Direct Neighbors Research Articles

Global Graph Attention Embedding Network for Relation Prediction in Knowledge Graphs.

The incompleteness of knowledge graphs triggers considerable research interest in relation prediction. As the key to predicting relations among entities, many efforts have been devoted to learning the embeddings of entities and relations by incorporating a variety of neighbors' information which includes not only the information from direct outgoing and incoming neighbors but also the ones from the indirect neighbors on the multihop paths. However, previous models usually consider entity paths of limited length or ignore sequential information of the paths. Either simplification will make the model lack a global understanding of knowledge graphs and may result in the loss of important and indispensable information. In this article, we propose a novel global graph attention embedding network (GGAE) for relation prediction by combining global information from both direct neighbors and multihop neighbors. Concretely, given a knowledge graph, we first introduce the path construction algorithms to obtain meaningful paths, then design path modeling methods to capture the potential long-distance sequential information in the multihop paths, final propose an entity graph attention and a relation graph attention mechanisms to obtain entity embeddings and relation embeddings. Moreover, an entity graph attention mechanism is proposed to calculate the entity embeddings by aggregating direct incoming and outgoing neighbors from: 1) an original knowledge graph with the original entity and relation embeddings and 2) a new knowledge graph constructed by the paths whose embeddings are updated by path modeling methods. for each relation, we construct a new graph with related entities and present a relation graph attention to learn the features. Therefore, our model can encapsulate the information from different distance neighbors, and enable the embeddings of entities and relations to better capture all-sided semantic information. The experimental results on benchmark datasets verify the superiority of our model over the state-of-the-art ones.

A finite time discrete distributed learning algorithm using stochastic configuration network

In this paper, we propose a finite-time discrete distributed learning algorithm, denoted as the FTDDL algorithm, using the Stochastic Configuration Network (SCN) and Zero Gradient Sum (ZGS) strategy. In distributed scenarios, the communication networks that store data are modeled as algebraic graphs and the learning problems are formulated as distributed optimization problems. The FTDDL algorithm persists the universal approximation of the SCN learner. The process of the FTDDL algorithm is divided into two phases, namely “distributed hidden parameters configuration” and “distributed output weights determination”. It has been theoretically proved that the FTDDL algorithm works in distributed manner and achieves the same efficiency as the centralized SCN. According to the FTDDL algorithm, each node over the communication network transmits the updated output weights of the SCN with its direct neighbors. Thus, the FTDDL algorithm preserves data privacy and saves network bandwidth. The FTDDL algorithm is theoretically proved to converge to the global optimal output weights of the SCN within finite time. Compared with the other distributed learning algorithms using SCNs, the FTDDL algorithm can significantly reduce the iteration times. At last, some experiments are shown in Simulations part to verify the effectiveness of the FTDDL algorithm.

A Novel Trust Adaptability Approach for Secure Data Transmissions using Enhanced Collaborative Nodes Trustworthiness in Mobile Ad-hoc Networks

Objectives: To find an efficient security routing model based on trust adaptability by considering various transmission parameters that influence the node’s behavior. Methods: Enhanced Collaborative Trust Based Approach (ECTBA) was applied to isolate the malicious nodes from routing by computing their enhanced collaborative trust value based on the node’s behavior using transmission parameters. Parameters that influence the node’s behavior like the number of data packets and control packets forwarded, dropped, or misrouted by the node are quantified to compute direct trust value and neighbor reputation. Node’s Enhanced Collaborative trust value was generated by the combination of direct and neighbor observations. Findings: The proposed strategy is compared with several cases like the Direct Trust Based Approach (DTBA), where routing involves trustworthy nodes categorized based on only direct trust, existing methods like Belief-dependent trust evolution method(BETM), Novel extended trust-dependent method (NETM) where routing is done with nodes that are categorized as trustworthy depending on direct and indirect observations and simple AODV routing performed with all the possible random nodes without any trust detection. The performance parameters of the proposed ECTBA exhibit a success rate of 10.2% in false positives detection (FPD),network throughput of 438.12 Kbps,and packet delivery ratio (PDR) of 92.3%.This method proves to be a better method when compared with the traditional trust-based security methods(BETM and NETM) in terms of efficiency. Novelty: This research suggested a novel and fine-tuned method for quantifying a node’s trustworthiness and for secure routing that coupled the direct and indirect observations into enhanced collaborative trustbased on the node’s behavior by considering the transmission parameters. The present work highlights the combination of data packets forwarding behavior and control packets forwarding behavior in computing enhanced collaborative trust to decide the involvement of intermediate trustworthy nodes’ which is not tried before but this study does. Keywords: Dynamic Topology; Direct Trust; Neighbor Trust; Secure Routing; Enhanced Collaborative Trust

