Neighbor Nodes Research Articles

High-frequency and low-frequency dual-channel graph attention network

Most existing graph convolution layers use learnable or fixed weights to sum up neighbor features to aggregate neighbor information. Since the attention values are always positive, these graph convolution layers perform as low-pass filters, which may result in their poor performance on heterophilic graphs. In this paper, two graph convolutional layers are proposed, HLGAT and NGAT. NGAT is a convolution network using only negative attention values, which only make the aggregation of high-frequency information of neighbor nodes. HLGAT makes the aggregation of low-frequency and high-frequency information by two channels, respectively, and fuses two outputs by using a learnable way. On node-classification task, both NGAT and HLGAT offer significant performance improvement compared to existing methods. The results clearly show that: (1) High-frequency information of neighborhoods plays a decisive role in heterophilic graphs. (2) The aggregation of low-frequency and high-frequency information of neighbor nodes can significantly improve the performance on heterophilic graphs.

Heterogenous biological network multi-task learning model for ncRNA-disease-drug association prediction

Traditional medical research is characterised by lengthy duration, significant financial investment, and substantial risk of failure. In response to these challenges, network medicine, combined with medicine and computer technology, has become an important development direction, and computational methods have been proposed to predict potential associations. However, most of the current computational methods focus on single-potential association prediction tasks, which face issues of association sparsity and weak generalisation ability. To address these challenges, we developed a heterogeneous biological network multi-task learning model (HBNMM). Unlike previous methods based on bipartite graphs, HBNMM constructs a complex heterogeneous biological network, including ncRNA-disease-drug association networks and diverse similarity networks. HBNMM applies graph attention networks to aggregate node neighbourhood information and acquire node feature embeddings, and is then trained with a multi-task learning strategy to simultaneously predict potential ncRNA-disease, ncRNA-drug, and drug-disease associations. As a result, the HBNMM achieves an excellent performance that is higher than that of the state-of-the-art models. Furthermore, five case studies supported by experiments showed powerful predictive ability for drug discovery and disease treatment.

DMFVAE: miRNA-disease associations prediction based on deep matrix factorization method with variational autoencoder

MicroRNAs (miRNAs) are closely related to numerous complex human diseases, therefore, exploring miRNA-disease associations (MDAs) can help people gain a better understanding of complex disease mechanism. An increasing number of computational methods have been developed to predict MDAs. However, the sparsity of the MDAs may hinder the performance of many methods. In addition, many methods fail to capture the nonlinear relationships of miRNA-disease network and inadequately leverage the features of network and neighbor nodes. In this study, we propose a deep matrix factorization model with variational autoencoder (DMFVAE) to predict potential MDAs. DMFVAE first decomposes the original association matrix and the enhanced association matrix, in which the enhanced association matrix is enhanced by self-adjusting the nearest neighbor method, to obtain sparse vectors and dense vectors, respectively. Then, the variational encoder is employed to obtain the nonlinear latent vectors of miRNA and disease for the sparse vectors, and meanwhile, node2vec is used to obtain the network structure embedding vectors of miRNA and disease for the dense vectors. Finally, sample features are acquired by combining the latent vectors and network structure embedding vectors, and the final prediction is implemented by convolutional neural network with channel attention. To evaluate the performance of DMFVAE, we conduct five-fold cross validation on the HMDD v2.0 and HMDD v3.2 datasets and the results show that DMFVAE performs well. Furthermore, case studies on lung neoplasms, colon neoplasms, and esophageal neoplasms confirm the ability of DMFVAE in identifying potential miRNAs for human diseases.

Energy Efficient strategy for Wireless Sensor Networks lifetime endurance using Genetic Algorithm

This study propose an optimized routing scheme for multiple hops Wireless Sensor Networks to enhance the lifetime of the network. Since the wireless sensor networks work as application-centric having the capabilities of data gathering and transmission to the base station. Therefore, a significant amount of sensor networks` energy spends during such operation of data collection and transmission if the route is not optimized. So, a meta-heuristic genetic algorithm plays a vital role in finding the optimized route. We will modify the genetic algorithm for better optimization results so that the best route can be selected among all possible routes and will save the wireless sensor networks` energy. All information is routed towards the sink via intermediate neighbor nodes, which only relay the data without performing any computation or operation. The genetic algorithm determines the route information to all nodes and sinks. Then, the data takes the most optimal route for data transmission. Thus, this study proved a considerably saved extra waste of energy.

