Community Detection In Networks Research Articles

Increased Segregation in Functional Connectivity Networks When Watching Unpleasant Arousing Videos: A Generalized Psychophysiological Interaction Analysis.

Background: Properties of functional connectivity (FC), such as network integration and segregation, are shown to be associated with various human behaviors. For example, Godwin et al. and Sun et al. found increased integration with attention allocation, whereas Cohen and D'Esposito and Shine et al. observed increased segregation with simple motor tasks. The current study investigated how viewing video clips with different valence and arousal influenced integration-segregation properties in task-based FC networks. Methods: We analyzed an open dataset collected by Kim et al. We performed a generalized psychophysiological interaction (gPPI) analysis paired with network analysis and community detection to investigate changes in brain network dynamics when people watched four types of videos that differed by affective valence (unpleasant or pleasant) and arousal (arousing or calm). Results: Results showed that unpleasant arousing videos produced greater FC deviation from the baseline (task-induced FC deviation [tiFCd]) and perturbed the brain into a more segregated state than other kinds of video. Increased segregation was only observed in association systems, not sensorimotor systems. Discussion: Unpleasant arousing content perturbed the brain to a functionally distinct state from the other three types of affective videos. We suggest that the change in brain state was related to people disengaging from the unpleasant arousing content or, alternatively, staying alert while exposed to unpleasant arousing stimuli. The study also added to our understanding of how combining task-based gPPI analysis with community detection methods and network segregation measures can advance our knowledge of the links between behavior and brain state changes. Impact statement Network integration and segregation is an important property of the human brain. We address the question of how affective stimuli influence brain dynamics from a functional connectivity (FC) network integration-segregation perspective. By conducting a whole-brain generalized psychophysiological interaction (gPPI) analysis paired with community detection methods, we found that highly aversive video content induced significant FC changes and perturbed the brain to a more segregated state.

Consistent community detection in inter-layer dependent multi-layer networks

Community detection in multi-layer networks, which aims at finding groups of nodes with similar connective patterns among all layers, has attracted tremendous interests in multi-layer network analysis. Most existing methods are extended from those for single-layer networks, which assume that different layers are independent. In this paper, we propose a novel community detection method in multi-layer networks with inter-layer dependence, which integrates the stochastic block model (SBM) and the Ising model. The community structure is modeled by the SBM model and the inter-layer dependence is incorporated via the Ising model. An efficient alternative updating algorithm is developed to tackle the resultant optimization task. Moreover, the asymptotic consistencies of the proposed method in terms of both parameter estimation and community detection are established, which are supported by extensive simulated examples and a real example on a multi-layer malaria parasite gene network.

Regional resilience during COVID-19: evidence from Colombian exporting clusters

ABSTRACT This study characterises the geography of Colombian exporters and their response to the COVID-19 crisis. We define exporting clusters within departments using bipartite network analysis and community detection tools. The methodology empirically detects product communities – groups of products that are strongly related – which are compared with an alternative taxonomy of industrial clusters, and clusters exporting firms by considering their exports within these taxonomies. We define these groups of specialised firms localised in departments as exporting clusters. We then examine whether belonging to an exporting cluster can enhance firms’ trade margins. We find that clusters do not automatically improve firms’ trade margins and that there are differences in how firms react to a crisis within clusters. Our analysis contributes to regional studies by shedding light on the potential of exporters’ agglomerations to navigate and recover from crises and outlining critical firm characteristics that can strengthen regional resilience.

