Pair Of Nodes Research Articles

Identifying Associations between Small Nucleolar RNAs and Diseases via Graph Convolutional Network and Attention Mechanism.

Research has shown that small nucleolar RNAs (snoRNAs) play crucial roles in various biological processes, and understanding disease pathogenesis by studying their relationship with diseases is beneficial. Currently, known associations are insufficient, and conventional biological experiments are costly and time-consuming. Therefore, developing efficient computational methods is crucial for identifying potential snoRNA-disease associations. In this paper, a method to identify snoRNA-disease associations based on graph convolutional network and multi-view graph attention mechanism (GCASDA) is proposed. Firstly, the similarity matrices of snoRNAs and diseases are calculated based on biological entity-related information, and the weights of the edges between the snoRNA nodes and the disease nodes are supplemented by random forest. Then two homogeneous graphs and one heterogeneous graph are constructed. Subsequently, different types of embedded features are extracted from the graphs using specific graph convolutional network structure and integrated through a multi-view graph attention mechanism to obtain node embedded feature representations. Finally, for each pair of nodes, in addition to their global features, node interaction features are passed together to a multilayer perceptron neural network (MLP) to identify snoRNA-disease associations. Experimental results show that GCASDA achieves 0.9356 and 0.9294 in AUC and AUPR, respectively, and significantly outperformed other state-of-the-art methods on the basis of different evaluation metrics. Furthermore, the case study could further demonstrate the realistic feasibility of GCASDA.

Genetic algorithms for optimizing the layout of wireless charging networks

This study explores the improvement of wireless charging network configurations for electric cars (EVs) using genetic algorithms, with the goal of increasing charging efficiency and network performance. The network optimization process takes into account the starting characteristics of include their geographical coordinates, power capacity, and beginning energy levels. Examination of the distance matrix exposes diverse distances between nodes, which impact energy consumption and charging efficiency. The energy consumption estimates between pairs of nodes illustrate the charging needs across the network, revealing that nodes that are farther away have greater energy consumption. The use of genetic algorithms yields a wide range of layouts that are assessed based on their fitness ratings, indicating the excellence of configurations in terms of coverage and connection. Percentage change study demonstrates the modifications in power capacity and node energy levels after optimization, showing prospective improvements in charging capabilities and efficiency. The correlation between node location and energy use is apparent, as nodes in closer proximity demonstrate decreased energy utilization. The convergence of fitness scores demonstrates the algorithm's effectiveness in achieving solutions that are very close to ideal, resulting in significant improvements in charging coverage and energy efficiency. The study highlights the effectiveness of genetic algorithms in improving wireless charging networks, providing valuable information on spatial optimization tactics, energy use patterns, and the resulting improvements in network performance. These results have implications for creating wireless charging infrastructures that are more efficient and long-lasting, in order to satisfy the changing needs of electric car charging networks.

Node Localization Algorithm for Irregular Regions Based on Particle Swarm Optimization Algorithm and Reliable Anchor Node Pairs

Node Localization Algorithm for Irregular Regions Based on Particle Swarm Optimization Algorithm and Reliable Anchor Node Pairs

Structure-Aware DropEdge Toward Deep Graph Convolutional Networks.

It has been discovered that graph convolutional networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. The main factor that accounts for why deep GCNs fail lies in oversmoothing, which isolates the network output from the input with the increase of network depth, weakening expressivity and trainability. In this article, we start by investigating refined measures upon DropEdge-an existing simple yet effective technique to relieve oversmoothing. We term our method as DropEdge ++ for its two structure-aware samplers in contrast to DropEdge: layer-dependent (LD) sampler and feature-dependent (FD) sampler. Regarding the LD sampler, we interestingly find that increasingly sampling edges from the bottom layer yields superior performance than the decreasing counterpart as well as DropEdge. We theoretically reveal this phenomenon with mean-edge-number (MEN), a metric closely related to oversmoothing. For the FD sampler, we associate the edge sampling probability with the feature similarity of node pairs and prove that it further correlates the convergence subspace of the output layer with the input features. Extensive experiments on several node classification benchmarks, including both full-and semi-supervised tasks, illustrate the efficacy of DropEdge ++ and its compatibility with a variety of backbones by achieving generally better performance over DropEdge and the no-drop version.

Patient-sharing relationships among primary healthcare professionals taking care of patients with mental health problems or substance abuse: the social network approach.