An effective metaheuristic based optimized type‐II fuzzy inference system for fault node identification in wireless sensor network

SummaryDeploying a wireless sensor network (WSN) for accessing the network of distant environments is more crucial. Node defect detection is a core technology of WSN and is essential for most WSN networks. The defective node reduces the overall service quality (OSQ) of the global WSN network system. Therefore, a type II fuzzy inference system (T2_FIS) is proposed for detecting defective nodes in the WSN network. The adaptive genetic algorithm (AGA) and proposed method are introduced for tuning the parameters in the T2_FIS system. The proposed T2_FIS method effectively detects the broken node in the WSN network using the fuzzy rules. In addition, the improved Mud Ring (IMR) optimization algorithm is proposed to replace the faulty node with the neighborhood node in the network. The defective nodes are identified and replaced with the closest nodes based on the membership function (MF) generated by the T2_FIS. Furthermore, the lifetime and throughput of the WSN network are increased by minimizing energy consumption. The overall performance is evaluated using the MATLAB tool, and the implementation results are compared with the existing methods. The total energy consumption for the proposed method is 50.451, with a throughput and lifetime of 153.657 and 22979.25. Furthermore, the performance metrics for the existing and proposed strategies are analyzed, and the accuracy of the proposed method is proven to be 99.3827%, the false alarm rate (FAR) is 0.0008, and the false positive rate (FPR) is 0.0617. The results show the effectiveness and performance of the proposed method.

Graph Adaptive Attention Network with Cross-Entropy.

Non-Euclidean data, such as social networks and citation relationships between documents, have node and structural information. The Graph Convolutional Network (GCN) can automatically learn node features and association information between nodes. The core ideology of the Graph Convolutional Network is to aggregate node information by using edge information, thereby generating a new node feature. In updating node features, there are two core influencing factors. One is the number of neighboring nodes of the central node; the other is the contribution of the neighboring nodes to the central node. Due to the previous GCN methods not simultaneously considering the numbers and different contributions of neighboring nodes to the central node, we design the adaptive attention mechanism (AAM). To further enhance the representational capability of the model, we utilize Multi-Head Graph Convolution (MHGC). Finally, we adopt the cross-entropy (CE) loss function to describe the difference between the predicted results of node categories and the ground truth (GT). Combined with backpropagation, this ultimately achieves accurate node classification. Based on the AAM, MHGC, and CE, we contrive the novel Graph Adaptive Attention Network (GAAN). The experiments show that classification accuracy achieves outstanding performances on Cora, Citeseer, and Pubmed datasets.

A reliable cluster-based opportunistic routing protocol for underwater wireless sensor networks

Underwater Acoustic Sensor Networks (UASNs) have gained significant popularity and application in various marine engineering exploration scenarios, driven by the global evolution of the ocean ecosystem. However, UASNs face numerous challenges arising from the unique characteristics of the underwater environment and acoustic channels, such as limited energy resources, unreliable communication, and dynamic network topology in uncertain environments, all of which impact the network lifetime and transmission reliability. To address these challenges and enable efficient underwater data packet transmissions, this paper proposes a reliable cluster-based routing method called RCRP. The RCRP organizes sensor nodes into clusters, where cluster heads transmit the fused data to the sink node through multi-hop forwarding. To overcome routing voids caused by node failures during packet transmission, a prediction model based on the Markov chain is introduced to identify void nodes and inform neighboring nodes about the routing holes. Furthermore, a connection prediction mechanism is developed to tackle changes in the uncertain network topology, taking into account node mobility and the received SNR. For packet transmissions, a waiting mechanism inspired by the opportunistic routing (OR) paradigm is proposed, which determines the optimal forwarding route based on the calculated probability of successful connection between nodes. Simulation results demonstrate that RCRP outperforms existing routing protocols in terms of packet delivery ratio, surviving time, and energy consumption, highlighting its effectiveness in enhancing the performance of UASNs.

