Graph Community Research Articles

Community Graph Convolution Neural Network for Alzheimer's Disease Classification and Pathogenetic Factors Identification.

As a complex neural network system, the brain regions and genes collaborate to effectively store and transmit information. We abstract the collaboration correlations as the brain region gene community network (BG-CN) and present a new deep learning approach, such as the community graph convolutional neural network (Com-GCN), for investigating the transmission of information within and between communities. The results can be used for diagnosing and extracting causal factors for Alzheimer's disease (AD). First, an affinity aggregation model for BG-CN is developed to describe intercommunity and intracommunity information transmission. Second, we design the Com-GCN architecture with intercommunity convolution and intracommunity convolution operations based on the affinity aggregation model. Through sufficient experimental validation on the AD neuroimaging initiative (ADNI) dataset, the design of Com-GCN matches the physiological mechanism better and improves the interpretability and classification performance. Furthermore, Com-GCN can identify lesioned brain regions and disease-causing genes, which may assist precision medicine and drug design in AD and serve as a valuable reference for other neurological disorders.

Exploring Cytokine Networks in Resistant Hypertension.

Controlling high blood pressure (BP) continues to be a major concern because the associated complications can lead to an increased risk of heart, brain, and kidney disease. Those with hypertension, despite lifestyle and diet modifications and pharmacotherapy, defined as resistant hypertension, are at increased risk for further risk for morbidity and mortality. Understanding inflammation in this population may provide novel avenues for treatment. This study aimed to examine a broad range of cytokines in adults with cardiovascular disease and identify specific cytokines associated with resistant hypertension. A secondary data analysis was conducted. The parent study included 156 adults with a history of myocardial infarction within the past 3-7 years and with a multiplex plasma analysis yielding a cytokine panel. A network analysis with lasso penalization for sparsity was performed to explore associations between cytokines and BP. Associated network centrality measures by cytokine were produced, and a community graph was extracted. A sensitivity analysis BP was also performed. Cytokines with larger node strength measures were sTNFR2 and CX3. The graphical network highlighted six cytokines strongly associated with resistant hypertension. Cytokines IL-29 and CCL3 were found to be negatively associated with resistant hypertension, whereas CXCL12, MMP3, sCD163, and sIL6Rb were positively associated with resistant hypertension. Understanding the network of associations through exploring oxidative stress and vascular inflammation may provide insight into treatment approaches for resistant hypertension.

Detecting and generating overlapping nested communities

Nestedness has been observed in a variety of networks but has been primarily viewed in the context of bipartite networks. Numerous metrics quantify nestedness and some clustering methods identify fully nested parts of graphs, but all with similar limitations. Clustering approaches also fail to uncover the overlap between fully nested subgraphs, as they assign vertices to a single group only. In this paper, we look at the nestedness of a network through an auxiliary graph, in which a directed edge represents a nested relationship between the two corresponding vertices of the network. We present an algorithm that recovers this so-called community graph, and finds the overlapping fully nested subgraphs of a network. We also introduce an algorithm for generating graphs with such nested structure, given by a community graph. This algorithm can be used to test a nested community detection algorithm of this kind, and potentially to evaluate different metrics of nestedness as well. Finally, we evaluate our nested community detection algorithm on a large variety of networks, including bipartite and non-bipartite ones, too. We derive a new metric from the community graph to quantify the nestedness of both bipartite and non-bipartite networks.

Community Channel-Net: Efficient channel-wise interactions via community graph topology

The layer-wise structure of deep neural networks (DNNs) isolates the channel interactions in the same layer, which significantly impedes the efficient learning of DNNs. Several existing methods enable channel-wise information exchange via learning channel interdependence in a heuristic and empirical manner. Nevertheless, only informative channels are emphasized while other channels are suppressed in these approaches. This results in a low channel diversity, which impeds the generalization of DNNs. Our work aims to learn channel-wise interdependence and keep the channel diversity concurrently via designing optimal channel interaction patterns. We model the channel interaction pattern from a graph perspective, where the interactions can be regarded as information exchange on the channel graph. Based on this framework, we propose the Community Channel-Net (CC-Net), using a community-based graph topology for channel interaction. Each community contains channels with semantic commonalities, and the inter-community connections are activated among critical channels. With this structured and dynamic topology, the channels from the same community can learn channel interdependence, and those critical channels from distinct communities can gain more diverse features. CC-Net outperforms baselines on image classification tasks over various backbones with fewer computational costs.