Introduction: Mental health disorders are recognized as considerable public health challenges that require close collaboration between professionals. Developing collaboration requires understanding the structure of how patient care is managed across professionals. Healthcare registers offer “naturally occuring” data of how different professionals are involved in patient care.
 Research question: To find out which local and individual factors influence patient-sharing network structure and composition.
 Methodologies: Data were from the Register of Primary Health Care visits (Avohilmo) which covers all outpatient primary healthcare visits in Finland. We combined data on visits from eight health and social centres during the year 2021. We further included to the data only those clients’ visits, who had at least one visit relating primarily to mental health or substance abuse. The patient-sharing networks were formed using the unique ID codes of the professionals and different occupational groups included in the register. Two professionals were considered to have a patient-sharing relationship if they both had delivered care to the same patient. The resulting network was a one-mode undirected network graph with 646 nodes (healthcare professionals) and 50 841 unweighted ties (the number of shared patients) between them. These ties were based on 11 796 patients and 126 521 visits.
 Statistical analyses: We analyzed the potential associations of the network structure and the nodal attributes (working in a specific health and social centre, belonging to a certain occupational group and the reason of the patient visit) with nodal formation using Exponential Random Graph Models (ERGM). ERGMs are statistical models that enable network pattern recognition and are similar to logistic regression: they predict the probability for a pair of nodes in a network to have a tie between them (in this case that two professionals share the same patient).
 Results: Our results show that there are uniform effects regarding occupational group and health and social centre. Two professionals were more likely to share a patient if they had similar occupation and naturally when they worked in the same centre. The coefficient for shared partners was positive indicating a propensity for a triadic closure in the network. The main effects were also significant suggesting that being a physician predicts having more connections than belonging to other occupational groups. There were also significant differences between the centres suggesting that the differences in degrees between centres were not random. More importantly, the main effect of the reason for the patient visit was significant, suggesting that when the reason for visit was related to mental health problems or substance abuse the connections with other professionals were more probable, than when the reason was related to other health issues. 
 Conclusion: The results suggest that professionals seem to work more often within their own occupational group than with other professionals. Contacts between professionals were more probable when the reason for visit was related to mental health problems or substance abuse. Further research is needed to examine, whether sharing patients also indicate that there is collaboration between the professionals.

GCN-Based Heterogeneous Complex Feature Learning to Enhance Predictability for LncRNA-Disease Associations.

Using computational models to predict potential lncRNA-disease associations (LDAs) has emerged as an effective supplement to bioexperiments for exploring the pathogenesis of diseases. However, current computational models still face limitations in their ability to learn the complex features of bionetworks. In this study, HGCNLDA, a model which combines graph convolutional network (GCN)-based aggregation, heterogeneous information fusion, and a bilinear-decoder to infer LDAs was proposed. Recognizing the need to extract essential features during data processing, our HGCNLDA explored four key steps for uncovering interaction patterns within the bionetwork: (1) a novel type of tripartite heterogeneous network, known as the lncRNA-disease-miRNA network (LDMN), was constructed using computed similarities and known associations. (2) Homogeneous and heterogeneous features of nodes were extracted from domains within the LDMN by a GCN-based encoder. (3) Feature fusions, including bipolymerization operations and attention mechanism, were employed to capture a more accurate and comprehensive representation of nodes. (4) Bilinear-decoder was used to rebuild the edge type (or rating type) for a specific node pair, resulting in the predicted association score. Through a 5-fold cross-validation on two data sets, namely, data set1 and data set2, our HGCNLDA consistently demonstrated superior performance compared to five related models. It almost achieved the highest AUROC and AUPR values on both data sets, especially on data set2 where the results obtained were more challenging and objective. Case studies involving three real cancer scenarios further validated the practicality of HGCNLDA in identifying potential LDAs in real-world contexts. The source code and data for this study are available at https://github.com/zywait/HGCNLDA.

Concurrent Design Optimization of Tether-Net System and Actions for Reliable Space-Debris Capture

Tether-nets deployed from a chaser spacecraft are a promising solution to capturing space debris. The success of the one-shot capture process depends on the net’s structural dynamic properties, attributed to its physical design, and on the ability to perform an optimal launch and closure subject to sensing and actuation uncertainties. Hence, this paper presents a reliability-based optimization framework to simultaneously optimize the net design and its launch and closing actions to minimize the system mass (case 1) or closing time (case 2) while preserving a specified probability of capture success. Success is assessed in terms of a capture quality index and the number of locked node pairs. Gaussian noise is used to model the uncertainties in the dynamics, state estimation, and actuation of the tether-net, which is propagated via Monte Carlo sampling. To account for uncertainties and ensure computational efficiency, given the cost of simulating the tether-net dynamics, Bayesian optimization is used to solve this problem. Optimization results show that the mission success rate in the presence of uncertainties has increased from 75% to over 98%, while the capture completion time has almost halved.

