Similar Nodes Research Articles

A network coupling approach to detecting hierarchical linkages between science and technology

AbstractDetecting science–technology hierarchical linkages is beneficial for understanding deep interactions between science and technology (S&T). Previous studies have mainly focused on linear linkages between S&T but ignored their structural linkages. In this paper, we propose a network coupling approach to inspect hierarchical interactions of S&T by integrating their knowledge linkages and structural linkages. S&T knowledge networks are first enhanced with bidirectional encoder representation from transformers (BERT) knowledge alignment, and then their hierarchical structures are identified based on K‐core decomposition. Hierarchical coupling preferences and strengths of the S&T networks over time are further calculated based on similarities of coupling nodes' degree distribution and similarities of coupling edges' weight distribution. Extensive experimental results indicate that our approach is feasible and robust in identifying the coupling hierarchy with superior performance compared to other isomorphism and dissimilarity algorithms. Our research extends the mindset of S&T linkage measurement by identifying patterns and paths of the interaction of S&T hierarchical knowledge.

Role-oriented representation learning via fusioning local and higher-order feature

Role-oriented representation learning extracts structural features by capturing the structural similarities of nodes to generate representations that preserve the structural equivalence, which is crucial for addressing the role discovery task of real networks. However, most studies directly combine different types of structural features and ignore the correlations among features, which is not enough to accurately portray node roles. Therefore, we propose a novel role-oriented network representation learning method RFLH that mines the correlations among features by normalizing flows to improve the performance on the role discovery tasks. We utilize the Variational Auto-Encoder (VAE) to generate the original representation distribution and learn the structural features of nodes by constraint of local and higher-order features, where local features are learned by the traditional variational module, while higher-order features are learned by the flow-based variational module that introduces normalizing flows to map the original representation distribution to a complex distribution. Moreover, we deduce the new loss by introducing the Jacobian determinant to Evidence Lower Bound (ELBO). Finally, we fuse local and higher-order features into the node representations, which are concatenated by the representations sampled from the original distribution and the new distribution, to generate the final node representations. Extensive experimental results on several real network datasets demonstrate that our model achieves superior performance compared to typical baseline methods.

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.

Semantics-preserved Graph Siamese Representation Learning

Currently, the expressive power of momentum-driven graph Siamese representation learning is mainly constrained by flawed positive selection strategies and data augmentation strategies. To solve these issues, we propose a Semantics-preserved Graph Siamese Representation Learning method named SGSRL. Firstly, we propose a local structure-aware positive selection strategy to reduce the generation of false positive samples. Specifically, the local structural similarity of nodes is obtained through the comparison between corresponding sampled subgraphs, where the anchor node’s subgraph is pooled to simplify the calculation. In addition, we propose a class information-aware feature augmentation method. Compared with directly modifying the inputs of the original graph, augmentation in the feature space is more controllable and intuitive. Specifically, we design an auxiliary contrastive learning task to train a class vector generator, and then overlay the class-oriented augmentation vectors generated by this generator onto the randomly augmented feature vectors. This joint feature augmentation strategy increases the variance between positive samples without changing the semanticity of nodes. To validate the superiority of our method, we conduct experiments on five real graph datasets for both node classification and node clustering tasks. The results demonstrate that our proposed SGSRL always outperforms state-of-art baselines.

UCoDe: unified community detection with graph convolutional networks

Community detection finds homogeneous groups of nodes in a graph. Existing approaches either partition the graph into disjoint, non-overlapping, communities, or determine only overlapping communities. To date, no method supports both detections of overlapping and non-overlapping communities. We propose UCoDe, a unified method for community detection in attributed graphs that detects both overlapping and non-overlapping communities by means of a novel contrastive loss that captures node similarity on a macro-scale. Our thorough experimental assessment on real data shows that, regardless of the data distribution, our method is either the top performer or among the top performers in both overlapping and non-overlapping detection without burdensome hyper-parameter tuning.