Explainable AI in big data intelligence of community detection for digitalization e-healthcare services

Recommender Systems are designed to analysis the available data in the system to predict user’s desires and provide appropriate personalized suggestions to each user that suits their interests. In this paper, we have developed an explainable medical recommender system that uses graph concepts to provide an interpretable approach to medical data. The presented approach is based on community detection algorithms. It forms a graph between the users based on their similarity scores. Individuals with common interests are then grouped using graph community detection algorithms. Two community detection algorithms have been applied on the graphs of users and physicians in our medical recommender system. The results of applying two community detection algorithms are then used to address the cold start problem. We have identified the most influential users using a graph-based technique that finds the overlapping communities. We claim that using the overlapping graph of communities to address cold start problem will enhance the accuracy of the recommendations. Weighting or voting systems are also applied on the selected users to give feedback to potential consumers where there are n different options in a cluster. The similarity score of the users in the overlapping communities has been used to weight the final recommendation. The accuracy of recommended services depends on the proper selection of target populations. The proposed approach outperforms the use of each one of the community detections separately. The accuracy and precision of the proposed method are 93.06 and 88.34, which exceed the highest achieved accuracy in the literature.

CommunityGCN: community detection using node classification with graph convolution network

PurposeA community demonstrates the unique qualities and relationships between its members that distinguish it from other communities within a network. Network analysis relies heavily on community detection. Despite the traditional spectral clustering and statistical inference methods, deep learning techniques for community detection have grown in popularity due to their ease of processing high-dimensional network data. Graph convolutional neural networks (GCNNs) have received much attention recently and have developed into a potential and ubiquitous method for directly detecting communities on graphs. Inspired by the promising results of graph convolutional networks (GCNs) in analyzing graph structure data, a novel community graph convolutional network (CommunityGCN) as a semi-supervised node classification model has been proposed and compared with recent baseline methods graph attention network (GAT), GCN-based technique for unsupervised community detection and Markov random fields combined with graph convolutional network (MRFasGCN).Design/methodology/approachThis work presents the method for identifying communities that combines the notion of node classification via message passing with the architecture of a semi-supervised graph neural network. Six benchmark datasets, namely, Cora, CiteSeer, ACM, Karate, IMDB and Facebook, have been used in the experimentation.FindingsIn the first set of experiments, the scaled normalized average matrix of all neighbor's features including the node itself was obtained, followed by obtaining the weighted average matrix of low-dimensional nodes. In the second set of experiments, the average weighted matrix was forwarded to the GCN with two layers and the activation function for predicting the node class was applied. The results demonstrate that node classification with GCN can improve the performance of identifying communities on graph datasets.Originality/valueThe experiment reveals that the CommunityGCN approach has given better results with accuracy, normalized mutual information, F1 and modularity scores of 91.26, 79.9, 92.58 and 70.5 per cent, respectively, for detecting communities in the graph network, which is much greater than the range of 55.7–87.07 per cent reported in previous literature. Thus, it has been concluded that the GCN with node classification models has improved the accuracy.

RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training

With the growth of the academic engines, the mining and analysis acquisition of massive researcher data, such as collaborator recommendation and researcher retrieval, has become indispensable. It can improve the quality of services and intelligence of academic engines. Most of the existing studies for researcher data mining focus on a single task for a particular application scenario and learning a task-specific model, which is usually unable to transfer to out-of-scope tasks. The pre-training technology provides a generalized and sharing model to capture valuable information from enormous unlabeled data. The model can accomplish multiple downstream tasks via a few fine-tuning steps. In this paper, we propose a multi-task self-supervised learning-based researcher data pre-training model named RPT. Specifically, we divide the researchers' data into semantic document sets and community graph. We design the hierarchical Transformer and the local community encoder to capture information from the two categories of data, respectively. Then, we propose three self-supervised learning objectives to train the whole model. Finally, we also propose two transfer modes of RPT for fine-tuning in different scenarios. We conduct extensive experiments to evaluate RPT, results on three downstream tasks verify the effectiveness of pre-training for researcher data mining.