Robust Posegraph Optimization Using Proximity Points

This paper proposes a robust posegraph optimization (PGO) method for posegraphs with keypoints. In the conventional PGO formulation, a loop constraint is defined between a pair of nodes, whereas in the proposed method, it is defined between a pair of keypoints. In this manner, robust PGO based on switch variables can be realized in a more fine-grained manner. Loop constraint is defined based on the unique geometric property of proximity point, and implemented as a new edge type of the g2o solver. The proposed method is compared with other robust PGO methods using real world data recorded in Nakanoshima Robot Challenge 2021.

Routing schemes for hybrid communication networks

We consider the problem of computing routing schemes in the HYBRID model of distributed computing where nodes have access to two fundamentally different communication modes. In this problem nodes have to compute small labels and routing tables that allow for efficient routing of messages in the local network, which typically offers the majority of the throughput. Recent work has shown that using the HYBRID model admits a significant speed-up compared to what would be possible if either communication mode were used in isolation. Nonetheless, if general graphs are used as the input graph the computation of routing schemes still takes polynomial rounds in the HYBRID model.We bypass this lower bound by restricting the local graph to unit-disc-graphs and solve the problem deterministically with running time O(|H|2+log⁡n), label size O(log⁡n), and size of routing tables O(|H|2⋅log⁡n) where |H| is the number of “radio holes” in the network. Our work builds on recent work by Coy et al., who obtain this result in the much simpler setting where the input graph has no radio holes. We develop new techniques to achieve this, including a decomposition of the local graph into path-convex regions, where each region contains a shortest path for any pair of nodes in it.

Higher-order interactions disturb community detection in complex networks

Edges are the most basic structures in complex networks, representing relationships of node pairs. However, many higher-order interactions in reality are beyond node-to-node relationships. In recent years, the conceptualization of “higher-order structures” is considered to provide information on multiple scales, which is helpful to discover new conclusions or achieve better results in issues such as propagation, synchronization, and evolution. But for community identification, the impact of higher-order interactions may not be positive. In this study, we discovered that higher-order interactions disproportionately increase the count of edges. This poses a substantial challenge for community detection, especially when we found that higher-order interactions tend to cross multiple communities. The existence of higher-order interactions obscures the community structure in the network. And once we realize this, removing some of the higher-order interactions is an easy way to improve the accuracy of community detection.

Online distributed waveform-synchronization for acoustic sensor networks with dynamic topology

Acoustic sensing by multiple devices connected in a wireless acoustic sensor network (WASN) creates new opportunities for multichannel signal processing. However, the autonomy of agents in such a network still necessitates the alignment of sensor signals to a common sampling rate. It has been demonstrated that waveform-based estimation of sampling rate offset (SRO) between any node pair can be retrieved from asynchronous signals already exchanged in the network, but connected online operation for network-wide distributed sampling-time synchronization still presents an open research task. This is especially true if the WASN experiences topology changes due to failure or appearance of nodes or connections. In this work, we rely on an online waveform-based closed-loop SRO estimation and compensation unit for nodes pairs. For WASNs hierarchically organized as a directed minimum spanning tree (MST), it is then shown how local synchronization propagates network-wide from the root node to the leaves. Moreover, we propose a network protocol for sustaining an existing network-wide synchronization in case of local topology changes. In doing so, the dynamic WASN maintains the MST topology after reorganization to support continued operation with minimum node distances. Experimental evaluation in a simulated apartment with several rooms proves the ability of our methods to reach and sustain accurate SRO estimation and compensation in dynamic WASNs.

Improving Augmentation Consistency for Graph Contrastive Learning

Graph contrastive learning (GCL) enhances unsupervised graph representation by generating different contrastive views, in which properties of augmented nodes are required to be aligned with their anchors. However, we find that in some existing GCL methods, it is hard to inherit semantic and structural properties of graphs from anchor views due to inconsistent augmentation schemes, which may hurt node consistency in augmented views. In this paper, we present ConGCL to improve node consistency and enhance node classification. Specifically, we first consider context entailment, which integrates the semantic and structural properties to better mine the underlying consistency relationships of nodes. Beneficial from this, we then design a novel consistency improvement loss to maintain augmentation consistency agreement among positive node pairs under stochastic augmentation schemes. To investigate the effectiveness of ConGCL on improving augmentation consistency and enhancing node classification, we conduct empirical study and extensive experiments on benchmark datasets. The code is available at: https://github.com/brysonwx/ConGCL.