Unsupervised Community Detection Algorithm with Stochastic Competitive Learning Incorporating Local Node Similarity

Community detection is an important task in the analysis of complex networks, which is significant for mining and analyzing the organization and function of networks. As an unsupervised learning algorithm based on the particle competition mechanism, stochastic competitive learning has been applied in the field of community detection in complex networks, but still has several limitations. In order to improve the stability and accuracy of stochastic competitive learning and solve the problem of community detection, we propose an unsupervised community detection algorithm LNSSCL (Local Node Similarity-Integrated Stochastic Competitive Learning). The algorithm calculates node degree as well as Salton similarity metrics to determine the starting position of particle walk; local node similarity is incorporated into the particle preferential walk rule; the particle is dynamically adjusted to control capability increments according to the control range; particles select the node with the strongest control capability within the node to be resurrected; and the LNSSCL algorithm introduces a node affiliation selection step to adjust the node community labels. Experimental comparisons with 12 representative community detection algorithms on real network datasets and synthetic networks show that the LNSSCL algorithm is overall better than other compared algorithms in terms of standardized mutual information (NMI) and modularity (Q). The improvement effect for the stochastic competition learning algorithm is evident, and it can effectively accomplish the community detection task in complex networks.

Link prediction by adversarial Nonnegative Matrix Factorization

Networks are now more crucial than ever for modeling complex systems with interconnected components. Many methods have been developed to infer unobserved links or predict latent links based on observed network topology. However, the effectiveness of current methods is often limited due to the nature of sparseness in large-scale networks. Nonnegative Matrix Factorization (NMF) is one of the most popular low-rank approximation methods which has been successfully applied to large-scale data. However, maintaining generalization from limited observations is still an open challenge. To overcome these challenges, we propose a novel link prediction method based on adversarial NMF, which reconstructs a sparse network by an efficient adversarial training algorithm. Unlike the conventional NMF methods, our model considers potential test adversaries beyond the pre-defined bounds and provides a robust reconstruction with good generalization power. Besides, to preserve the local structure of a network, we use the common neighbor algorithm to extract the node similarity and apply it to low-dimensional latent representation. Simultaneously, we use Frobenius-norm regularization to prevent the factorization from overfitting. We provide an effective Majorization-Minimization method to learn the model parameters. Our method outperforms the state-of-the-art methods, as shown by extensive experiment results on twelve real-world datasets.

EAGMN: Coronary artery semantic labeling using edge attention graph matching network

Coronary artery disease (CAD) is one of the primary causes leading deaths worldwide. The presence of atherosclerotic lesions in coronary arteries is the underlying pathophysiological basis of CAD, and accurate extraction of individual arterial branches using invasive coronary angiography (ICA) is crucial for stenosis detection and CAD diagnosis. However, deep-learning-based models face challenges in generating semantic segmentation for coronary arteries due to the morphological similarity among different types of arteries. To address this challenge, we propose an innovative approach called the Edge Attention Graph Matching Network (EAGMN) for coronary artery semantic labeling. Inspired by the learning process of interventional cardiologists in interpreting ICA images, our model compares arterial branches between two individual graphs generated from different ICAs. We begin with extracting individual graphs based on the vascular tree obtained from the ICA. Each node in the individual graph represents an arterial segment, and the EAGMN aims to learn the similarity between nodes from the two individual graphs. By converting the coronary artery semantic segmentation task into a graph node similarity comparison task, identifying the node-to-node correspondence would assign semantic labels for each arterial branch. More specifically, the EAGMN utilizes the association graph constructed from the two individual graphs as input. A graph attention module is employed for feature embedding and aggregation, while a decoder generates the linear assignment for node-to-node semantic mapping. Based on the learned node-to-node relationships, unlabeled coronary arterial segments are classified using the labeled coronary arterial segments, thereby achieving semantic labeling. A dataset with 263 labeled ICAs is used to train and validate the EAGMN. Experimental results indicate the EAGMN achieved a weighted accuracy of 0.8653, a weighted precision of 0.8656, a weighted recall of 0.8653 and a weighted F1-score of 0.8643. Furthermore, we employ ZORRO to provide interpretability and explainability of the graph matching for artery semantic labeling. These findings highlight the potential of the EAGMN for accurate and efficient coronary artery semantic labeling using ICAs. By leveraging the inherent characteristics of ICAs and incorporating graph matching techniques, our proposed model provides a promising solution for improving CAD diagnosis and treatment.

