Use Of Global Information Research Articles

Graph convolutional network with position and global information improves relation extraction

With the continuous improvement of the related relation extraction model, researchers focused on optimizations of the input of the sentence expression structures, such as dependency trees, and slight improvements and integrations of basic models applied to this task. This paper utilizes position-aware attention mechanisms to highlight critical information and makes good use of global information generated by the bidirectional LSTM, absorbing characteristics and advantages of those related models to propose a new Position-Aware Graph Convolutional Network (PA-GCN) model and describe it in three steps. Moreover, this paper trials the model on the RACRED dataset to evaluate its performance and suitability. The experiment results demonstrate that the PA-GCN model outperformed others listed in this paper, achieving an F_1 score of 66.6%, which verifies an improvement of the model and the effectiveness of adding an attention-aware mechanism.

Towards Zero-Shot Learning: A Brief Review and an Attention-Based Embedding Network

Zero-shot learning (ZSL), an emerging topic in recent years, targets at distinguishing unseen class images by taking images from seen classes for training the classifier. Existing works often build embeddings between global feature space and attribute space, which, however, neglect the treasure in image parts. Discrimination information is usually contained in the image parts, e.g., black and white striped area of a zebra is the key difference from a horse. As such, image parts can facilitate the transfer of knowledge among the seen and unseen categories. In this paper, we first conduct a brief review on ZSL with detailed descriptions of these methods. Next, to discover meaningful parts, we propose an end-to-end attention-based embedding network for ZSL, which contains two sub-streams: the attention part embedding (APE) stream, and the attention second-order embedding (ASE) stream. APE is used to discover multiple image parts based on attention. ASE is introduced for ensuring knowledge transfer stably by second-order collaboration. Furthermore, an adaptive thresholding strategy is proposed to suppress noise and redundant parts. Finally, a global branch is incorporated for the full use of global information. Experiments on four benchmarks demonstrate that our models achieve superior results under both ZSL and GZSL settings.

Reinforcement Learning From Hierarchical Critics.

In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the framework of actor-critic RL, we introduce multiple cooperative critics from two levels of a hierarchy and propose an RL from the hierarchical critics (RLHC) algorithm. In our approach, each agent receives value information from local and global critics regarding a competition task and accesses multiple cooperative critics in a top-down hierarchy. Thus, each agent not only receives low-level details, but also considers coordination from higher levels, thereby obtaining global information to improve the training performance. Then, we test the proposed RLHC algorithm against a benchmark algorithm, that is, proximal policy optimization (PPO), under four experimental scenarios consisting of tennis, soccer, banana collection, and crawler competitions within the Unity environment. The results show that RLHC outperforms the benchmark on these four competitive tasks.

Temporal knowledge graph embedding via sparse transfer matrix

Knowledge Graph Completion (KGC) is a fundamental problem for temporal knowledge graphs (TKGs), and TKGs embedding methods are one of the essential methods for KGC. However, existing TKG embedding methods encounter a scalability dilemma, i.e., the inconsistency in parameter scalability among different datasets, and the less use of global information, e.g., statistics and dependencies of facts. To mitigate these two issues, we propose a novel and effective TKG embedding method, named Temporal Knowledge Graph Embedding via Sparse Transfer Matrix (TASTER), which provides a framework to utilize both global and local information. Regarding a TKG as a static knowledge graph when ignoring the time dimension, TASTER first learns global embeddings based on this static knowledge graph to capture global information. To capture the local information in a specific timestamp, TASTER evolves local embeddings from global embeddings based on the corresponding subgraph. Besides, TASTER learns evolving entity embeddings through sparse transformation matrices, which could better adapt to TKGs with a varied number of subgraphs. We conduct experiments on three real-world datasets, and TASTER outperforms most existing models on the link prediction task of TKGs, which validates the its effectiveness.

HA-Unet: A Modified Unet Based on Hybrid Attention for Urban Water Extraction in SAR Images

Urban water plays a significant role in the urban ecosystem, but urban water extraction is still a challenging task in automatic interpretation of synthetic aperture radar (SAR) images. The influence of radar shadows and strong scatters in urban areas may lead to misclassification in urban water extraction. Nevertheless, the local features captured by convolutional layers in Convolutional Neural Networks (CNNs) are generally redundant and cannot make effective use of global information to guide the prediction of water pixels. To effectively emphasize the identifiable water characteristics and fully exploit the global information of SAR images, a modified Unet based on hybrid attention mechanism is proposed to improve the performance of urban water extraction in this paper. Considering the feature extraction ability and the global modeling capability in SAR image segmentation, the Channel and Spatial Attention Module (CSAM) and the Multi-head Self-Attention Block (MSAB) are both introduced into the proposed Hybrid Attention Unet (HA-Unet). In this work, Resnet50 is adopted as the backbone of HA-Unet to extract multi-level features of SAR images. During the feature extraction process, CSAM based on local attention is adopted to enhance the meaningful water features and ignore unnecessary features adaptively in feature maps of two shallow layers. In the last two layers of the backbone, MSAB is introduced to capture the global information of SAR images to generate global attention. In addition, two global attention maps generated by MSAB are aggregated together to reconstruct the spatial feature relationship of SAR images from high-resolution feature maps. The experimental results on Sentinel-1A SAR images show that the proposed urban water extraction method has a strong ability to extract water bodies in the complex urban areas. The ablation experiment and visualization results vividly indicate that both CSAM and MSAB contribute significantly to extracting urban water accurately and effectively.