Distributed Kalman Filtering Through Trace Proximity

This article is concerned with the distributed Kalman filtering problem for discrete-time linear systems whose measurement information comes from a set of sensor nodes that can communicate with their direct neighbors. Two algorithms for distributed Kalman filtering are proposed, where the first algorithm is based on single-node measurement and the second algorithm is based on neighboring-node measurements. In order to improve the performance, a novel criterion is introduced to the algorithm design, where in the criterion, the proximity of matrix’s trace is used to determine the proximity of positive semidefinite matrix. We prove that all the proposed algorithms for distributed Kalman filtering are unbiased. Numerical examples are provided to demonstrate the correctness of the proposed theoretical method and the performance of the proposed new design technique.

SFGAE: a self-feature-based graph autoencoder model for miRNA-disease associations prediction.

Increasing evidence has suggested that microRNAs (miRNAs) are important biomarkers of various diseases. Numerous graph neural network (GNN) models have been proposed for predicting miRNA-disease associations. However, the existing GNN-based methods have over-smoothing issue-the learned feature embeddings of miRNA nodes and disease nodes are indistinguishable when stacking multiple GNN layers. This issue makes the performance of the methods sensitive to the number of layers, and significantly hurts the performance when more layers are employed. In this study, we resolve this issue by a novel self-feature-based graph autoencoder model, shortened as SFGAE. The key novelty of SFGAE is to construct miRNA-self embeddings and disease-self embeddings, and let them be independent of graph interactions between two types of nodes. The novel self-feature embeddings enrich the information of typical aggregated feature embeddings, which aggregate the information from direct neighbors and hence heavily rely on graph interactions. SFGAE adopts a graph encoder with attention mechanism to concatenate aggregated feature embeddings and self-feature embeddings, and adopts a bilinear decoder to predict links. Our experiments show that SFGAE achieves state-of-the-art performance. In particular, SFGAE improves the average AUC upon recent GAEMDA [1] on the benchmark datasets HMDD v2.0 and HMDD v3.2, and consistently performs better when less (e.g. 10%) training samples are used. Furthermore, SFGAE effectively overcomes the over-smoothing issue and performs stably well on deeper models (e.g. eight layers). Finally, we carry out case studies on three human diseases, colon neoplasms, esophageal neoplasms and kidney neoplasms, and perform a survival analysis using kidney neoplasm as an example. The results suggest that SFGAE is a reliable tool for predicting potential miRNA-disease associations.

Graph Mixed Random Network Based on PageRank

In recent years, graph neural network algorithm (GNN) for graph semi-supervised classification has made great progress. However, in the task of node classification, the neighborhood size is often difficult to expand. The propagation of nodes always only considers the nearest neighbor nodes. Some algorithms usually approximately classify by message passing between direct (single-hop) neighbors. This paper proposes a simple and effective method, named Graph Mixed Random Network Based on PageRank (PMRGNN) to solve the above problems. In PMRGNN, we design a PageRank-based random propagation strategy for data augmentation. Then, two feature extractors are used in combination to supplement the mutual information between features. Finally, a graph regularization term is designed, which can find more useful information for classification results from neighbor nodes to improve the performance of the model. Experimental results on graph benchmark datasets show that the method of this paper outperforms several recently proposed GNN baselines on the semi-supervised node classification. In the research of over-smoothing and generalization, PMRGNN always maintains better performance. In classification visualization, it is more intuitive than other classification methods.