Feature matching of remote‐sensing images based on bilateral local–global structure consistency

AbstractThe goal of feature matching is to establish accurate correspondences between feature points in different images depicting the same scene. To address the polymorphism of local structures, the authors propose a mismatch removal method using bilateral local–global structural consistency. This method incorporates the problem of mismatch removal into the framework of graph matching, constructs a global affinity matrix using local structural similarity and global affine transformation consistency, and optimizes it using a constrained integer quadratic programming method. To comprehensively describe the local structure, the signature quadratic form distance (SQFD) is used to measure the consistency of the neighbourhood structure. Specifically, the weights of edges are constructed based on the SQFD of the local structure, while the matching correctness of nodes and edges between the two graphs is described using local vector similarity. Furthermore, the consistency of the global affine transformation is evaluated by assessing the consistency of the local neighbourhood affine transformation between different corresponding point pairs. In estimating the local affine transformation, a bilateral correction is performed using a total least‐squares (TLS) algorithm to measure the similarity of nodes between the two different graphs. Experimental results demonstrate that the proposed algorithm outperforms state‐of‐the‐art methods in terms of accuracy and effectiveness.

SHNE: Semantics and Homophily Preserving Network Embedding.

Graph convolutional networks (GCNs) have achieved great success in many applications and have caught significant attention in both academic and industrial domains. However, repeatedly employing graph convolutional layers would render the node embeddings indistinguishable. For the sake of avoiding oversmoothing, most GCN-based models are restricted in a shallow architecture. Therefore, the expressive power of these models is insufficient since they ignore information beyond local neighborhoods. Furthermore, existing methods either do not consider the semantics from high-order local structures or neglect the node homophily (i.e., node similarity), which severely limits the performance of the model. In this article, we take above problems into consideration and propose a novel Semantics and Homophily preserving Network Embedding (SHNE) model. In particular, SHNE leverages higher order connectivity patterns to capture structural semantics. To exploit node homophily, SHNE utilizes both structural and feature similarity to discover potential correlated neighbors for each node from the whole graph; thus, distant but informative nodes can also contribute to the model. Moreover, with the proposed dual-attention mechanisms, SHNE learns comprehensive embeddings with additional information from various semantic spaces. Furthermore, we also design a semantic regularizer to improve the quality of the combined representation. Extensive experiments demonstrate that SHNE outperforms state-of-the-art methods on benchmark datasets.

Critical Node Identification of Multi-UUV Formation Based on Network Structure Entropy

In order to identify and attack the multi-UUV (unmanned underwater vehicle) groups, this paper proposes a method for identifying the critical nodes of multi-UUV formations. This method helps in combating multi-UUV formations by identifying the key nodes to attack them. Moreover, these multi-UUV formations are considered to have an unknown structure as the research object. Therefore, the network structure of the formation is reconstructed according to its space–time trajectory, and the importance of nodes is determined based on network structure entropy. As for the methodology, firstly, based on the swarm intelligence behavior method, the motion similarity of multi-UUV nodes in the formation is analyzed in pairs; furthermore, the leader–follower relationship and the network structure of the formation are calculated successively. Then, based on this network structure, the importance of the network nodes is further determined by the network structure entropy method. Finally, through simulation and experiments, it is verified that the algorithm can accurately construct the network structure of the unknown multi-UUV formation, and the accuracy of the calculated time delay data reaches 84.6%, and compared with the traditional information entropy algorithm, the ordering of the important nodes obtained by this algorithm is more in line with the underwater formation network.

Integrating Node Importance and Network Topological Properties for Link Prediction in Complex Network

Link prediction is one of the most important and challenging tasks in complex network analysis, which aims to predict the existence of unknown links based on the known information in the network. As critical topological properties in the network, node’s degree and clustering coefficient are well-suited for describing the tightness of connection between nodes. The importance of node can affect the possibility of link existence to a certain extent. By analyzing the impact of different centrality on links, which concluded that the degree centrality and proximity centrality have the greatest influence on network link prediction. A link prediction algorithm combines importance of node and network topological properties, called DCCLP, is proposed in this paper, the symmetry of the adjacency matrix is considered in the DCCLP link prediction algorithm to further describe the structural similarity of network nodes. In the training phase of the DCCLP algorithm, the maximized AUC indicator in the training set as the objective, and the optimal parameters are estimated by utilizing the White Shark Optimization algorithm. Then the prediction accuracy of the DCCLP algorithm is evaluated in the test set. By experimenting on twenty-one networks with different scales, and comparing with existing algorithms, the experimental results show that the effectiveness and feasibility of DCCLP algorithm, and further illustrate the importance of the degree centrality of node pairs and proximity centrality of nodes to improve the prediction accuracy of link prediction.

