Community Discovery Algorithm Research Articles

Towards Integrating Federated Learning with Split Learning via Spatio-temporal Graph Framework for Brain Disease Prediction.

Functional Magnetic Resonance Imaging (fMRI) is used for extracting blood oxygen signals from brain regions to map brain functional connectivity for brain disease prediction. Despite its effectiveness, fMRI has not been widely used: on the one hand, collecting and labeling the data is time-consuming and costly, which limits the amount of valid data collected at a single healthcare site; on the other hand, integrating data from multiple sites is challenging due to data privacy restrictions. To address these issues, we propose a novel, integrated Federated learning and Split learning Spatio-temporal Graph framework (FS2G). Specifically, we introduce federated learning and split learning techniques to split a spatio-temporal model into a client temporal model and a server spatial model. In the client temporal model, we propose a time-aware mechanism to focus on changes in brain functional states and use an InceptionTime model to extract information about changes in the brain states of each subject. In the server spatial model, we propose a united graph convolutional network to integrate multiple graph convolutional networks. Integrating federated learning and split learning, FS2G can utilize multi-site fMRI data without violating data privacy protection and reduce the risk of overfitting as it is capable of learning from limited training data sets. Moreover, it boosts the extraction of spatio-temporal features of fMRI using spatio-temporal graph networks. Experiments on ABIDE and ADHD200 datasets demonstrate that our proposed method outperforms state-of-the-art methods. In addition, we explore biomarkers associated with brain disease prediction using community discovery algorithms using intermediate results of FS2G. The source code is available at https://github.com/yutian0315/FS2G.

Exploring an adaptive management model for “status-optimization-regulation” of mining city in transition: A case study of Huangshi, China

Mining cities face the challenges of ecological transformation and sustainable development after mineral depletion. Thus, ecological space optimization and adaptive management are pivotal after ecological restoration project, but easily neglected. Taking Huangshi in Hubei Province as an example, a top-down adaptive management model for regional mining ecological space integrating status-optimization-regulation (SOR) was established based on land system resilience (LSR) evaluation, circuit theory, complex network model and community discovery algorithm. The results showed that i) As the LSR increased, the land use structure shifted from non-ecological zones to forest and cropland, indicating that balancing agriculture and forest protection was crucial for increasing LSR in Huangshi. i) The ecological networks (ENs) of Huangshi had an irregular fishnet pattern, with densely intricate corridors in the south and broader, sparser ones in the north, and numerous ecological barriers near the mining area. Furthermore, the distribution of ecological sources and corridors displayed complementarity and hierarchy. iii) The optimized ENs exhibited higher connectivity and efficiency under disturbance, reducing corridor redundancy and migration costs. iv) The ENs clusters were classified into five types based on ecological connectivity: ecological buffer zone, priority restoration zone, moderate restoration zone, natural restoration zone, and moderate development zone, and tailored ecological regulatory strategies were proposed. The findings provide practice-oriented guidance for the sustainable development of mining cities, and offer a direct approach to support conscious, clear, and coherent adaptive management of ecological restoration in rapidly changing environments.

NDI-PPO: Node degree increment-based proximal policy optimization method for employment community discovery in online social networks

Purpose: aiming at the limitations of pre-input parameters in the complex network overlapping community discovery algorithm based on tag propagation in real networks and the problems of tag redundancy, method: a node degree increment-based proximal policy optimization method for community discovery in online social networks is proposed (named NDI-PPO). Process: by applying the cohesion idea and introducing the concept of modularity increment, a social network great community is constructed from the bottom up according to the criteria of community division. For the problem that the number of iterative steps is sensitive to the strategy gradient algorithm, we adopt an improved PPO to improve the efficiency of feature extraction. In label updating, the maximum clique is used as the core unit to update the labels and weights of the maximum maximum clique adjacent nodes from the center to the periphery using intimacy, and the weights of the non-maximum maximum clique adjacent nodes are updated by means of the maximum weight. In the post-processing stage, the adaptive threshold method is used to remove the noise in the node label, which effectively overcomes the limitation of the number of pre-input overlapping communities in the real network. Result: The simulation results show that the proposed community discovery algorithm NDI-PPO is superior to other advanced algorithms, the time complexity is greatly reduced, and it is suitable for community discovery in large social networks.