Meta-Path Semantic and Global-Local Representation Learning Enhanced Graph Convolutional Model for Disease-Related miRNA Prediction.

Dysregulation of miRNAs is closely related to the progression of various diseases, so identifying disease-related miRNAs is crucial. Most recently proposed methods are based on graph reasoning, while they did not completely exploit the topological structure composed of the higher-order neighbor nodes and the global and local features of miRNA and disease nodes. We proposed a prediction method, MDAP, to learn semantic features of miRNA and disease nodes based on various meta-paths, as well as node features from the entire heterogeneous network perspective, and node pair attributes. Firstly, for both the miRNA and disease nodes, node category-wise meta-paths were constructed to integrate the similarity and association connection relationships. Each target node has its specific neighbor nodes for each meta-path, and the neighbors of longer meta-paths constitute its higher-order neighbor topological structure. Secondly, we constructed a meta-path specific graph convolutional network module to integrate the features of higher-order neighbors and their topology, and then learned the semantic representations of nodes. Thirdly, for the entire miRNA-disease heterogeneous network, a global-aware graph convolutional autoencoder was built to learn the network-view feature representations of nodes. We also designed semantic-level and representation-level attentions to obtain informative semantic features and node representations. Finally, the strategy based on the parallel convolutional-deconvolutional neural networks were designed to enhance the local feature learning for a pair of miRNA and disease nodes. The experiment results showed that MDAP outperformed other state-of-the-art methods, and the ablation experiments demonstrated the effectiveness of MDAP's major innovations. MDAP's ability in discovering potential disease-related miRNAs was further analyzed by the case studies over three diseases.

Energy balancing strategy for the multi-storage islanded DC microgrid based on hierarchical cooperative control

To simultaneously solve the problems of the state-of-charge (SOC) equalization and accurate current distribution among distributed energy storage units (DESUs) with different capacities in isolated DC microgrids, a multi-storage DC microgrid energy equalization strategy based on the hierarchical cooperative control is proposed. In the primary control layer, the link between the droop coefficient and SOC is established through a logarithmic function, and the droop coefficient is adaptively adjusted according to the SOC value in order to achieve fast SOC equalization. In the secondary control layer, by designing a coordinated state factor, only one PI controller is required to eliminate the influence of the line impedance on the accurate distribution of the output current and the DC bus voltage drop. In the communication layer, local nodes only need to communicate with neighboring nodes without the need for a central controller, and the dynamic consistency algorithm is used to obtain the average value information about the energy storage system (ESS). Finally, the feasibility and effectiveness of the proposed control strategy are verified by experimental analysis on the DC microgrid hardware-in-the-loop experimental platform.

Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition

Skeleton-based action recognition has attracted increasing interest in recent years. With the flexibility of modeling long-range dependency of joints, the self-attention module has served as the basic component in skeleton-based action recognition. However, the global receptive field of self-attention is not conducive to the modeling of skeleton locality, and the self-attention model is imbued with less inductive bias, which leads to overfitting. In this paper, we propose an attention graph convolutional network (AGCN) with multi-scale sampling to effectively model the local and global features of the skeleton. Firstly, we propose two extreme sampling strategies for generating and ordering neighboring nodes of root nodes. A local-first sampling method is introduced to construct local graph windows, and a global-first sampling method is proposed to assemble long-range joints for constructing global graph windows. The local-first sampling and global-first sampling introduce more skeleton-specific inductive biases to regularize the model capacity. Secondly, the AGCN combines the self-attention mechanism with graph convolution operation, which alleviates the over-smoothing of graph convolution and preserves the translation invariant. Based on the multi-scale sampling strategy, the AGCN can effectively model the locality and non-locality of the skeleton. Finally, by coupling the aforementioned proposals, we develop a two-pathway model for multi-scale feature fusion. Extensive experiments demonstrate that our model could achieve comparable performance with state-of-the-art works on the NTU RGB+D 60, NTU RGB+D 120, the UAV-HUMAN and NW-UCLA datasets.