Developing a robust model to predict depth of anesthesia from single channel EEG signal

Monitoring depth of anaesthesia (DoA) from electroencephalograph (EEG) signals is an ongoing challenge for anaesthesiologists. In this study, we propose an intelligence model that predicts the DoA from a single channel electroencephalograph (EEG) signal. A segmentation technique based on a sliding window is employed to partition EEG signals. Hierarchical dispersion entropy (HDE) is applied to each EEG segment. A set of features is extracted from each EEG segment. The extracted features are investigated using a community graph detection approach (CGDA), and the most relevant features are selected to trace the DoA. The proposed model, based on HDE coupled with CGDA, is evaluated in term of BIS index using several statistical metrics such Q-Q plot, regression, and correlation coefficients. In addition, the proposed model is evaluated against the BIS index in the case of the poor signal quality. The results demonstrated that the proposed model showed an earlier reaction compared with the BIS index when patient’s state transits from deep anaesthesia to moderate anaesthesia in the case of poor signal quality. The highest Pearson correlation coefficient obtained by the proposed is 0.96.

Dynamic topology analysis for spatial patterns of multifocal lesions on MRI.

Quantitatively analysing the spatial patterns of multifocal lesions on clinical MRI is an important step towards a better understanding of the disease and for precision medicine, which is yet to be properly explored by feature engineering and deep learning methods. Network science addresses this issue by explicitly modeling the inter-lesion topology. However, the construction of the informative graph with optimal edge sparsity and quantification of community graph structures are the current challenges in network science. In this paper, we address these challenges with a novel Dynamic Topology Analysis framework on the basis of persistent homology, aiming to investigate the predictive values of global geometry and local clusters of multifocal lesions. Firstly, Dynamic Hierarchical Network is proposed to construct informative global and community-level topology over multi-scale networks from sparse to dense. Multi-scale global topology is constructed with a nested sequence of Rips complexes, from which a new K-simplex Filtration is designed to generate a higher-level topological abstraction for community identification based on the connectivity of k-simplices in the Rips Complex. Secondly, to quantify multi-scale community structures, we design a new Decomposed Community Persistence algorithm to track the dynamic evolution of communities, and then summarise the evolutionary communities incorporated with a customisable descriptor. The quantified community features are encapsulated with global geometric invariants for topological pattern analysis. The proposed framework was evaluated on both diagnostic differentiation and prognostic prediction for multiple sclerosis that is a typical multifocal disease, and achieved ROC_AUC 0.875 and 0.767, respectively, outperforming seven state-of-the-art persistent homology methods and the reported performance of six feature engineering and deep learning methods.

Random intersection graphs with communities

AbstractRandom intersection graphs model networks with communities, assuming an underlying bipartite structure of communities and individuals, where these communities may overlap. We generalize the model, allowing for arbitrary community structures within the communities. In our new model, communities may overlap, and they have their own internal structure described by arbitrary finite community graphs. Our model turns out to be tractable. We analyze the overlapping structure of the communities, show local weak convergence (including convergence of subgraph counts), and derive the asymptotic degree distribution and the local clustering coefficient.

An efficient hybrid query recommendation using shingling and hashing techniques

Search engines recommend queries to improve the satisfaction level of users by shortening their search task. A proper solution for query recommendation is to analyze the users’ behaviors and mimic the query transition patterns adopted by different users who are succeeded in finding their needed information. In this paper, we propose a novel three-layer query recommendation method which is benefited from a query community graph in the first layer. This graph is generated through clustering similar queries which tend to convey the same meaning. To reduce the overhead of clustering while preserving its performance, we utilize locality-sensitive hashing of k-shingles to represent queries in a space with smaller and fixed dimensions. The second layer is enriched by a query-flow graph which models the transitional patterns made by users inside sessions. The hybrid graph, created by consolidating the query community and query-flow graphs, takes into account the lexical similarity as well as the reformulation diversity to suggest queries. The results of our experiments on data logs of two real search engines show that the proposed method outperforms some well-known algorithms by at least 14% with respect to precision and P@10 parameters.