A novel three-phase expansion algorithm for uncovering communities in social networks using local influence and similarity in embedding space

Community detection can help uncover and understand complex networks’ underlying patterns and structures. It involves identifying cohesive groups with similar entities while being separated from other groups. Social networks are a prime example of an area where community detection is particularly relevant, as it can provide insight into the behaviors of individuals. Several community detection methods have been proposed, each addressing the problem from different perspectives. However, the rise of vast and intricate networks from diverse domains has necessitated the development of community detection methods that can effectively handle large-scale graphs. This study introduces a novel three-phase expansion algorithm for community discovery based on nodes’ local information and similarity in embedding space. The proposed model consists of three steps. In the first stage, we generate an embedding space in which nodes are represented as vectors, and we extract nodes that greatly influence others and have an extraordinary ability to create communities using degree centrality measures. Then, based on cosine similarity in the embedding space, we group the most similar nodes to the influential ones in the same community and create an initial community structure. In the last phase, we extract the weak communities from the initial community structure generated in the second phase and merge them with the strong ones. We conduct extensive experiments on both real-world and synthetic networks to demonstrate the effectiveness of our proposal. The experimental results show that the proposed algorithm performs better than other widely used algorithms and is highly reliable and efficient in large-scale graphs.

Analysis of a Multiple Traffic Flow Network’s Spatial Organization Pattern Recognition Based on a Network Map

Detecting the spatial organization patterns of urban networks with multiple traffic flows from the perspective of complex networks and traffic behavior will help to optimize the urban spatial structure and thereby promote the sustainable development of the city. However, there are notable differences in regional spatial patterns among the different modes of transportation. Based on the road, railway, and air frequency data, this article investigates the spatial distribution and accessibility patterns of multiple transportation flows in the Yangtze River Economic Belt. Next, we use the TCD (Transportation Cluster Detection) community discovery algorithm and integrate it with the Baidu Maps API to obtain real-time time cost data to construct a community detection model of a multiple traffic flow network. We integrate the geographical network and topological network to perform feature extraction and rule mining on the spatial organization model of the urban network in the Yangtze River Economic Belt. The results show that: (1) The multiple traffic flow network of the Yangtze River Economic Belt has significant spatial differentiation. The spatial differentiation of aviation and railway networks is mainly concentrated between regions and within provinces, while the imbalance of highway networks is manifested as an imbalance within regions and between provinces. (2) The accessibility pattern of the highway network in the Yangtze River Economic Belt presents a “core–edge” spatial pattern. The accessibility pattern of the railway network generally presents a spatial pattern of “strong in the east and weak in the west”. Compared with sparse road and railway networks, the accessibility pattern of the aviation network shows a spatial pattern of “time and space compression in western cities”. (3) A total of 24 communities were identified through the TCD algorithm, mainly encompassing six major “urban economic communities” located in Guizhou, Yunnan, Anhui, Sichuan–Chongqing, Hubei–Hunan–Jiangxi, and Jiangsu–Zhejiang–Shanghai. (4) The urban network space organization model of the Yangtze River Economic Belt can be roughly divided into three models: the “single-core” model, with Guizhou, Kunming, and Hefei as the core, the “dual-core” model, constructed by Chengdu–Chongqing, and the “multi-core” model, constructed by Changsha–Wuhan–Nanchang and Shanghai–Nanjing–Hangzhou. This model of urban network spatial organization holds indicative significance in revealing the spatial correlation pattern among prefecture-level city units.