Offloading Strategy Based on Graph Neural Reinforcement Learning in Mobile Edge Computing

In the mobile edge computing (MEC) architecture, base stations with computational capabilities are subject to service coverage limitations, and the mobility of devices leads to dynamic changes in their connections, directly impacting the offloading decisions of agents. The connections between base stations and mobile devices, as well as the connections between base stations themselves, are abstracted into an MEC structural diagram due to the difficulty of deep reinforcement learning (DRL) in capturing the complex relationships between nodes and their multi-order neighboring nodes in the graph; decisions solely generated by DRL have limitations. To address this issue, this study proposes a hierarchical mechanism strategy based on Graph Neural Reinforcement Learning (M-GNRL) under multiple constraints. Specifically, the MEC structural graph constructed with the current device as an observation point aggregates to learn node features, thus comprehensively considering the contextual information of nodes, and the learned graph information serves as the environment for deep reinforcement learning, effectively integrating a graph neural network (GNN) with DRL. In the M-GNRL strategy, edge features from GNN are introduced into the architecture of the DRL network to enhance the accuracy of agents’ decision-making. Additionally, this study proposes an updated algorithm to obtain graph data that change with observation points. Comparative experiments demonstrate that the M-GNRL algorithm outperforms other baseline algorithms in terms of system cost and convergence performance.

Distance- and Angle-Based Hybrid Localization Integrated in the IEEE 802.15.4 TSCH Communication Protocol

Accurate localization of devices within Internet of Things (IoT) networks is driven by the emergence of novel applications that require context awareness to improve operational efficiency, resource management, automation, and safety in industry and smart cities. With the Integrated Localization and Communication (ILAC) functionality, IoT devices can simultaneously exchange data and determine their position in space, resulting in maximized resource utilization with reduced deployment and operational costs. Localization capability in challenging scenarios, including harsh environments with complex geometry and obstacles, can be provided with robust, reliable, and energy-efficient communication protocols able to combat impairments caused by interference and multipath, such as the IEEE 802.15.4 Time-Slotted Channel Hopping (TSCH) protocol. This paper presents an enhancement of the TSCH protocol that integrates localization functionality along with communication, improving the protocol’s operational capabilities and setting a baseline for monitoring, automation, and interaction within IoT setups in physical environments. A novel approach is proposed to incorporate a hybrid localization by integrating Direction of Arrival (DoA) estimation and Multi-Carrier Phase Difference (MCPD) ranging methods for providing DoA and distance estimates with each transmitted packet. With the proposed enhancement, a single node can determine the location of its neighboring nodes without significantly affecting the reliability of communication and the efficiency of the network. The feasibility and effectiveness of the proposed approach are validated in a real scenario in an office building using low-cost proprietary devices, and the software incorporating the solution is provided. The experimental evaluation results show that a node positioned in the center of the room successfully estimates both the DoA and the distance to each neighboring node. The proposed hybrid localization algorithm demonstrates an accuracy of a few tens of centimeters in a two-dimensional space.

Multi-scale graph clustering network

Deep graph clustering, a fundamental yet formidable task in data analysis, aims to partition samples belonging to the same category into their respective clusters. Recently, significant advancements in graph self-supervised learning have been made through generative and contrastive learning methods. However, existing methods focus on directly aggregating neighboring node information during the feature extraction stage, thereby neglecting the crucial long-range correlations between nodes. Consequently, non-neighbor node information within the same category remains unexplored, leading to subpar performance in the clustering task. To address this issue, we propose a generative method named Multi-scale Graph Clustering Network (MGCN) to learn comprehensive and rich graph representations for deep graph clustering in the feature encoding stage. Specifically, we design a Multi-hop Adaptive Convolutional Module (MACM) integrated into MGCN, which effectively aggregates high-order neighbor node features in each layer of the network. Additionally, we develop an autoencoder to assist MACM in enhancing attribute information, which prevents the node's own features from being overshadowed in the multi-scale feature learning process. Experimental results demonstrate that our proposed MGCN method achieves significantly better clustering performance than existing methods on multiple public datasets.