Graph Theory Analysis of Semantic Fluency in Russian-English Bilinguals.

Semantic category fluency is a widely used task involving language, memory, and executive function. Previous studies of bilingual semantic fluency have shown only small differences between languages. Graph theory analyzes complex relationships in networks, including node and edge number, clustering coefficient, average path length, average number of direct neighbors, and scale-free and small-world properties. To shed light on whether the underlying neural processes involved in semantic category fluency testing yield substantially different networks in different languages. We compared languages and methods using both network analysis and conventional analysis of word production. We administered the animal naming task to 51 Russian-English bilinguals in each language. We constructed network graphs using three methods: (a) simple association of unique co-occurring neighbors, (b) corrected associations between consecutive words occurring beyond chance, and (c) a network community approach using planar maximally filtered graphs. We compared the resultant network analytics as well as their scale-free and small-world properties. Participants produced more words in Russian than in English. Small-worldness metrics were variable between Russian and English but were consistent across the three graph theory analytical methods. The networks had similar graph theory properties in both languages. The optimal methodology for creating networks from semantic category fluency remains to be determined.

Latent neighborhood-based heterogeneous graph representation

Graph, as a powerful data structure, has shown superior capability on modeling complex systems. Since real-world objects and their interactions are often multi-modal and multi-typed, compared with traditional homogeneous graphs, heterogeneous graphs can represent real-world objects more effectively. Meanwhile, rich semantic information brings great challenges for learning heterogeneous graph representation (HGR). Most existing HGR methods are based on the concept of meta-path, which is constructed based on direct neighbors and define composite semantic relations in heterogeneous graph. However, when the direct neighbor information is inadequate, which always happens due to insufficient observation, the quality of meta-paths cannot be guaranteed. Therefore, we propose a novel HGR framework based on latent direct neighbors. Specifically, random walks are first utilized to discover the potential candidates from indirect neighbors. Then HodgeRank is introduced to determine the latent direct neighbors according to their importance to the target. After that, neighborhood relationships are augmented with the selected latent direct neighbors, and the adjacency tensor of the heterogeneous graph is refactored correspondingly. Finally, Graph Transformer Network is adopted to construct semantic meta-paths automatically and generate HGR. Numerical experiments on different real-world heterogeneous networks show that our new approach can produce more meta-path instances and introduce more complex and diverse semantic information, and consequently achieves more accurate predictions compared with several state-of-the-art baselines.

Matching Biomedical Ontologies via a Hybrid Graph Attention Network.

Biomedical ontologies have been used extensively to formally define and organize biomedical terminologies, and these ontologies are typically manually created by biomedical experts. With more biomedical ontologies being built independently, matching them to address the problem of heterogeneity and interoperability has become a critical challenge in many biomedical applications. Existing matching methods have mostly focused on capturing features of terminological, structural, and contextual semantics in ontologies. However, these feature engineering-based techniques are not only labor-intensive but also ignore the hidden semantic relations in ontologies. In this study, we propose an alternative biomedical ontology-matching framework BioHAN via a hybrid graph attention network, and that consists of three techniques. First, we propose an effective ontology-enriching method that refines and enriches the ontologies through axioms and external resources. Subsequently, we use hyperbolic graph attention layers to encode hierarchical concepts in a unified hyperbolic space. Finally, we aggregate the features of both the direct and distant neighbors with a graph attention network. Experimental results on real-world biomedical ontologies demonstrate that BioHAN is competitive with the state-of-the-art ontology matching methods.