Inferring links in directed complex networks through feed forward loop motifs

Complex networks are mathematical abstractions of real-world systems using sets of nodes and edges representing the entities and their interactions. Prediction of unknown interactions in such networks is a problem of interest in biology, sociology, physics, engineering, etc. Most complex networks exhibit the recurrence of subnetworks, called network motifs. Within the realm of social science, link prediction (LP) models are employed to model opinions, trust, privacy, rumor spreading in social media, academic and corporate collaborations, liaisons among lawbreakers, and human mobility resulting in contagion. We present an LP metric based on a motif in directed complex networks, called feed-forward loop (FFL). Unlike nearest neighbor-based metrics and machine learning-based techniques that gauge the likelihood of a link based on node similarity, the proposed approach leverages a known dichotomy in the motif distribution of directed networks. Complex networks are sparse, causing most nodes and their associated links to have low motif participation. Yet, due to intrinsic network motif-richness, few links participate in many distinct motif substructures. Thus, the FFL-based metric combines the presence and absence of motifs as a signature to outperform baseline metrics on ten directed social and biological network datasets. We conclude with the future of the FFL-based metric in dynamic network inference as well as its use in designing combined metrics using network motifs of varying orders as features.

Attribute and Structure Preserving Graph Contrastive Learning

Graph Contrastive Learning (GCL) has drawn much research interest due to its strong ability to capture both graph structure and node attribute information in a self-supervised manner. Current GCL methods usually adopt Graph Neural Networks (GNNs) as the base encoder, which typically relies on the homophily assumption of networks and overlooks node similarity in the attribute space. There are many scenarios where such assumption cannot be satisfied, or node similarity plays a crucial role. In order to design a more robust mechanism, we develop a novel attribute and structure preserving graph contrastive learning framework, named ASP, which comprehensively and efficiently preserves node attributes while exploiting graph structure. Specifically, we consider three different graph views in our framework, i.e., original view, attribute view, and global structure view. Then, we perform contrastive learning across three views in a joint fashion, mining comprehensive graph information. We validate the effectiveness of the proposed framework on various real-world networks with different levels of homophily. The results demonstrate the superior performance of our model over the representative baselines.

Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering

As one of the most important research topics in the unsupervised learning field, Multi-View Clustering (MVC) has been widely studied in the past decade and numerous MVC methods have been developed. Among these methods, the recently emerged Graph Neural Networks (GNN) shine a light on modeling both topological structure and node attributes in the form of graphs, to guide unified embedding learning and clustering. However, the effectiveness of existing GNN-based MVC methods is still limited due to the insufficient consideration in utilizing the self-supervised information and graph information, which can be reflected from the following two aspects: 1) most of these models merely use the self-supervised information to guide the feature learning and fail to realize that such information can be also applied in graph learning and sample weighting; 2) the usage of graph information is generally limited to the feature aggregation in these models, yet it also provides valuable evidence in detecting noisy samples. To this end, in this paper we propose Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering (SGDMC), which promotes the performance of GNN-based deep MVC models by making full use of the self-supervised information and graph information. Specifically, a novel attention-allocating approach that considers both the similarity of node attributes and the self-supervised information is developed to comprehensively evaluate the relevance among different nodes. Meanwhile, to alleviate the negative impact caused by noisy samples and the discrepancy of cluster structures, we further design a sample-weighting strategy based on the attention graph as well as the discrepancy between the global pseudo-labels and the local cluster assignment. Experimental results on multiple real-world datasets demonstrate the effectiveness of our method over existing approaches.

Temporal Network Link Prediction Based on the Optimized Exponential Smoothing Model and Node Interaction Entropy

Link prediction accuracy in temporal networks is easily affected by the time granularity of network snapshots. This is due to the insufficient information conveyed by snapshots and the lack of temporal continuity between snapshots. We propose a temporal network link prediction method based on the optimized exponential smoothing model and node interaction entropy (OESMNIE). This method utilizes fine-grained interaction information between nodes within snapshot periods and incorporates the information entropy theory to improve the construction of node similarity in the gravity model as well as the prediction process of node similarity. Experiment results on several real-world datasets demonstrate the superiority and reliability of this proposed method in adapting to link prediction requirements over other methods across different time granularities of snapshots, which is essential for studying the evolution of temporal networks.