Label propagation algorithm for community discovery based on centrality and common neighbours

Label propagation algorithm for community discovery based on centrality and common neighbours

Cover Image

The cover image is based on the Original Article Research on symptoms composition, time series evolution, and network visualisation of interstitial cystitis based on complex network community discovery algorithm by Lei Pang et al., https://doi.org/10.1049/syb2.12083image

ECDEP: identifying essential proteins based on evolutionary community discovery and subcellular localization

BackgroundIn cellular activities, essential proteins play a vital role and are instrumental in comprehending fundamental biological necessities and identifying pathogenic genes. Current deep learning approaches for predicting essential proteins underutilize the potential of gene expression data and are inadequate for the exploration of dynamic networks with limited evaluation across diverse species.ResultsWe introduce ECDEP, an essential protein identification model based on evolutionary community discovery. ECDEP integrates temporal gene expression data with a protein–protein interaction (PPI) network and employs the 3-Sigma rule to eliminate outliers at each time point, constructing a dynamic network. Next, we utilize edge birth and death information to establish an interaction streaming source to feed into the evolutionary community discovery algorithm and then identify overlapping communities during the evolution of the dynamic network. SVM recursive feature elimination (RFE) is applied to extract the most informative communities, which are combined with subcellular localization data for classification predictions.We assess the performance of ECDEP by comparing it against ten centrality methods, four shallow machine learning methods with RFE, and two deep learning methods that incorporate multiple biological data sources on Saccharomyces. Cerevisiae (S. cerevisiae), Homo sapiens (H. sapiens), Mus musculus, and Caenorhabditis elegans. ECDEP achieves an AP value of 0.86 on the H. sapiens dataset and the contribution ratio of community features in classification reaches 0.54 on the S. cerevisiae (Krogan) dataset.ConclusionsOur proposed method adeptly integrates network dynamics and yields outstanding results across various datasets. Furthermore, the incorporation of evolutionary community discovery algorithms amplifies the capacity of gene expression data in classification.

Model-data matching method for natural disaster emergency service scenarios: implementation based on a knowledge graph and community discovery algorithm

Model-data matching method for natural disaster emergency service scenarios: implementation based on a knowledge graph and community discovery algorithm

Research on symptoms composition, time series evolution, and network visualisation of interstitial cystitis based on complex network community discovery algorithm.

We analyzed the symptoms composition of Interstitial Cystitis (IC), the regularity of the evolution of symptoms before and after treatment, and the visualization of the community network, to provide a reference for clinical diagnosis and treatment of Interstitial Cystitis. Based on the outpatient electronic case data of 552 patients with Interstitial Cystitis, we used a complex network community discovery algorithm, directed weighted complex network, and Sankey map to mine the data of the symptoms composition of Interstitial Cystitis, the evolution of symptoms before and after treatment and the visualization of the community network, to analyze the epidemiological characteristics of interstitial cystitis symptoms in the real world. By the community division of the complex network of interstitial cystitis symptoms, We finally obtained three core symptom communities. Among them, symptom community A (bladder-related symptoms) is the symptom community with the highest proportion of nodes (60.00%) in the complex network of Interstitial Cystitis, symptom community B (non-bladder-related symptoms 1) ranks second (32.00%) in a complex network of Interstitial Cystitis, and symptom community C (non-bladder-related symptoms 2) has the lowest proportion (8.00%). There is a complex evolutionary relationship between the symptoms of Interstitial Cystitis before and after treatment. Among the single symptoms before and after treatment, the decreased rate of Day frequency is 93.22%, and the reduced urgency rate is 93.07%. The decline rate of Nocturia was 82.33%. From the perspective of different communities, theoverall symptoms of symptom community A decreased by 34.39% after treatment, the general symptoms of symptom community B decreased by 35.37%, and the prevalent symptoms of symptom community C decreased by 71.43%. In the case of using diet regulation treatment to treat bladder pain, the cure rate of bladder pain can reach 22.67%. The cure rate of burning in bladders can get 15.38% with Percutaneous Sacral neuromodulation, 96.95% with diet regulation treatment, and 100% with Percutaneous Sacral neuromodulation. When using behavioral physiotherapy to treat bladder pain, 3.57% of the patient's symptoms change to bladder discomfort; 4% of the patient's symptoms change to bladder discomfort when using oral medicine to treat bladder pain.Symptom research methods based on community findings can effectively explore the rule of symptom outcome of Interstitial Cystitis before and after treatment, and the results are highly interpretable by professionals. The cover image is based on the Original Article Research on symptoms composition, time series evolution, and network visualisation of interstitial cystitis based on complex network community discovery algorithm by Lei Pang etal., https://doi.org/10.1049/syb2.12083.