Discovery of pan-cancer related genes via integrative network analysis.

Identification of cancer-related genes is helpful for understanding the pathogenesis of cancer, developing targeted drugs and creating new diagnostic and therapeutic methods. Considering the complexity of the biological laboratory methods, many network-based methods have been proposed to identify cancer-related genes at the global perspective with the increasing availability of high-throughput data. Some studies have focused on the tissue-specific cancer networks. However, cancers from different tissues may share common features, and those methods may ignore the differences and similarities across cancers during the establishment of modeling. In this work, in order to make full use of global information of the network, we first establish the pan-cancer network via differential network algorithm, which not only contains heterogeneous data across multiple cancer types but also contains heterogeneous data between tumor samples and normal samples. Second, the node representation vectors are learned by network embedding. In contrast to ranking analysis-based methods, with the help of integrative network analysis, we transform the cancer-related gene identification problem into a binary classification problem. The final results are obtained via ensemble classification. We further applied these methods to the most commonly used gene expression data involving six tissue-specific cancer types. As a result, an integrative pan-cancer network and several biologically meaningful results were obtained. As examples, nine genes were ultimately identified as potential pan-cancer-related genes. Most of these genes have been reported in published studies, thus showing our method's potential for application in identifying driver gene candidates for further biological experimental verification.

ЛАТЫН ӘЛІПБИІНЕ КӨШУДЕ ЦИФРЛЫҚ ТЕХНОЛОГИЯЛАРДЫ ҚОЛДАНУ - ЗАМАН ТАЛАБЫ

Abstract. Currently learning the Latin alphabet is a requirement of the time. To date, only twelve countries of the world use Cyrillic. Most other States use the Latin alphabet. As we all know, today eighty percent of the peoples of the world use Latin fonts. Seventy percent of scientific information is in Latin. China and Japan, with the world's leading economies using their hieroglyphs, have also begun to adapt to Latin letters. The Latin alphabet has two thousand five hundred years of history. The order of the new Kazakh alphabet is developed in accordance with the order of the English alphabet today. In the conditions of globalization, the Republic of Kazakhstan needs to study the Latin alphabet, take steps to writing, reading, so as not to stay away from the developed countries of the world and perfectly understand the language of technology, education and science. We can understand the language of the world by studying the Latin alphabet. The transition to the Latin alphabet is the way to integration with the Turkic and global world, the revival of national consciousness, the entry of the Kazakh language to the international level. He makes a great contribution to the promotion of the Kazakh people, to its growth in accordance with the requirements of the new time, to its comprehensive development in the future. Modernization of the Kazakh language at a new qualitative stage of the country's development fully meets the global demands for the use of global information and communication tools in language policy. More than seventy percent of the current information in the world is transmitted in Latin graphics, and the global IT sphere creates key tools for technical solutions and programming in Latin format. This article shows ways to prepare people for changes through a mobile application (telegram bot). Solutions to a number of problems in the process of switching to the Latin alphabet are also proposed. Keywords: Latin alphabet, mobile application, programming, Telegram application, bot, server, digital technologies.

TMRN-GLU: A Transformer-Based Automatic Classification Recognition Network Improved by Gate Linear Unit

Automaticmodulation recognition (AMR) has been a long-standing hot topic among scholars, and it has obvious performance advantages over traditional algorithms. However, CNN and RNN, which are commonly used in serial classification tasks, suffer from the problems of not being able to make good use of global information and slow running speed due to serial operations, respectively. In this paper, to solve the above problems, a Transformer-based automatic classification recognition network improved by Gate Linear Unit (TMRN-GLU) is proposed, which combines the advantages of CNN with a high efficiency of parallel operations and RNN with a sufficient extraction of global information of the temporal signal context. Relevant experiments on the RML2016.10b public dataset show that the proposed algorithm not only has a significant advantage in the number of parameters compared with the existing algorithms, but also has improved recognition accuracy under various signal-to-noise ratios.In particular, the accuracy of the proposed algorithm improves significantly compared with other algorithms under low signal-to-noise ratio conditions. The accuracy is improved by at least 9% at low signal-to-noise ratio (6 dB) and about 3% at high signal-to-noise ratio (>2 dB).

