Enhancing network lifespan in wireless sensor networks using deep learning based Graph Neural Network

Inadequate energy of sensors is one of the most significant challenges in the development of a reliable wireless sensor network (WSN) that can withstand the demands of growing WSN applications. Implementing a sleep-wake scheduling scheme while assigning data collection and sensing chores to a dominant group of awake sensors while all other nodes are in a sleep state seems to be a potential way for preserving the energy of these sensor nodes. When the starting energy of the nodes changes from one node to another, this issue becomes more difficult to solve. The notion of a dominant set-in graph has been used in a variety of situations. The search for the smallest dominant set in a big graph might be time-consuming. Specifically, we address two issues: first, identifying the smallest possible dominant set, and second, extending the network lifespan by saving the energy of the sensors. To overcome the first problem, we design and develop a deep learning-based Graph Neural Network (DL-GNN). The GNN training method and back-propagation approach were used to train a GNN consisting of three networks such as transition network, bias network, and output network, to determine the minimal dominant set in the created graph. As a second step, we proposed a hybrid fixed-variant search (HFVS) method that considers minimal dominant sets as input and improves overall network lifespan by swapping nodes of minimal dominating sets. We prepared simulated networks with various network configurations and modeled different WSNs as undirected graphs. To get better convergence, the different values of state vector dimensions of the input vectors are investigated. When the state vector dimension is 3 or 4, minimum dominant set is recognized with high accuracy. The paper also presents comparative analyses between the proposed HFVS algorithm and other existing algorithms for extending network lifespan and discusses the trade-offs that exist between them. Lifespan of wireless sensor network, which is based on the dominant set method, is greatly increased by the techniques we have proposed.     

Multi-Scale Aggregation Graph Neural Networks Based on Feature Similarity for Semi-Supervised Learning

The problem of extracting meaningful data through graph analysis spans a range of different fields, such as social networks, knowledge graphs, citation networks, the World Wide Web, and so on. As increasingly structured data become available, the importance of being able to effectively mine and learn from such data continues to grow. In this paper, we propose the multi-scale aggregation graph neural network based on feature similarity (MAGN), a novel graph neural network defined in the vertex domain. Our model provides a simple and general semi-supervised learning method for graph-structured data, in which only a very small part of the data is labeled as the training set. We first construct a similarity matrix by calculating the similarity of original features between all adjacent node pairs, and then generate a set of feature extractors utilizing the similarity matrix to perform multi-scale feature propagation on graphs. The output of multi-scale feature propagation is finally aggregated by using the mean-pooling operation. Our method aims to improve the model representation ability via multi-scale neighborhood aggregation based on feature similarity. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our method compared to a variety of popular architectures.     

Research of Software Defect Prediction Model Based on Complex Network and Graph Neural Network

The goal of software defect prediction is to make predictions by mining the historical data using models. Current software defect prediction models mainly focus on the code features of software modules. However, they ignore the connection between software modules. This paper proposed a software defect prediction framework based on graph neural network from a complex network perspective. Firstly, we consider the software as a graph, where nodes represent the classes, and edges represent the dependencies between the classes. Then, we divide the graph into multiple subgraphs using the community detection algorithm. Thirdly, the representation vectors of the nodes are learned through the improved graph neural network model. Lastly, we use the representation vector of node to classify the software defects. The proposed model is tested on the PROMISE dataset, using two graph convolution methods, based on the spectral domain and spatial domain in the graph neural network. The investigation indicated that both convolution methods showed an improvement in various metrics, such as accuracy, F-measure, and MCC (Matthews correlation coefficient) by 86.6%, 85.8%, and 73.5%, and 87.5%, 85.9%, and 75.5%, respectively. The average improvement of various metrics was noted as 9.0%, 10.5%, and 17.5%, and 6.3%, 7.0%, and 12.1%, respectively, compared with the benchmark models.     