Application and Research of Multi-Feature Fusion Tag Propagation Computer Algorithm in Image Search and Matching

When analyzing the advantages and disadvantages of common community discovery algorithms, the paper points out that the label propagation algorithm (LPA) has low time complexity, does not need to set the number of communities in advance, and the calculation process is simple. When dealing with large and complex networks, it has high the characteristics of efficiency. However, the algorithm does not consider the similarity of adjacent nodes in the network structure and content in the process of label propagation. Therefore, from the perspective of node similarity, the paper proposes a multi-feature fusion label propagation algorithm. The algorithm first uses the Sim Rank algorithm to calculate the structural similarity of the nodes in the network, and at the same time uses the main body model to obtain the topic distribution of the node content, and calculates the similarity of the topic distribution of different nodes, and finally merges the two similarities to be the label propagated by adjacent nodes, Give the corresponding weight to improve the communication strategy. Experimental comparison shows that this algorithm is better than the traditional label propagation algorithm.

Combining Global-Constrained Concept Factorization and a Regularized Gaussian Graphical Model for Clustering Single-Cell RNA-seq Data.

Single-cell RNA sequencing technology is one of the most cost-effective ways to uncover transcriptomic heterogeneity. With the rapid rise of this technology, enormous amounts of scRNA-seq data have been produced. Due to the high dimensionality, noise, sparsity and missing features of the available scRNA-seq data, accurately clustering the scRNA-seq data for downstream analysis is a significant challenge. Many computational methods have been designed to address this issue; nevertheless, the efficacy of the available methods is still inadequate. In addition, most similarity-based methods require a number of clusters as input, which is difficult to achieve in real applications. In this study, we developed a novel computational method for clustering scRNA-seq data by considering both global and local information, named GCFG. This method characterizes the global properties of data by applying concept factorization, and the regularized Gaussian graphical model is utilized to evaluate the local embedding relationship of data. To learn the cell-cell similarity matrix, we integrated the two components, and an iterative optimization algorithm was developed. The categorization of single cells is obtained by applying Louvain, a modularity-based community discovery algorithm, to the similarity matrix. The behavior of the GCFG approach is assessed on 14 real scRNA-seq datasets in terms of ACC and ARI, and comparison results with 17 other competitive methods suggest that GCFG is effective and robust.

CDRKD: An improved density peak algorithm based on kernel fuzzy measure in the overlapping community detection

Compared with other traditional community discovery algorithms, density peak clustering algorithm is more efficient in getting network structures through clustering. However, DPC needs to contain the distance information between all nodes as sources, so it cannot directly processing the complex network represented by the adjacency matrix. DPC introduces truncation distance when calculating the local density of nodes, which is usually set as a fixed value according to experience, and lacks self-adaptability for different network structures. A feasible solution to those problems is to combined rough set theory and kernel fuzzy similarity measures. In this work, we present overlapping community detection algorithm based on improved rough entropy fusion density peak. The algorithm applied rough set theory to attribute reduction of massive high-dimensional data. Another algorithm defines the similarity of sample points by the inner product between two vectors on the basis of fuzzy partition matrix. Finally, a community detection algorithm based on rough entropy and kernel fuzzy density peaks clustering (CDRKD) has proposed by combining the two algorithms above, we perform an extensive set of experiments to verify the effectiveness and feasibility of the algorithm.