Distributed Cooperative Output Regulation of Linear Heterogeneous Multiagent Systems

In this paper, the output regulation problem of fully distributed linear heterogeneous multi-agent systems via event-triggered communication is investigated. A novel information acquisition scheme is proposed, which can effectively save the computing resources of the controller. The time-invariant matrix S is obtained directly through completely distributed communication. Therefore, the computational burden caused by the introduction of matrix observer is reduced. At the same time, to save communication resources, this paper adopts a communication scheme and designs a Zeno-free event-triggered mechanism for each agent. The trigger mechanism in this paper can avoid the continuous monitoring of the system state, and does not need to supplement the self-triggering algorithm. In addition, the control strategy designed in this paper is fully distributed with fixed parameters, and the use of global information can be avoided without using dynamic parameters in the controller. Finally, a numerical example is given to verify the effectiveness of the proposed method.

DPG-Net: Densely progressive-growing network for point cloud completion

This paper proposes a Densely Progressive-growing Network (DPG-Net) for 3D point cloud completion based on the Generative Adversarial Network (GAN). It aims to learn useful features from incomplete 3D objects to infer the complete geometric shape. Most methods usually acquire global features directly from the incomplete point cloud. However, the global feature often loses local information from the input point cloud. To solve this problem, we design a novel network named DPG-Net for point cloud completion by proposing a multi-resolution dense contextual feature mechanism, a progressive growth process, and combining the adversarial process. Firstly, we study a Multi-resolution Densely Contextual Encoder to infer the potential features with local information of the partial point cloud. The encoder can obtain the global information of the point cloud while fusing the local structure details. Secondly, we propose a Progressive Growth Decoder, which can make full use of global information, to gradually refine local areas and generate a complete shape. In addition, the discriminator is used to control the network for a realistic point cloud. Our model composed of the above modules can extract the features from incomplete point clouds, and then generate detailed complete point clouds. The performance (chamfer distance) of the proposed method is better than other methods on different datasets. The experiment proves the effectiveness of our method on point cloud completion.

Dual-Channel Convolution Network With Image-Based Global Learning Framework for Hyperspectral Image Classification

Recently, convolutional neural networks (CNNs) have been widely applied to hyperspectral image (HSI) classification due to their detailed representation of features. Nevertheless, the current CNN-based HSI classification methods mainly follow a patch-based learning framework. These methods are nonglobal learning methods, which not only limit the use of global information but also require a high computational cost. In this letter, an image-based global learning framework is introduced to HSI classification. Based on this framework, we propose a dual-channel convolutional network (DCCN) for HSI classification to maximize the exploitation of the global and multiscale information of HSI. The experimental results conducted on two real hyperspectral datasets indicate that our method is superior to other related methods in terms of both efficiency and accuracy for HSI classification.

Bipartite Tracking Formation Control of Nonlinear Multi-Agent Systems Using Adaptive Output–Feedback Protocols

This paper proposed distributed adaptive formation control for leader-follower bipartite time-varying formation (BTVF) of a nonlinear multi-agent system (MAS). The proposed nonlinear MAS satisfies the one-sided Lipschitz-type condition. In the topological graphs with directed spanning trees, the design of adaptive protocols does not depend on the known communication topology, which can avoid the use of global information. Given limited information, the proposed MAS can achieve desired formation tracking by utilizing an observer protocol and converting the bipartite formation control problem into a stability problem of system errors. The analysis results of the systematic errors by using Lyapunov candidate functions, indicate that the MAS can be globally stable with a certain convergence rate during operation. Finally, numerical simulations are presented to confirm the validity of the proposed approach.

Cross-Attention Fusion Based Spatial-Temporal Multi-Graph Convolutional Network for Traffic Flow Prediction.

Accurate traffic flow prediction is essential to building a smart transportation city. Existing research mainly uses a given single-graph structure as a model, only considers local and static spatial dependencies, and ignores the impact of dynamic spatio-temporal data diversity. To fully capture the characteristics of spatio-temporal data diversity, this paper proposes a cross-Attention Fusion Based Spatial-Temporal Multi-Graph Convolutional Network (CAFMGCN) model for traffic flow prediction. First, introduce GCN to model the historical traffic data’s three-time attributes (current, daily, and weekly) to extract time features. Second, consider the relationship between distance and traffic flow, constructing adjacency, connectivity, and regional similarity graphs to capture dynamic spatial topology information. To make full use of global information, a cross-attention mechanism is introduced to fuse temporal and spatial features separately to reduce prediction errors. Finally, the CAFMGCN model is evaluated, and the experimental results show that the prediction of this model is more accurate and effective than the baseline of other models.