Pak Afghan Border Problems and its Inferences on Pushtoon Both Sides Residents

It is widely accepted that Pakistan is situated at a very important strategic location on world map. Russia, China and Central Asian countries in north, Middle east in south west and far east countries in east of Pakistan makes this country strategically very important among world nations. Because of its valuable strategic location, most importantly its sea connection to the central Asian states, China and Russia which connects trade, oil and gas routs to the rest of the world through warm waters increases the importance of the country at no-match level. As every big fortune brings a trouble, this strategic importance brings a lot of troubles for the country. After world war II, Soviet Union needed to access warm waters for its uninterrupted connectivity with the world through sea routs. For that Soviets need a good sea port, the options they had were limited. Either they would connect through Chabahar port, Iran or either they would touch Baluchistan region of Pakistan. Comparatively, they found Pakistan an easy target aimed their invasion to Afghanistan as their direct neighbor and Pakistan as a weak state and a sandwich between India and Russia through Afghanistan. Besides this scenario, since the foundation of Pakistan, mismanagement at Pakistan Afghanistan border has been a reason of conflicts. A well secure and managed border can bring stability in economic and security situation of the region. After Soviet invasion, federally administered tribal areas (FATA) became the heaven of militant groups and the symbol of resistance against Soviet forces. Since that time, cross border movement of militant groups is a huge security concern for both countries. Available data also suggests that Pakistan has suffered huge economic and security costs because of the mismanagement of its western border with Afghanistan. In order to maintain peace and stability in the region, Pakistan has proposed and started construction of fences and infrastructure in 2016 including gateways for trade and cross border activities of complex socio-economic tribal system on the both sides of Pak-Afghanistan border. These steps significantly reduced cross border terrorist activities.

Node Pair Information Preserving Network Embedding Based on Adversarial Networks.

Network embedding aims to learn the low-dimensional node representations for networks, which has attracted an increasing amount of attention in recent years. Most existing efforts in this field attempt to embed the network based on node similarity, which generally relies on edge existence statistics of the network. Instead of relying on the global edge existence statistics for every node pair, in this article, we utilize the information between a pair of nodes in a local way and propose a model, called node pair information preserving network embedding (NINE), based on adversarial networks. The main idea lies in preserving the node pair information (NI) by means of adversarial networks. The architecture of the proposed NINE model consists of three main components, namely: 1) NI embedder; 2) NI generator; and 3) NI discriminator. In the NI embedder, to avoid the complicated similarity calculation for a pair of nodes, the original NI vector calculated from the direct neighbor information of the two nodes is adopted as features, and the edge existence information is taken as labels to learn the embedded NI vector in a supervised learning manner. The second component is the NI generator, which takes the original node representation vectors of a node pair as input and outputs the generated NI vector. In order to make the generated NI vector follow the same distribution of the corresponding embedded NI vector, the generative adversarial network (GAN) is adopted, resulting in the third component, called the NI discriminator. Extensive experiments are conducted on seven real-world datasets in three downstream tasks, namely: 1) network reconstruction; 2) link prediction; and 3) node classification. Comparison results with seven state-of-the-art models demonstrate the effectiveness, efficiency, and rationality of our model.

Behind the Wall-Compartment-Specific Neovascularisation during Post-Stroke Recovery in Mice.

Ischemic stroke is a highly prevalent vascular disease leading to oxygen- and glucose deprivation in the brain. In response, ischemia-induced neovascularization occurs, which is supported by circulating CD34+ endothelial progenitor cells. Here, we used the transient middle cerebral artery occlusion (tMCAO) mouse model to characterize the spatio-temporal alterations within the ischemic core from the acute to the chronic phase using multiple-epitope-ligand cartography (MELC) for sequential immunohistochemistry. We found that around 14 days post-stroke, significant angiogenesis occurs in the ischemic core, as determined by the presence of CD31+/CD34+ double-positive endothelial cells. This neovascularization was accompanied by the recruitment of CD4+ T-cells and dendritic cells as well as IBA1+ and IBA1− microglia. Neighborhood analysis identified, besides pericytes only for T-cells and dendritic cells, a statistically significant distribution as direct neighbors of CD31+/CD34+ endothelial cells, suggesting a role for these cells in aiding angiogenesis. This process was distinct from neovascularization of the peri-infarct area as it was separated by a broad astroglial scar. At day 28 post-stroke, the scar had emerged towards the cortical periphery, which seems to give rise to a neuronal regeneration within the peri-infarct area. Meanwhile, the ischemic core has condensed to a highly vascularized subpial region adjacent to the leptomeningeal compartment. In conclusion, in the course of chronic post-stroke regeneration, the astroglial scar serves as a seal between two immunologically active compartments—the peri-infarct area and the ischemic core—which exhibit distinct processes of neovascularization as a central feature of post-stroke tissue remodeling. Based on our findings, we propose that neovascularization of the ischemic core comprises arteriogenesis as well as angiogenesis originating from the leptomenigeal vasculature.