Distributed fusion filtering for multi-rate nonlinear systems with random sensor failures under event-triggering round-robin-like scheme

The distributed fusion filtering problem is addressed for the multi-rate nonlinear systems with random sensor failures (RSFs) over sensor networks, where a prediction compensation approach is proposed to transform the system unlike the lifting technique. The RSFs are portrayed by using stochastic variables with known statistical properties that satisfy certain probability distribution. In order to prevent data conflicts and reduce unnecessary data transmission, the event-triggering round-robin-like scheme (ETRRLS) is introduced to schedule the data transmission among sensor nodes. The main objectives of this paper are to design a local distributed filtering scheme based on the information of itself and ETRRLS scheduled neighboring nodes, and obtain an upper bound on the local filtering error (LFE) covariance which is minimized based on the filter gains design. Afterward, the local filters are fused by using the sequential covariance intersection fusion criterion. Moreover, we provide a sufficient condition, which can ensure the boundedness of the trace of LFE covariance. Finally, a simulation example is presented to illustrate the effectiveness and superiority of the newly proposed distributed fusion estimation algorithm.

Combined localization and clustering approach for reduced energy presumption in heterogeneous IoT

The field of H-IoT is emerging with enormous potential to empower various technologies. Smart cities and advanced manufacturing are a few of the fields where H-IoT is currently used. The issue with H-IoT is its heavy energy consumption while transmitting data, which makes scaling difficult. To overcome such issues, a hybrid approach of Crayfish Optimization (CFO) with FCM and Restricted Boltzmann Machine (RBM) with Soft Sign Activation (SSA) has been proposed. Initially, Node initialization lays the foundation by configuring individual sensor nodes for network participation. After initialization, Fuzzy C Means clustering optimizes data aggregation by categorizing nodes into clusters based on similarity. Gathering Neighbor Node Traffic Data (NNTD) provides insights into communication patterns. Based on the threshold of NNTD, node localization is performed that enhances network accuracy by pinpointing sensor node locations. Integration of CFO into clustering, along with localization further improves cluster head selection for optimal data routing. Classification through the RBM with SSA function enhances anomaly detection, combining data analysis for optimizing energy utilization in heterogeneous IoT environments. The ‘combined CFO-FCM and SSA-RBM’ has been implemented in MATLAB and achieved an accuracy of 94.50%. As a result, the overall performance of the system is improved.

Neighbors selective Graph Convolutional Network for homophily and heterophily

Graph Convolutional Networks (GCNs) gain remarkable success in graph-related tasks under homophily graph assumption—most connected nodes have the same label. However, this assumption is fragile since heterophily is common in real-world networks, where most linked nodes have different labels. Some methods address heterophily using graph-level weighted combinations of multi-hop neighbor representations. However, they introduce noise and irrelevant information from two aspects: (1) higher-order neighborhoods may include more neighbors with different labels than those with the same label; (2) graph-level weighted combination fails to capture distinct node properties. To address these issues, firstly, a Neighborhood Distribution-induced Similarity (NDS) measure is developed to identify potential similar neighbors for nodes. Secondly, a node-level fusion mechanism Selective-Neighbors Gated Unit (SNGU) is designed to adaptively aggregate potential neighbors, first-hop neighbors, and the node itself by learning distinct weights for nodes. By combining the above two designs, this work proposes a novel Neighbors Selective Graph Convolutional Network (NSGCN), which allows nodes to selectively receive relevant neighbor information for better node representations, effectively modeling homophily and heterophily. Experiments on 10 widely used real-world datasets with varying properties demonstrate the superiority of the NSGCN, surpassing a strong baseline with an absolute increase of 9.83% in classification accuracy. The code is available at https://github.com/GGA23/NSGCN.

Learning Graph Representations Through Learning and Propagating Edge Features.

Graph convolutional networks have achieved considerable success in various graph domain tasks. Recently, numerous types of graph convolutional networks have been developed. A typical rule for learning a node's feature in these graph convolutional networks is to aggregate node features from the node's local neighborhood. However, in these models, the interrelation information between adjacent nodes is not well-considered. This information could be helpful to learn improved node embeddings. In this article, we present a graph representation learning framework that generates node embeddings through learning and propagating edge features. Instead of aggregating node features from a local neighborhood, we learn a feature for each edge and update a node's representation by aggregating local edge features. The edge feature is learned from the concatenation of the edge's starting node feature, the input edge feature, and the edge's end node feature. Unlike node feature propagation-based graph networks, our model propagates different features from a node to its neighbors. In addition, we learn an attention vector for each edge in aggregation, enabling the model to focus on important information in each feature dimension. By learning and aggregating edge features, the interrelation between a node and its neighboring nodes is integrated in the aggregated feature, which helps learn improved node embeddings in graph representation learning. Our model is evaluated on graph classification, node classification, graph regression, and multitask binary graph classification on eight popular datasets. The experimental results demonstrate that our model achieves improved performance compared with a wide variety of baseline models.