Deep Adaptive Graph Clustering via von Mises-Fisher Distributions

Graph clustering has been a hot research topic and is widely used in many fields, such as community detection in social networks. Lots of works combining auto-encoder and graph neural networks have been applied to clustering tasks by utilizing node attributes and graph structure. These works usually assumed the inherent parameters (i.e., size and variance) of different clusters in the latent embedding space are homogeneous, and hence the assigned probability is monotonous over the Euclidean distance between node embeddings and centroids. Unfortunately, this assumption usually does not hold since the size and concentration of different clusters can be quite different, which limits the clustering accuracy. In addition, the node embeddings in deep graph clustering methods are usually L2 normalized so that it lies on the surface of a unit hyper-sphere. To solve this problem, we proposed D eep A daptive G raph C lustering via von Mises-Fisher distributions, namely DAGC. DAGC assumes the node embeddings H can be drawn from a von Mises-Fisher distribution and each cluster k is associated with cluster inherent parameters ρ k which includes cluster center μ and cluster cohesion degree κ. Then we adopt an EM-like approach (i.e., 𝒫( H | ρ ) and 𝒫( ρ | H ), respectively) to learn the embedding and cluster inherent parameters alternately. Specifically, with the node embeddings, we proposed to update the cluster centers in an attraction-repulsion manner to make the cluster centers more separable. And given the cluster inherent parameters, a likelihood-based loss is proposed to make node embeddings more concentrated around cluster centers. Thus, DAGC can simultaneously improve the intra-cluster compactness and inter-cluster heterogeneity. Finally, extensive experiments conducted on four benchmark datasets have demonstrated that the proposed DAGC consistently outperforms the state-of-the-art methods, especially on imbalanced datasets.

DMRFO-CD: a discrete manta ray foraging inspired optimisation algorithm for community detection in networks

DMRFO-CD: a discrete manta ray foraging inspired optimisation algorithm for community detection in networks

Weighted Feature Selection for Machine Learning Based Accurate Intrusion Detection in Communication Networks

Weighted Feature Selection for Machine Learning Based Accurate Intrusion Detection in Communication Networks

Reinforcement-Learning-Based Intrusion Detection in Communication Networks: A Review

Reinforcement-Learning-Based Intrusion Detection in Communication Networks: A Review

Optimizing SNARK networks via double metric dimension

<p>Doubly resolving sets (DRSs) provide a promising approach for source detection. They consist of minimal subsets of nodes with the smallest cardinality, referred to as the double metric dimension (DMD), that can uniquely identify the location of any other node within the network. Utilizing DRSs can improve the accuracy and efficiency of the identification of the origin of a diffusion process. This ability is crucial for early intervention and control in scenarios such as epidemic outbreaks, misinformation spreading in social media, and fault detection in communication networks. In this study, we computed the DMD of flower snarks $ J_{m} $ and quasi-flower snarks $ G_{m} $ by describing their minimal doubly resolving sets (MDRSs). We deduce that the DMD for the flower snarks $ J_{m} $ is finite and depends on the network's order, and the DMD for the quasi-flower snarks $ G_{m} $ is finite and independent of the network's order. Furthermore, our findings offer valuable insights into the structural features of complex networks. This knowledge can offer direction for future studies in network theory and its practical implementations.</p>

LB-SAM: Local Beam Search with Simulated Annealing for Community Detection in Large-Scale Social Networks

LB-SAM: Local Beam Search with Simulated Annealing for Community Detection in Large-Scale Social Networks

Community detection in temporal citation network via a tensor-based approach

Community detection in temporal citation network via a tensor-based approach

Multiplex Community Detection in Social Networks Using a Chaos‐Based Hybrid Evolutionary Approach

Multiplex Community Detection in Social Networks Using a Chaos‐Based Hybrid Evolutionary Approach

Multi-Graph Contrastive Learning for Community Detection in Multi-Layer Networks

Multi-Graph Contrastive Learning for Community Detection in Multi-Layer Networks

Robust Overlapping Community Detection in Complex Networks With Graph Convolutional Networks and Fuzzy C-Means

Robust Overlapping Community Detection in Complex Networks With Graph Convolutional Networks and Fuzzy C-Means

Community Detection in Social Networks Using a Local Approach Based on Node Ranking

Community Detection in Social Networks Using a Local Approach Based on Node Ranking

Bayesian Community Detection for Networks with Covariates

Bayesian Community Detection for Networks with Covariates

Towards improving community detection in complex networks using influential nodes