Cross-Layer Optimization Spatial Multi-Channel Directional Neighbor Discovery with Random Reply in mmWave FANET

MmWave FANETs play an increasingly important role in the development of UAVs technology. Fast neighbor discovery is a key bottleneck in mmWave FANETs. In this paper, we propose a two-way neighbor discovery algorithm based on a spatial multi-channel through cross-layer optimization. Firstly, we give two boundary conditions of the physical (PHY) layer and media access control (MAC) layer for successful link establishment of mmWave neighbor discovery and give the optimal pairing of antenna beamwidth in different stages and scenarios using cross-layer optimization. Then, a mmWave neighbor discovery algorithm based on a spatial multi-channel is proposed, which greatly reduces the convergence time by increasing the discovery probability of nodes in the network. Finally, a random reply algorithm is proposed based on dynamic reserved time slots. By adjusting the probability of reply and the number of reserved time slots, the neighbor discovery time can be further reduced when the number of nodes is larger. Simulations show that as the network scale is 100 to 500 nodes, the convergence time is 10 times higher than that of the single channel algorithm.

A Simple Yet Effective Layered Loss for Pre-Training of Network Embedding

Pre-training of network embedding aims to encode unlabeled node proximity into a low-dimensional space, where nodes are close to their neighbors while being far from negative samples. In recent years, Graph Neural Networks have shown groundbreaking performance in semi-supervised learning on the node classification and link prediction tasks. However, because of their inherent information aggregation pattern, almost all these methods can only obtain inferior embedding results in the pre-training of the unlabeled nodes. The margins between a target node and its multi-hop neighbors become hard distinguishable during node message aggregation. To address this problem, we propose a simple yet effective layered loss to combine with a graph attention network, dubbed as LlossNet, for pre-training. We regard the proximity of a target node and its two-hop neighbors as a unit (called a unit graph), where a target node is needed to be more closer to its direct neighbor than its two-hop neighbors. As such, LlossNet would be able to preserve the margins of nodes in the learned embedding space. Experimental results of various downstream tasks including classification and clustering demonstrate the effectiveness of our method on learning discriminative node representations.

Research on Product Design Strategy Based on User Preference and Machine Learning Intelligent Recommendation

In the machine learning model, intelligent recommendation system can select valuable information from a lot of data to help users find the products or services they need, which has been more and more widely used in recent years. However, there are still many problems in machine learning recommender systems, such as data sparsity, natural noise, and cold start, which leads to the fact that machine learning recommender systems cannot obtain accurate user preferences. When a project is rated, the quality of the recommendation is greatly affected. In order to solve the problem that the existing recommendation algorithms have poor recommendation results in sparse data sets, this paper proposes a machine learning method for recommendation rating prediction based on user interest concept lattice. Firstly, the nearest neighbors are divided into direct nearest neighbors and indirect nearest neighbors by user interest concept lattice. Then, different methods are used to calculate the similarity between the direct “nearest neighbor” and the target user, and the similarity between the indirect “nearest neighbor” and the target user. Finally, the invisible item score of the target user is calculated by the similarity value. Experiments are carried out on real data sets, and the experimental results show that the CFCNN-CL algorithm and RRP-UI CL algorithm proposed in this paper have high recommendation accuracy and still have good performance in the case of sparse data.