The changing role of foreign investors in Tokyo stock price formation

Recent research suggests that foreign investors improve the informational efficiency of national stock markets. We examine how foreign investors contribute to efficiency. We model the influence of domestic and foreign investors' trades on the efficient price of Japanese stocks over 39 years. Our results show that foreign investors trade at an information advantage over domestic investors, and this advantage has increased since around 2000. We find this is due to a substantial increase in the importance of global stock price and exchange rate information in stock price formation. Our results suggest that foreign investors have made more use of global information in trading Japanese equities as the influence of international financial factors on the domestic market has increased over recent decades.

The Changing Role of Foreign Investors in Tokyo Stock Price Formation

Recent research suggests that foreign investors improve the informational efficiency of national stock markets. We examine how foreign investors contribute to efficiency. We model the influence of domestic and foreign investors’ trades on the efficient price of Japanese stocks over 39 years. Our results show that foreign investors trade at an information advantage over domestic investors, and this advantage has increased since around 2000. We find this is due to a substantial increase in the importance of global stock price and exchange rate information in stock price formation. Our results suggest that foreign investors have made more use of global information in trading Japanese equities as the influence of international financial factors on the domestic market has increased over recent decades.

Time-varying multi-objective optimisation over switching graphs via fixed-time consensus algorithms

This paper considers distributed multi-objective optimisation problems with time-varying cost functions for network-connected multi-agent systems over switching graphs. The scalarisation approach is used to convert the problem into a weighted-sum objective. Fixed-time consensus algorithms are developed for each agent to estimate the global variables and drive all local copies of the decision vector to a consensus. The algorithm with fixed gains is first proposed, where some global information is required to choose the gains. Then, an adaptive algorithm is presented to eliminate the use of global information. The convergence of those algorithms to the Pareto solutions is established via Lyapunov theory for connected graphs. In the case of disconnected graphs, the convergence to the subsets of the Pareto fronts is studied. Simulation results are provided to demonstrate the effectiveness of the proposed algorithms.

Regionally Enhanced Global (REG) 4D-Var

Abstract A regionally enhanced global (REG) data assimilation (DA) method is proposed. The technique blends high-resolution model information from a single or multiple limited-area model domains with global model and observational information to create a regionally enhanced analysis of the global atmospheric state. This single analysis provides initial conditions for both the global and limited-area model forecasts. The potential benefits of the approach for operational data assimilation are (i) reduced development cost, (ii) reduced overall computational cost, (iii) improved limited-area forecast performance from the use of global information about the atmospheric flow, and (iv) improved global forecast performance from the use of more accurate model information in the limited-area domains. The method is tested by an implementation on the U.S. Navy’s four-dimensional variational global data assimilation system and global and limited-area numerical weather prediction models. The results of the monthlong forecast experiments suggest that the REG DA approach has the potential to deliver the desired benefits.

Three‐way recommendation integrating global and local information

The matrix factorisation approach computes a low-rank approximation of the incomplete user-item rating matrix. Existing approaches suffer from under-fitting due to the use of global information for all users and items. In this study, the authors propose a three-way recommendation model that integrates global and local information. This new model has a number of main aspects. The first is rating prediction with global and local information. A clustering and two matrix factorisation algorithms are employed for this purpose. The second is the computation of recommendation thresholds based on the decision-theoretic rough set model. Misclassification and promotion costs are considered simultaneously to build the cost matrix. The last is the determination of the recommender actions based on the prediction and thresholds. Experimental results on the well-known datasets show that authors’ proposed model improves recommendation quality in terms of average cost.

Global graph diffusion for interactive object extraction

Many interactive image segmentation methods design energy functions based on the local relationship of neighboring pixels, which is insufficient at capturing the abundant information of an image, and these methods are susceptible to many problems, such as sensitivity to seeds and under-segmentation of boundaries. To solve these problems, this paper explores utilizing the global relationship for interactive image segmentation. To effectively obtain the global information of the image, we first propose a robust affinity diffusion (RAD) method to propagate the local affinity graph. Compared with the existing diffusion-based approaches, the advantage of RAD is that it can converge to an effective limit value, which makes the diffusion process more computationally efficient and easier to control. The segmentation model is then constructed based on this convergent global graph. To efficiently utilize the global information, the energy function is designed by the multiplication of the global affinity matrix and a prior probability vector. The use of global information can significantly improve the segmentation performance. Experiments on challenging data sets demonstrate that RAD can obtain better results than state-of-the-art methods.

On lookahead equilibria in congestion games

We investigate the issues of existence and efficiency of lookahead equilibria in congestion games. Lookahead equilibria, whose study has been initiated by Mirrokni et al. (2012), correspond to the natural extension of pure Nash equilibria in which the players, when making use of global information in order to predict subsequent reactions of the other ones, have computationally limited capabilities.