Improving temporal smoothness and snapshot quality in dynamic network community discovery using NOME algorithm.

The goal of dynamic community discovery is to quickly and accurately mine the network structure for individuals with similar attributes for classification. Correct classification can effectively help us screen out more desired results, and it also reveals the laws of dynamic network changes. We propose a dynamic community discovery algorithm, NOME, based on node occupancy assignment and multi-objective evolutionary clustering. NOME adopts the multi-objective evolutionary algorithm MOEA/D framework based on decomposition, which can simultaneously decompose the two objective functions of modularization and normalized mutual information into multiple single-objective problems. In this algorithm, we use a Physarum-based network model to initialize populations, and each population represents a group of community-divided solutions. The evolution of the population uses the crossover and mutation operations of the genome matrix. To make the population in the evolution process closer to a better community division result, we develop a new strategy for node occupancy assignment and cooperate with mutation operators, aiming at the boundary nodes in the connection between the community and the connection between communities, by calculating the comparison node. The occupancy rate of the community with the neighbor node, the node is assigned to the community with the highest occupancy rate, and the authenticity of the community division is improved. In addition, to select high-quality final solutions from candidate solutions, we use a rationalized selection strategy from the external population size to obtain better time costs through smaller snapshot quality loss. Finally, comparative experiments with other representative dynamic community detection algorithms on synthetic and real datasets show that our proposed method has a better balance between snapshot quality and time cost.

Overlapping community detection algorithm based on similarity of node relationship

Community discovery is a vital link in the research of social networks aiming at the shortcomings of the current local extension-based community discovery algorithm in local community discovery and extension. In this paper, we proposed a algorithm based on relationship similarity and local extension overlapping community detection (RSLO). First, use the node's relationship similarity strategy to find close seed communities. Then, according to the discovered seed community, the similarity between the neighboring nodes of the community and the community is calculated, and the nodes whose similarity meets the threshold are selected. After that, an adaptive optimization function is used to expand the community. Finally, the free nodes that have not been divided into the community are divided into communities, thereby achieving a more comprehensive community discovery. We conduct experiments on classic datasets and artificially generated networks. The results show that the RSLO algorithm can find accurate and objective community structures.

Identification of key genes involved in neural regeneration and the repairing effect of BDNF-overexpressed BMSCs on spinal cord ischemia-reperfusion injury in rats

Bone marrow mesenchymal stem cells (BMSCs) can repair spinal cord ischemia-reperfusion injury (SCII); however, only a few BMSCs are usually located in the injured spinal cord. Since the brain-derived neurotrophic factor (BDNF) can promote neural development and maturation, we hypothesised that BDNF-overexpressed BMSCs can ameliorate SCII more effectively than BMSCs alone. To determine the effect of BDNF overexpression on SCII repair, BDNF-overexpressed BMSCs and BMSCs were transplanted into SCII rats. Our results revealed that BDNF-overexpressed BMSCs can better promote the recovery of damaged spinal cords than BMSCs alone. Gene chip detection of spinal cord tissues showed 803 differentially expressed genes in all groups. BTG anti-proliferation factor 2 (Btg2), FOS like 2 (Fosl2), early growth response protein 1 (Egr1), and serpin family E member 1 (Serpine1) were identified as key interrelated genes based on their expression trends, as validated via quantitative PCR and protein–protein interaction network analysis. A co-expression network was constructed to further explore the role of the candidate key genes using Pearson correlation analysis. Cluster 5 was identified as the key cluster using community discovery algorithms. Functional analysis of Cluster 5 genes revealed that this cluster was mainly involved in the stress-activated MAPK cascade, p38MAPK cascade, and apoptosis. Notably, Egr1 may play an important role in SCII repair as the top hub gene in Cluster 5. Therefore, the repair activity of transplanted BDNF-overexpressed BMSCs in SCII rats is better than that of BMSCs alone, which may be regulated by the interactions between Btg2, Fosl2, Egr1, Serpine1, and BDNF.