Path-aware multi-hop graph towards improving graph learning

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in graph-related tasks. Most of them pass messages between direct neighbors and the deeper GNNs can theoretically capture the more global neighborhood information. However, they often suffer from over-smoothing problems when the GNNs’ depth deepens. To eliminate this limitation, we propose a path-aware multi-hop graph framework with hop-level attention (HAPG), which has a larger receptive field than GNNs with the same depth. HAPG generates some multi-path multi-hop graphs by converting the original graph to achieve message passing between multi-hop neighbors in a single layer. HAPG aggregates one-hop and multi-hop neighbors by stacking the original graph and the generated graphs into GNNs. The node embeddings are obtained by combining the multiple outputs of the GNNs with the help of hop-level attention. Comparative experiments with various existing GNNs are conducted on three benchmark datasets, and results show that the HAPG is an effective way for improving these models. Specifically, for semi-supervised node classification tasks, the proposed HAPG-GAT and HAPG-AGNN have achieved state-of-the-art performance.

Quantifying the spatial homogeneity of urban road networks via graph neural networks

Quantifying the topological similarities of different parts of urban road networks enables us to understand urban growth patterns. Although conventional statistics provide useful information about the characteristics of either a single node’s direct neighbours or the entire network, such metrics fail to measure the similarities of subnetworks or capture local, indirect neighbourhood relationships. Here we propose a graph-based machine learning method to quantify the spatial homogeneity of subnetworks. We apply the method to 11,790 urban road networks across 30 cities worldwide to measure the spatial homogeneity of road networks within each city and across different cities. We find that intracity spatial homogeneity is highly associated with socioeconomic status indicators such as gross domestic product and population growth. Moreover, intercity spatial homogeneity values obtained by transferring the model across different cities reveal the intercity similarity of urban network structures originating in Europe, passed on to cities in the United States and Asia. The socioeconomic development and intercity similarity revealed using our method can be leveraged to understand and transfer insights between cities. It also enables us to address urban policy challenges including network planning in rapidly urbanizing areas and regional inequality. The spatial homogeneity of urban road networks can be quantified in a fine-grained manner with graph neural networks. This method is studied across 11,790 inner-city road networks around the world and can be used to study socioeconomic development and help with urban planning.

Edgar Wind and Modern Art: In Defence of Marginal Anarchy

Edgar Wind and Modern Art: In Defence of Marginal Anarchy

Membrane ratcheting directs progressive cell shape changes in a pulsatile system through PIP3 lipid cues

In epithelial sheets, processes that drive cells to change topological relationships can be harnessed by developmental mechanisms to effect changes in tissue architecture. Organisms ranging from humans to Drosophila lengthen their anterior-posterior axis during development. An essential driver of tissue elongation is oriented cell intercalation. In the Drosophila embryonic epithelium, individual cells are able to either consolidate cell-cell contacts or direct neighbor exchange movements through the asymmetric localization of cell adhesion and polarity proteins.

Protein complexes detection based on node local properties and gene expression in PPI weighted networks

BackgroundIdentifying protein complexes from protein–protein interaction (PPI) networks is a crucial task, and many related algorithms have been developed. Most algorithms usually employ direct neighbors of nodes and ignore resource allocation and second-order neighbors. The effective use of such information is crucial to protein complex detection.ResultBased on this observation, we propose a new way by combining node resource allocation and gene expression information to weight protein network (NRAGE-WPN), in which protein complexes are detected based on core-attachment and second-order neighbors.ConclusionsThrough comparison with eleven methods in Yeast and Human PPI network, the experimental results demonstrate that this algorithm not only performs better than other methods on 75% in terms of f-measure+, but also can achieve an ideal overall performance in terms of a composite score consisting of five performance measures. This identification method is simple and can accurately identify more complexes.