DeepWalk with Reinforcement Learning (DWRL) for node embedding

DeepWalk is used to convert nodes in an original graph into equivalent vectors in a latent space for performing various predictive tasks. To ensure second-order structural similarity between nodes in the original graph and their vectors in the latent space, dot products are applied to each pair of nodes explored on the random walk (RW) in the latent space. However. dot products for graphs with millions of nodes and billions of edges are computationally expensive. To minimize the computation time required for calculating the second-order structural similarity, DeepWalk with reinforcement learning (DWRL) is proposed herein. In DWRL, a level pointer for each node in the original graph is prepared. By identifying common nodes between each pair of nodes in the original graph, the number of computations in the dot product in the latent space is reduced, thereby ensuring second-order structural similarity. Additionally, repeated selection of the same node during RWs produces redundant samples for training. Therefore, the subsampling technique is used to choose the next node based on its degree, which improves the generalization of node representations in the latent space and increases accuracy. The proposed techniques are applied to popular datasets to perform multilabel classification and link prediction tasks, and their efficiency in reducing the computation time is verified. The proposed DWRL minimizes the computation time 47% for large graphs to build latent vectors and improves the average micro and macro F1 scores up to 12%. The link prediction performance also increases up to 20%.

A Comprehensive Review of Similarity Based Link Prediction Methods for Complex Networks including Computational Biology

Information retrieval is one of the most challenging tasks for the mankind and to retrieve information interaction is required, which ultimately leads to the formation of networks. Universe is packed with different type of networks. Networks with complex topological properties are called complex network. Such types of networks are major tools for learning the connection between the organizations and finding the purpose of complex systems. The link prediction problems in complex networks facilitate predictions about the future organization of the network. Network is represented as a graph. The data in the network is signified by nodes, and the relations are represented by links. The future of non-connected links amid node pairs is predicted. This paper reviews the methods used to predict links for complex networks using similarity-based heuristics. Previous reviews, despite having a clear outline of the link prediction study, only described the prediction approaches. Research gaps between the similarity-based link prediction techniques, however, were not explicitly stated. With the help of chronological findings and a research gaps approach, this review seeks to give a continuing review and introduce the link prediction.

WDP-GAN: Weighted Graph Generation With GAN Under Differential Privacy

Many real-world networks can be represented as weighted graphs, where weights represent the closeness or importance of relationships between node pairs. Sharing these graphs is beneficial for many applications while potentially leading to privacy breaches. Variants of deep learning approaches have been developed for synthetic graph publishing, but privacy-preserving graph (especially weighted graph) publishing has not been fully addressed. To bridge this gap, we propose WDP-GAN, a generative adversarial network (GAN) based privacy-preserving weighted graph generation approach, which can generate unlimited synthetic graphs of a given weighted graph while ensuring individual privacy. To do this, we devise a new node sequence sampling method to generate the training set while preserving both the edge weight and topological structure of the original graph. Moreover, we apply the bi-directional long-short term memory (Bi-LSTM) network to capture the interdependence of node pairs. WDP-GAN then approximates the edge weight information using the frequencies of edges produced by the generator. Furthermore, we propose an adaptive gradient perturbation algorithm to improve the speed and stability of the training process while ensuring individual privacy. Theoretical analysis and experiments on real-world network datasets show that WDP-GAN can generate graphs that effectively preserve structural utility while satisfying differential privacy.

On the Power of Gradual Network Alignment Using Dual-Perception Similarities.

Network alignment (NA) is the task of finding the correspondence of nodes between two networks based on the network structure and node attributes. Our study is motivated by the fact that, since most of existing NA methods have attempted to discover all node pairs at once, they do not harness information enriched through interim discovery of node correspondences to more accurately find the next correspondences during the node matching. To tackle this challenge, we propose Grad-Align, a new NA method that gradually discovers node pairs by making full use of node pairs exhibiting strong consistency, which are easy to be discovered in the early stage of gradual matching. Specifically, Grad-Align first generates node embeddings of the two networks based on graph neural networks along with our layer-wise reconstruction loss, a loss built upon capturing the first-order and higher-order neighborhood structures. Then, nodes are gradually aligned by computing dual-perception similarity measures including the multi-layer embedding similarity as well as the Tversky similarity, an asymmetric set similarity using the Tversky index applicable to networks with different scales. Additionally, we incorporate an edge augmentation module into Grad-Align to reinforce the structural consistency. Through comprehensive experiments using real-world and synthetic datasets, we empirically demonstrate that Grad-Align consistently outperforms state-of-the-art NA methods.