A Block-Based Adaptive Decoupling Framework for Graph Neural Networks

Graph neural networks (GNNs) with feature propagation have demonstrated their power in handling unstructured data. However, feature propagation is also a smooth process that tends to make all node representations similar as the number of propagation increases. To address this problem, we propose a novel Block-Based Adaptive Decoupling (BBAD) Framework to produce effective deep GNNs by utilizing backbone networks. In this framework, each block contains a shallow GNN with feature propagation and transformation decoupled. We also introduce layer regularizations and flexible receptive fields to automatically adjust the propagation depth and to provide different aggregation hops for each node, respectively. We prove that the traditional coupled GNNs are more likely to suffer from over-smoothing when they become deep. We also demonstrate the diversity of outputs from different blocks of our framework. In the experiments, we conduct semi-supervised and fully supervised node classifications on benchmark datasets, and the results verify that our method can not only improve the performance of various backbone networks, but also is superior to existing deep graph neural networks with less parameters.     

Node importance for dynamical process on networks: a multiscale characterization

Defining the importance of nodes in a complex network has been a fundamental problem in analyzing the structural organization of a network, as well as the dynamical processes on it. Traditionally, the measures of node importance usually depend either on the local neighborhood or global properties of a network. Many real-world networks, however, demonstrate finely detailed structure at various organization levels, such as hierarchy and modularity. In this paper, we propose a multiscale node-importance measure that can characterize the importance of the nodes at varying topological scale. This is achieved by introducing a kernel function whose bandwidth dictates the ranges of interaction, and meanwhile, by taking into account the interactions from all the paths a node is involved. We demonstrate that the scale here is closely related to the physical parameters of the dynamical processes on networks, and that our node-importance measure can characterize more precisely the node influence under different physical parameters of the dynamical process. We use epidemic spreading on networks as an example to show that our multiscale node-importance measure is more effective than other measures.     

Bert-Enhanced Text Graph Neural Network for Classification

Text classification is a fundamental research direction, aims to assign tags to text units. Recently, graph neural networks (GNN) have exhibited some excellent properties in textual information processing. Furthermore, the pre-trained language model also realized promising effects in many tasks. However, many text processing methods cannot model a single text unit’s structure or ignore the semantic features. To solve these problems and comprehensively utilize the text’s structure information and semantic information, we propose a Bert-Enhanced text Graph Neural Network model (BEGNN). For each text, we construct a text graph separately according to the co-occurrence relationship of words and use GNN to extract text features. Moreover, we employ Bert to extract semantic features. The former part can take into account the structural information, and the latter can focus on modeling the semantic information. Finally, we interact and aggregate these two features of different granularity to get a more effective representation. Experiments on standard datasets demonstrate the effectiveness of BEGNN.     

基于相继故障信息的网络节点重要度演化机理分析

分析了过载机制下节点重要度的演化机理.首先,在可调负载重分配级联失效模型基础上,根据节点失效后其分配范围内节点的负载振荡程度,提出了考虑级联失效局域信息的复杂网络节点重要度指标.该指标具有两个特点:一是值的大小可以清晰地指出节点的失效后果;二是可以依据网络负载分配范围、负载分配均匀性、节点容量系数及网络结构特征分析节点重要度的演化情况.然后,给出该指标的仿真算法,并推导了最近邻择优分配和全局择优分配规则下随机网络和无标度网络节点重要度的解析表达式.最后,实验验证了该指标的有效性和可行性,并深入分析了网络中节点重要度的演化机理,即非关键节点如何演化成影响网络级联失效行为的关键节点.     

基于注意力机制与图卷积神经网络的单目红外图像深度估计

对场景中的物体进行深度估计是无人驾驶领域中的关键问题,红外图像有利于在光线不佳的情况下解决深度估计问题.针对红外图像纹理不清晰与边缘信息不丰富的特点,提出了将注意力机制与图卷积神经网络相结合来解决单目红外图像深度估计问题.首先,在深度估计问题中,图像中每个像素点的深度信息不仅与其周围像素点的深度信息相关,还需考虑更大范...     

Analysis of identification methods of key nodes in transportation network

The identification of key nodes plays an important role in improving the robustness of the transportation network. For different types of transportation networks, the effect of the same identification method may be different. It is of practical significance to study the key nodes identification methods corresponding to various types of transportation networks. Based on the knowledge of complex networks, the metro networks and the bus networks are selected as the objects, and the key nodes are identified by the node degree identification method, the neighbor node degree identification method, the weighted k-shell degree neighborhood identification method (KSD), the degree k-shell identification method (DKS), and the degree k-shell neighborhood identification method (DKSN). Take the network efficiency and the largest connected subgraph as the effective indicators. The results show that the KSD identification method that comprehensively considers the elements has the best recognition effect and has certain practical significance.     