Community Discovery Algorithm Based on Multi-Relationship Embedding

Complex systems in the real world often can be modeled as network structures, and community discovery algorithms for complex networks enable researchers to understand the internal structure and implicit information of networks. Existing community discovery algorithms are usually designed for single-layer networks or single-interaction relationships and do not consider the attribute information of nodes. However, many real-world networks consist of multiple types of nodes and edges, and there may be rich semantic information on nodes and edges. The methods for single-layer networks cannot effectively tackle multi-layer information, multi-relationship information, and attribute information. This paper proposes a community discovery algorithm based on multi-relationship embedding. The proposed algorithm first models the nodes in the network to obtain the embedding matrix for each node relationship type and generates the node embedding matrix for each specific relationship type in the network by node encoder. The node embedding matrix is provided as input for aggregating the node embedding matrix of each specific relationship type using a Graph Convolutional Network (GCN) to obtain the final node embedding matrix. This strategy allows capturing of rich structural and attributes information in multi-relational networks. Experiments were conducted on different datasets with baselines, and the results show that the proposed algorithm obtains significant performance improvement in community discovery, node clustering, and similarity search tasks, and compared to the baseline with the best performance, the proposed algorithm achieves an average improvement of 3.1% on Macro-F1 and 4.7% on Micro-F1, which proves the effectiveness of the proposed algorithm.

Towards explainable community finding.

The online version contains supplementary material available at 10.1007/s41109-022-00515-6.

How to Protect Ourselves From Overlapping Community Detection in Social Networks

In recent years, overlapping community detection algorithms have been paid more and more attention, which not only reveal the real social relations, but also expose the possible communication channels between communities. Those individuals (or people) in the overlapping area are very important to the communities that can promote communication between two or more communities. On the other hand, from the privacy perspective, some people may not want to be found out in the overlapping areas. With this in mind, we raise a question “Can individuals modify their relationships to avoid the community discovery algorithms locating them into overlapping areas?” If this problem could be solved, these people may not need to worry about being disturbed. In particular, we first give three heuristic hiding strategies, i.e., Random Hiding(RH), Based Degree Hiding(DH) and Betweenness Hiding(BH), as comparison, utilizing the randomly the node, information of node degree and node betweenness centrality, respectively. And then, we propose a novel hiding algorithm by exploiting the importance degree of nodes in communities based on which the corresponding social connections are added or deleted called name <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">BIH</i> . Through extensive experiments, we show the effectiveness of the proposed algorithm in moving out a target node from overlapped areas.

Correlation Analysis of Variables From the Atherosclerosis Risk in Communities Study.

The need to test chemicals in a timely and cost-effective manner has driven the development of new alternative methods (NAMs) that utilize in silico and in vitro approaches for toxicity prediction. There is a wealth of existing data from human studies that can aid in understanding the ability of NAMs to support chemical safety assessment. This study aims to streamline the integration of data from existing human cohorts by programmatically identifying related variables within each study. Study variables from the Atherosclerosis Risk in Communities (ARIC) study were clustered based on their correlation within the study. The quality of the clusters was evaluated via a combination of manual review and natural language processing (NLP). We identified 391 clusters including 3,285 variables. Manual review of the clusters containing more than one variable determined that human reviewers considered 95% of the clusters related to some degree. To evaluate potential bias in the human reviewers, clusters were also scored via NLP, which showed a high concordance with the human classification. Clusters were further consolidated into cluster groups using the Louvain community finding algorithm. Manual review of the cluster groups confirmed that clusters within a group were more related than clusters from different groups. Our data-driven approach can facilitate data harmonization and curation efforts by providing human annotators with groups of related variables reflecting the themes present in the data. Reviewing groups of related variables should increase efficiency of the human review, and the number of variables reviewed can be reduced by focusing curator attention on variable groups whose theme is relevant for the topic being studied.