Finding Community Infection Spreading Factor’s presence in a Community

In all the countries, all the communities consist of people having certain attitudes and interests in common. The whole community can be mapped into a graph network. Every distinct individual can be assumed as a node of the constructed graph for the community. To declare a pandemic situation for any country, we first need to check whether the infection is spread throughout the Community or not. For this purpose we need to calculate the existence of cliques and the nodes of the maximal clique will be the infection spreading factors. In this work, we try to find out the presence of these spreading factors in the community graph network.

Graph Signal Sampling and Interpolation Based on Clusters and Averages

We consider a disjoint cover (partition) of an undirected weighted finite or infinite graph G by J connected subgraphs (clusters) $$\{S_{j}\}_{j\in J}$$ and select functions $$\psi _{j}$$ on each of the clusters. For a given signal f on G the set of its weighted average values samples is defined via inner products $$\{\langle f, \psi _{j}\rangle \}_{j\in J}$$ . The main results of the paper are based on Poincare-type inequalities that we introduce and prove. These inequalities provide an estimate of the norm of the signal f on the entire graph G from sets of samples of f and its local gradient on each of the subgraphs. This allows us to establish discrete Plancherel-Polya-type inequalities (or Marcinkiewicz-Zigmund-type or frame inequalities) for signals whose gradients satisfy a Bernstein-type inequality. These results enable the development of a sampling theory for signals on undirected weighted finite or infinite graphs. For reconstruction of the signals from their samples an interpolation theory by weighted average variational splines is developed. Here by a weighted average variational spline we understand a minimizer of a discrete Sobolev norm which takes on the prescribed weighted average values on a set of clusters (in particular, just values on a subset of vertices). Although our approach is applicable to general graphs it’s especially well suited for finite and infinite graphs with multiple clusters. Such graphs are known as community graphs and they find many important applications in materials science, engineering, computer science, economics, biology, and social studies.

User Embedding for Expert Finding in Community Question Answering

The number of users who have the appropriate knowledge to answer asked questions in community question answering is lower than those who ask questions. Therefore, finding expert users who can answer the questions is very crucial and useful. In this article, we propose a framework to find experts for given questions and assign them the related questions. The proposed model benefits from users’ relations in a community along with the lexical and semantic similarities between new question and existing answers. Node embedding is applied to the community graph to find similar users. Our experiments on four different Stack Exchange datasets show that adding community relations improves the performance of expert finding models.

Advanced Community Identification Model for Social Networks

Community detection in social networks is a hard problem because of the size, and the need of a deep understanding of network structure and functions. While several methods with significant effort in this direction have been devised, an outstanding open problem is the unknown number of communities, it is generally believed that the role of influential nodes that are surrounded by neighbors is very important. In addition, the similarity among nodes inside the same cluster is greater than among nodes from other clusters. Lately, the global and local methods of community detection have been getting more attention. Therefore, in this study, we propose an advanced community-detection model for social networks in order to identify network communities based on global and local information. Our proposed model initially detects the most influential nodes by using an Eigen score then performs local expansion powered by label propagation. This process is conducted with the same color till nodes reach maximum similarity. Finally, the communities are formed, and a clear community graph is displayed to the user. Our proposed model is completely parameter-free, and therefore, no prior information is required, such as the number of communities, etc. We perform simulations and experiments using well-known synthetic and real network benchmarks, and compare them with well-known state-of-the-art models. The results prove that our model is efficient in all aspects, because it quickly identifies communities in the network. Moreover, it can easily be used for friendship recommendations or in business recommendation systems.