Inter‐network connectivity of early Aβ and tau‐seeded functional networks is associated with longitudinal tau accumulation in at‐risk cognitively normal older adults

AbstractBackgroundFunctional connectivity (FC) between networks may be related to Aβ and tau interactions in preclinical Alzheimer’s disease (AD). Here, we investigated associations between inter‐network FC of early Aβ and tau‐seeded networks, APOEe4, global Aβ, and longitudinal tau accumulation in cognitively healthy older adults (OA).MethodVoxel‐wise PiB‐PET and FTP‐PET OA images were ordered by increasing pathology burden and iteratively compared to a reference set of young adult (YA) PET images. Peak voxels of the earliest significant differences were matched to Brainnetome ROIs and used to construct separate Aβ and tau‐seeded networks within a group average YA FC matrix (Figure 1). Next, the average inter‐network FC between all node pairs between the networks was calculated in OA (n = 60; aged 77.6±5.5). Longitudinal FTP slopes of the entorhinal cortex (EC) and inferior temporal gyrus (ITG) were estimated using linear mixed effects models. Linear regression was used to assess relationships between baseline inter‐network FC, APOEe4 status, baseline global PiB, and both a prior ROI and voxel‐wise FTP slopes.ResultIn all OA, inter‐network FC was not associated with baseline global PIB (t(58) = ‐0.23, p = 0.82), EC FTP slope (t(58) = 0.49, p = 0.63), or ITG FTP slope (t(58) = ‐1.45, p = 0.15). There was a significant interaction between baseline global PiB status and inter‐network FC where FC was negatively associated with ITG FTP slope in PiB+ participants (t(56) = ‐2.01, p = 0.04; Figure 2A). There was also a significant interaction between APOEe4 status and inter‐network FC in predicting ITG FTP slope with a negative relationship only in e4 carriers (t(56) = ‐3.19, p = 0.003; Figure 2B). Voxel‐wise analyses revealed significant negative relationships between inter‐network FC and FTP slope in the left fusiform gyrus and ITG in PiB+ participants and e4 carriers, respectively (Figure 2C‐D).ConclusionLower baseline inter‐network FC of early Aβ and tau‐seeded networks was associated with greater longitudinal tau accumulation outside of the medial temporal lobe (MTL) in cognitively normal OA with higher AD risk (i.e., elevated Aβ or APOEe4). Our results suggest that this network disruption is associated with faster rates of tau accumulation outside of the MTL, possibly reflecting a later stage in the preclinical progression to AD.

Dynamics of information networks

AbstractWe explore a simple model of network dynamics which has previously been applied to the study of information flow in the context of epidemic spreading. A random rooted network is constructed that evolves according to the following rule: at a constant rate, pairs of nodes (i, j) are randomly chosen to interact, with an edge drawn from i to j (and any other out-edge from i deleted) if j is strictly closer to the root with respect to graph distance. We characterise the dynamics of this random network in the limit of large size, showing that it instantaneously forms a tree with long branches that immediately collapse to depth two, then it slowly rearranges itself to a star-like configuration. This curious behaviour has consequences for the study of the epidemic models in which this information network was first proposed.

Computing minimal solutions to the ring loading problem

Given a cycle graph of n nodes and a non-negative demand di,j for each pair of nodes i,j, the ring loading problem with demand splitting (RLPW) asks to determine a routing of these demands such that the maximum load on any edge is minimal. In this work, we present an algorithm for computing minimal solutions to RLPW in O(n2) time. This algorithm, when employed as a subroutine, also improves the runtimes for several other ring loading algorithms by a factor of up to O(n2).

AGCL: Adaptive Graph Contrastive Learning for graph representation learning

Unsupervised graph representation learning has attracted great attention as it can learn low-dimensional and compact node embeddings from high-dimensional and sparse graph data without labels. However, two major drawbacks exist in most previous methods, i.e., limited applications of the global graph structure and the problem of the false-negative samples.To address the above problems, we propose a novel Adaptive Graph Contrastive Learning (AGCL) method that utilizes multiple graph filters to capture both the local and the global view information and propose a novel adaptive graph contrastive learning framework to alleviate the false-negative sample problem. AGCL first utilizes a Graph Convolution Network (GCN) filter and our designed Diffusion-based filters to smooth the initial node features. Then, AGCL measures the node pair similarity and then iteratively selects the similar and the dissimilar node pairs as the positive and the negative samples to do the graph contrastive learning. Finally, AGCL leverages various aggregators to obtain node embeddings from multiple views. In addition, we further propose AGCL-Light which can reduce the complexity of updating the training samples, which pre-selects a similar node subset for each node for the subsequent updates. Extensive experiments on nine benchmark datasets demonstrate that our models outperform previous state-of-the-art methods.