GTAD: Graph and Temporal Neural Network for Multivariate Time Series Anomaly Detection

The rapid development of smart factories, combined with the increasing complexity of production equipment, has resulted in a large number of multivariate time series that can be recorded using sensors during the manufacturing process. The anomalous patterns of industrial production may be hidden by these time series. Previous LSTM-based and machine-learning-based approaches have made fruitful progress in anomaly detection. However, these multivariate time series anomaly detection algorithms do not take into account the correlation and time dependence between the sequences. In this study, we proposed a new algorithm framework, namely, graph attention network and temporal convolutional network for multivariate time series anomaly detection (GTAD), to address this problem. Specifically, we first utilized temporal convolutional networks, including causal convolution and dilated convolution, to capture temporal dependencies, and then used graph neural networks to obtain correlations between sensors. Finally, we conducted sufficient experiments on three public benchmark datasets, and the results showed that the proposed method outperformed the baseline method, achieving detection results with F1 scores higher than 95% on all datasets.     

A generalized approach to complex networks

This work describes how the formalization of complex network concepts in terms of discrete mathematics, especially mathematical morphology, allows a series of generalizations and important results ranging from new measurements of the network topology to new network growth models. First, the concepts of node degree and clustering coefficient are extended in order to characterize not only specific nodes, but any generic subnetwork. Second, the consideration of distance transform and rings are used to further extend those concepts in order to obtain a signature, instead of a single scalar measurement, ranging from the single node to whole graph scales. The enhanced discriminative potential of such extended measurements is illustrated with respect to the identification of correspondence between nodes in two complex networks, namely a protein-protein interaction network and a perturbed version of it.     

Identifying influential nodes based on graph signal processing in complex networks

Identifying influential nodes in complex networks is of both theoretical and practical importance. Existing methods identify influential nodes based on their positions in the network and assume that the nodes are homogeneous. However,node heterogeneity(i.e., different attributes such as interest, energy, age, and so on) ubiquitously exists and needs to be taken into consideration. In this paper, we conduct an investigation into node attributes and propose a graph signal processing based centrality(GSPC) method to identify influential nodes considering both the node attributes and the network topology. We first evaluate our GSPC method using two real-world datasets. The results show that our GSPC method effectively identifies influential nodes, which correspond well with the underlying ground truth. This is compatible to the previous eigenvector centrality and principal component centrality methods under circumstances where the nodes are homogeneous. In addition, spreading analysis shows that the GSPC method has a positive effect on the spreading dynamics.     

Deep Link-Prediction Based on the Local Structure of Bipartite Networks

Link prediction based on bipartite networks can not only mine hidden relationships between different types of nodes, but also reveal the inherent law of network evolution. Existing bipartite network link prediction is mainly based on the global structure that cannot analyze the role of the local structure in link prediction. To tackle this problem, this paper proposes a deep link-prediction (DLP) method by leveraging the local structure of bipartite networks. The method first extracts the local structure between target nodes and observes structural information between nodes from a local perspective. Then, representation learning of the local structure is performed on the basis of the graph neural network to extract latent features between target nodes. Lastly, a deep-link prediction model is trained on the basis of latent features between target nodes to achieve link prediction. Experimental results on five datasets showed that DLP achieved significant improvement over existing state-of-the-art link prediction methods. In addition, this paper analyzes the relationship between local structure and link prediction, confirming the effectiveness of a local structure in link prediction.     