Graph Neural Network-Based Efficient Subgraph Embedding Method for Link Prediction in Mobile Edge Computing

Link prediction is critical to completing the missing links in a network or to predicting the generation of new links according to current network structure information, which is vital for analyzing the evolution of a network, such as the logical architecture construction of MEC (mobile edge computing) routing links of a 5G/6G access network. Link prediction can provide throughput guidance for MEC and select appropriate c nodes through the MEC routing links of 5G/6G access networks. Traditional link prediction algorithms are always based on node similarity, which needs predefined similarity functions, is highly hypothetical and can only be applied to specific network structures without generality. To solve this problem, this paper proposes a new efficient link prediction algorithm PLAS (predicting links by analysis subgraph) and its GNN (graph neural network) version PLGAT (predicting links by graph attention networks) based on the target node pair subgraph. In order to automatically learn the graph structure characteristics, the algorithm first extracts the h-hop subgraph of the target node pair, and then predicts whether the target node pair will be linked according to the subgraph. Experiments on eleven real datasets show that our proposed link prediction algorithm is suitable for various network structures and is superior to other link prediction algorithms, especially in some 5G MEC Access networks datasets with higher AUC (area under curve) values.

Detecting local communities in complex network via the optimization of interaction relationship between node and community.

The goal of local community detection algorithms is to explore the optimal community with a reference to a given node. Such algorithms typically include two primary processes: seed selection and community expansion. This study develops and tests a novel local community detection algorithm called OIRLCD that is based on the optimization of interaction relationships between nodes and the community. First, we introduce an improved seed selection method to solve the seed deviation problem. Second, this study uses a series of similarity indices to measure the interaction relationship between nodes and community. Third, this study uses a series of algorithms based on different similarity indices, and designs experiments to reveal the role of the similarity index in algorithms based on relationship optimization. The proposed algorithm was compared with five existing local community algorithms in both real-world networks and artificial networks. Experimental results show that the optimization of interaction relationship algorithms based on node similarity can detect communities accurately and efficiently. In addition, a good similarity index can highlight the advantages of the proposed algorithm based on interaction optimization.

Classifying Urban Functional Zones Based on Modeling POIs by Deepwalk

Developing urban functional zone classification method to study urban spatial structure is a hotspot in current research. Using the word embedding model to excavate spatial relationship of the geographic elements in urban functional zones is an important way to develop urban functional zone classification method. However, in these studies, the spatial relationship of geographic elements was regarded as their homogeneity, while the structural similarity of geographical elements was ignored, which inevitably reduces the classification accuracy of urban functional zone classification method. This paper proposes to develop an urban functional zone classification method based on Deepwalk model, which could extract homogeneity and structural similarity of nodes in graph. The proposed method uses POI data to represent geographical elements, organizes POIs into graphs, and uses Deepwalk to embedding POIs for urban functional zone classification. It was applied to classify the urban functional zones of Chaoyang district in Beijing; and the classification results were compared with those of two baseline method based on Word2vec model and Place2vec model. The experimental results show that considering both the homogeneity and structural similarity of geographical elements, the proposed model has higher accuracy than the models only considering the homogeneity of geographical elements.

Multilayer Network Community Detection: A Novel Multi-Objective Evolutionary Algorithm Based on Consensus Prior Information [Feature

In recent years, multilayer networks have served as effective models for addressing and analyzing real-world systems with multiple relationships. Among these scenarios, the community detection (CD) problem is one of the most prominent research hotspots. Although some research on multilayer network CD (MCD) has been proposed to address this problem, most studies focus only on topological structures. Therefore, their algorithms cannot extract the most out of complementary network information, such as node similarities and low-rank features, which may lead to unsatisfactory accuracy. To tackle this problem, this paper proposes a novel multi-objective evolutionary algorithm based on consensus prior information (MOEA-CPI). The proposed algorithm takes full advantage of prior information to guide the MOEA with respect to topological structures, initializations, and the optimization process. More specifically, this paper first extracts two kinds of prior information, i.e., graph-level and node-level information, based on Node2vec and Jaccard similarity, respectively. Then, the prior layer and a high-quality initial population are constructed on the basis of the graph-level information. During the optimization process, the genetic operator, which integrates the weighting strategy and node-level information, is applied to guide the algorithm to distribute similar nodes into the same community. Extensive experiments are implemented to prove the superior performance of MOEA-CPI over the state-of-the-art methods.