities that have a comparable or better quality (as measured by bipartite modularity) than existing methods, while significantly reducing the time-to-solution between one and four orders of magnitude.

Interest-Based Clustering Approach for Social Networks

Recently, the applications of community detection have increased because of their effectiveness in identifying communities correctly. Many methods and algorithms have been introduced to bring new insights that will improve community detection in social networks. While such algorithms can find useful communities, they tend to focus on network structure and ignore node interests and interconnections. However, accurate community detection requires the consideration of both network structure and node interests. The best method to achieve this is by utilizing unsupervised models. In this article, we introduce a new approach for social network clustering, termed Interest-based Clustering, which clusters nodes in social networks based on a measure of interest similarity. It considers structure, interaction, and node interest along with nodes friends’ interests. The empirical evaluation of this new approach was done using real dataset crawled from Twitter. The approach outperforms well-known community detections algorithms, SCAN, Fast Modularity, Zhao et al., in terms of modularity, connectivity, and overlapping.