LCH: A local clustering H-index centrality measure for identifying and ranking influential nodes in complex networks

Identifying influential nodes in complex networks is one of the most significant and challenging issues, which may contribute to optimizing the network structure, controlling the process of epidemic spreading and accelerating information diffusion. The node importance ranking measures based on global information are not suitable for large-scale networks due to their high computational complexity. Moreover, they do not take into account the impact of network topology evolution over time, resulting in limitations in some applications. Based on local information of networks, a local clustering H-index (LCH) centrality measure is proposed, which considers neighborhood topology, the quantity and quality of neighbor nodes simultaneously. The proposed measure only needs the information of first-order and second-order neighbor nodes of networks, thus it has nearly linear time complexity and can be applicable to large-scale networks. In order to test the proposed measure, we adopt the susceptible-infected-recovered (SIR) and susceptible-infected (SI) models to simulate the spreading process. A series of experimental results on eight real-world networks illustrate that the proposed LCH can identify and rank influential nodes more accurately than several classical and state-of-the-art measures.     

基于层间相似性的时序网络节点重要性研究

时序网络可以更加准确地描述节点之间的交互顺序和交互关系.结合多层耦合网络分析法,本文提出了基于节点层间相似性的超邻接矩阵时序网络节点重要性识别方法,与经典的认为所有层间关系为常数不同,层间关系用节点的邻居拓扑重叠系数进行度量.Workspace和Enrons数据集上的结果显示:相比经典的方法,使用该方法得到的Kendall’sτ值在各时间层上的平均提高,最高为17.72%和12.44%,结果表明层间相似性的度量对于时序网络的节点重要性度量具有十分重要的意义.     

基于度与集聚系数的网络节点重要性度量方法研究

网络中节点重要性度量对于研究网络的鲁棒性具有十分重要的意义. 研究者们普遍运用度或集聚系数来度量节点的重要程度, 然而度指标只考虑节点自身邻居个数而忽略了其邻居之间的信息, 集聚系数只考虑节点邻居之间的紧密程度而忽略了其邻居的规模. 本文综合考虑节点的邻居个数, 以及其邻居之间的连接紧密程度, 提出了一种基于邻居信息与集聚系数的节点重要性评价方法. 对美国航空网络和美国西部电力网进行的选择性攻击实验表明, 采用该方法的效果较k-shell指标可以分别提高24%和112%. 本文的节点重要性度量方法只需要考虑网络局部信息, 因此非常适合于对大规模网络的节点重要性进行有效分析. 关键词： 网络科学 鲁棒性 节点重要性 集聚系数     

Network robustness to targeted attacks. The interplay of expansibility and degree distribution

We study the property of certain complex networks of being both sparse and highly connected, which is known as “good expansion” (GE). A network has GE properties if every subset S of nodes (up to 50% of the nodes) has a neighborhood that is larger than some “expansion factor” φ multiplied by the number of nodes in S. Using a graph spectral method we introduce here a new parameter measuring the good expansion character of a network. By means of this parameter we are able to classify 51 real-world complex networks — technological, biological, informational, biological and social — as GENs or non-GENs. Combining GE properties and node degree distribution (DD) we classify these complex networks in four different groups, which have different resilience to intentional attacks against their nodes. The simultaneous existence of GE properties and uniform degree distribution contribute significantly to the robustness in complex networks. These features appear solely in 14% of the 51 real-world networks studied here. At the other extreme we find that ∼40% of all networks are very vulnerable to targeted attacks. They lack GE properties, display skewed DD — exponential or power-law — and their topologies are changed more dramatically by targeted attacks directed at bottlenecks than by the removal of network hubs.     

Hierarchical Characterization of Complex Networks

While the majority of approaches to the characterization of complex networks has relied on measurements considering only the immediate neighborhood of each network node, valuable information about the network topological properties can be obtained by considering further neighborhoods. The current work considers the concept of virtual hierarchies established around each node and the respectively defined hierarchical node degree and clustering coefficient (introduced in cond-mat/0408076), complemented by new hierarchical measurements, in order to obtain a powerful set of topological features of complex networks. The interpretation of such measurements is discussed, including an analytical study of the hierarchical node degree for random networks, and the potential of the suggested measurements for the characterization of complex networks is illustrated with respect to simulations of random, scale-free and regular network models as well as real data (airports, proteins and word associations). The enhanced characterization of the connectivity provided by the set of hierarchical measurements also allows the use of agglomerative clustering methods in order to obtain taxonomies of relationships between nodes in a network, a possibility which is also illustrated in the current article.