An efficient neighbor nodes trust tagging model for optimized route detection in smart grids with secure data transmission

Smart Grids are the control and transmission networks of the future; they allow suppliers and customers to interact in real time to optimize and intelligently manage resources. Although wireless mesh network technology can facilitate these smart functionalities, it is important to address the vulnerabilities and cyber-attack risks that are inherent to it. Smart Grid's reliance on the Internet amplifies security concerns. A number of methods have been proposed to address this issue; while some have made promises, they all need substantial amounts of computational resources. With this technology, channels based on trust can be set up. The security of the system is built utilizing a family relationship-based method, which makes use of measures that may be used to gauge a node's originality. Additionally, the power consumption and signal strength of the node are taken into account. The complexity and extent of the network need the development of new types of smart grid communication. Finding a way to detect and thwart major assaults on routing protocols is another design challenge. Smart grids rely on these protocols in its data system for efficient interchange of renewable energy. A unique secure energy routing mechanism is developed in this proposed model for secure data communication. In the proposed model, a new method for Neighbor Nodes Trust Tagging Model for Optimized Route Detection (NNTT-ORD) is proposed for establishing secure route for data communication in smart grids. The proposed model is compared with the existing model and the results represent that the proposed model route provides a secure environment for data transmission.

PGCF: Perception graph collaborative filtering for recommendation

Extensive studies have fully proved the effectiveness of collaborative filtering (CF) recommendation models based on graph convolutional networks (GCNs). As an advanced interaction encoder, however, GCN-based CF models do not differentiate neighboring nodes, which will lead to suboptimal recommendation performance. In addition, most GCN-based CF studies pay insufficient attention to the loss function and they simply select the Bayesian personalized ranking (BPR) loss function to train the model. However, we believe that the loss function is as important as the interaction encoder and deserves more attentions. To address the above issues, we propose a novel GCN-based CF model, named Perception Graph Collaborative Filtering (PGCF). Specifically, for the interaction encoder, we design a neighborhood-perception GCN to enhance the aggregation of interest-related information of the target node during the information aggregation process, while weakening the propagation of noise and irrelevant information to help the model learn better embedding representation. For the loss function, we design a margin-perception Bayesian personalized ranking (MBPR) loss function, which introduces a self-perception margin, requiring the predicted score of the user-positive sample to be greater than that of the user-negative sample, and also greater than the sum of the predicted score of the user-negative sample and the margin. The experimental results on five benchmark datasets show that PGCF is significantly superior to multiple existing CF models.

Inference of gene regulatory networks based on directed graph convolutional networks.

Inferring gene regulatory network (GRN) is one of the important challenges in systems biology, and many outstanding computational methods have been proposed; however there remains some challenges especially in real datasets. In this study, we propose Directed Graph Convolutional neural network-based method for GRN inference (DGCGRN). To better understand and process the directed graph structure data of GRN, a directed graph convolutional neural network is conducted which retains the structural information of the directed graph while also making full use of neighbor node features. The local augmentation strategy is adopted in graph neural network to solve the problem of poor prediction accuracy caused by a large number of low-degree nodes in GRN. In addition, for real data such as E.coli, sequence features are obtained by extracting hidden features using Bi-GRU and calculating the statistical physicochemical characteristics of gene sequence. At the training stage, a dynamic update strategy is used to convert the obtained edge prediction scores into edge weights to guide the subsequent training process of the model. The results on synthetic benchmark datasets and real datasets show that the prediction performance of DGCGRN is significantly better than existing models. Furthermore, the case studies on bladder uroepithelial carcinoma and lung cancer cells also illustrate the performance of the proposed model.