Fast single-phase fault location method based on community graph depth-first traversal for distribution network

With the increasing complexity of distribution network structure originated from high penetration of renewable energy and responsive loads, fast and accurate fault location technology of distribution network is a prerequisite for rapid isolation of faults and restoration of power supply. In this paper, a fault location method based on community graph depth-first traversal is proposed for fast location of single-phase ground faults in distribution network. First, this paper defines the fault graph weight of the vertices in the distribution network graph model, which are used to reflect the topology of the vertices and fault points as well as the fluctuation of the vertices' currents. Then, the vertices on the graph model are clustered by using an improved parallel louvain method (IPLM). Finally, the community formed by IPLM is used as the smallest unit for depth-first traversal to achieve fast and accurate location of the fault section. The paper builds the distribution network graph model of IEEE 33-bus system on the graph database for testing. And three other methods were selected for comparison with IPLMDF. The test results show that IPLMDF can achieve fast and accurate fault location when half of the nodes in the distribution network are equipped with D-PMUs. When some of the D-PMUs lose time synchronization, it is still possible to locate the fault section, and at the same time, the locating results can be avoided to fall into local optimal solutions.

GraphKKE: graph Kernel Koopman embedding for human microbiome analysis

More and more diseases have been found to be strongly correlated with disturbances in the microbiome constitution, e.g., obesity, diabetes, or some cancer types. Thanks to modern high-throughput omics technologies, it becomes possible to directly analyze human microbiome and its influence on the health status. Microbial communities are monitored over long periods of time and the associations between their members are explored. These relationships can be described by a time-evolving graph. In order to understand responses of the microbial community members to a distinct range of perturbations such as antibiotics exposure or diseases and general dynamical properties, the time-evolving graph of the human microbial communities has to be analyzed. This becomes especially challenging due to dozens of complex interactions among microbes and metastable dynamics. The key to solving this problem is the representation of the time-evolving graphs as fixed-length feature vectors preserving the original dynamics. We propose a method for learning the embedding of the time-evolving graph that is based on the spectral analysis of transfer operators and graph kernels. We demonstrate that our method can capture temporary changes in the time-evolving graph on both synthetic data and real-world data. Our experiments demonstrate the efficacy of the method. Furthermore, we show that our method can be applied to human microbiome data to study dynamic processes.

Detection of Sub Community Graph in N Community Graphs using Graph Mining

Detection of sub-graphs in community graphs is an important task and useful for characterizing community graphs. This characterization leads to classification as well as clusterings of community graphs. It also leads to finding differences among a set of community graphs as well as buildings of indices of community graphs. Finally, this characterization leads discovery of knowledge from sub-graphs. This proposed approach of detection of a sub-community graph from a group of community graphs using simple graph theory techniques. So, that knowledge could be discovered from the sub-community graph detected in a set of community graphs. The proposed algorithm has been implemented with two examples including one benchmark network and observed satisfactory results.

Sub-Community Graph Retrieval from a Compressed Community Graph using Graph Mining

Community detection and its retrieval is one of the most relevant and important topics in graph mining. Hence it is treated as one of the important applications in the field of social network analysis. Community detection plays an important role in a large community graph by enabling and selecting the desired community’s sub-graph. The proposed algorithm detects and extracts the desired sub-community graph from a compressed community graph for further analysis purpose. The authors present both theoretical and experimental results with three benchmark social networks. The proposed technique is efficient in terms of complexities.

Give Attention to Overlapping Network Detection in Networks for Multimedia

Finding overlapping agencies from multimedia social networks is an thrilling and important trouble in records mining and recommender systems but, existing overlapping network discovery often generates overlapping community structures with superfluous small groups. Network detection in a multimedia and social network is a conducive difficulty in the network gadget and it helps to understand and learn the overall network shape in element. Those are essentially the dividing wall of network nodes into a few subgroups in which nodes within these subgroups are densely linked, but the connections are sparser in between the subgroups. Social network analysis is widely widespread domain which draws the attention of many information mining experts. Some wide variety of actual community common characteristics which it shares are facebook, Twitter show off the idea of network shape inside the community. Social network is represented as a community graph. Detecting the groups entails locating the densely linked nodes.