Abstract Complex network analysis is inspired by empirical studies of real-world networks such as computer networks, technology networks and social networks. The analysis of community structure in complex networks is understood as an important issue by the research society. A community is a set of nodes in a network where the density of connections is high. The insight in the literature shows many approaches to identify influential nodes, but these approaches only lead to finding community centres. Meanwhile, clustering techniques are effectively used for community detection, where they can reveal group structure and hidden connections by considering topological and demographic information. This article presents an ensemble clustering algorithm based on influential nodes to improve community detection in complex networks. Considering different characteristics of the network, the proposed method seeks to discover common interests between users and their behaviours to identify the most suitable communities. First, a set of influential nodes are identified as community centres. Then, these centres are considered as cluster centres. After that, primary clusters are created based on the determined centres. Finally, the primary clusters are reclustered to form the final clusters. Here, the final clusters are considered as communities of users in the network. The simulation has been performed on real-world networks and the results confirm the effectiveness of the proposed method. Specifically, the communities identified by the proposed method are 2.1% better than the best existing state-of-the-art method in terms of modularity. Keywords: complex network; community detection; influential nodes; ensemble clustering.

Higher-order interactions disturb community detection in complex networks

Edges are the most basic structures in complex networks, representing relationships of node pairs. However, many higher-order interactions in reality are beyond node-to-node relationships. In recent years, the conceptualization of “higher-order structures” is considered to provide information on multiple scales, which is helpful to discover new conclusions or achieve better results in issues such as propagation, synchronization, and evolution. But for community identification, the impact of higher-order interactions may not be positive. In this study, we discovered that higher-order interactions disproportionately increase the count of edges. This poses a substantial challenge for community detection, especially when we found that higher-order interactions tend to cross multiple communities. The existence of higher-order interactions obscures the community structure in the network. And once we realize this, removing some of the higher-order interactions is an easy way to improve the accuracy of community detection.

Linking social motivation, general motivation, and social cognition to interpersonal functioning in schizophrenia: insights from exploratory graph analysis

Motivation in general, and social motivation in particular are important for interpersonal functioning in individuals with schizophrenia. Still, their roles after accounting for social cognition, are not well understood. The sample consisted of 147 patients with schizophrenia. General motivation was measured using the Behavioral inhibition/activation scale (BIS/BAS). Social motivation was measured by Passive social withdrawal and Active social avoidance items from PANSS. Interpersonal functioning was evaluated with Birchwood’s Social Functioning Scale (SFS). We used Exploratory Graph Analysis for network estimation and community detection. Active social avoidance, passive social withdrawal, and social withdrawal/engagement (from SFS) were the most important nodes. In addition, three distinct communities were identified: Social cognition, Social motivation, and Interpersonal functioning. Notably, the BIS and BAS measures of general motivation were not part of any community. BAS showed stronger links to functioning than BIS. Passive social withdrawal was more strongly linked to interpersonal functioning than social cognitive abilities. Results suggest that social motivation, especially social approach, is more closely related to interpersonal functioning in schizophrenia than general motivation. In contrast, we found that general motivation was largely unrelated to social motivation. This pattern highlights the importance of type of motivation for understanding variability in interpersonal difficulties in schizophrenia.

Community detection in social networks by spectral embedding of typed graphs

Community detection in social networks by spectral embedding of typed graphs

Improved brain community structure detection by two-step weighted modularity maximization

The human brain can be regarded as a complex network with interacting connections between brain regions. Complex brain network analyses have been widely applied to functional magnetic resonance imaging (fMRI) data and have revealed the existence of community structures in brain networks. The identification of communities may provide insight into understanding the topological functions of brain networks. Among various community detection methods, the modularity maximization (MM) method has the advantages of model conciseness, fast convergence and strong adaptability to large-scale networks and has been extended from single-layer networks to multilayer networks to investigate the community structure changes of brain networks. However, the problems of MM, suffering from instability and failing to detect hierarchical community structure in networks, largely limit the application of MM in the community detection of brain networks. In this study, we proposed the weighted modularity maximization (WMM) method by using the weight matrix to weight the adjacency matrix and improve the performance of MM. Moreover, we further proposed the two-step WMM method to detect the hierarchical community structures of networks by utilizing node attributes. The results of the synthetic networks without node attributes demonstrated that WMM showed better partition accuracy than both MM and robust MM and better stability than MM. The two-step WMM method showed better accuracy of community partitioning than WMM for synthetic networks with node attributes. Moreover, the results of resting state fMRI (rs-fMRI) data showed that two-step WMM had the advantage of detecting the hierarchical communities over WMM and was more insensitive to the density of the rs-fMRI networks than WMM.