Ridge-Regression-Induced Robust Graph Relational Network.

Graph convolutional networks (GCNs) have attracted increasing research attention, which merits in its strong ability to handle graph data, such as the citation network or social network. Existing models typically use first-order neighborhood information to design specific convolution operations, which aggregate the features of all adjacent nodes. However, such models ignore the high-order spatial relationship among neighboring nodes in noisy data due to its modeling complexity. In this article, we propose a novel robust graph relational network to address this issue toward modeling high-order relationships in noisy data for graph convolution. Our key innovation lies in designing a generic relation network layer, which is used to infer the underlying relations among adjacent noisy nodes. Specifically, a fixed number of adjacent nodes for each node is chosen by solving the ridge regression problem, in which the regression coefficients are used to rank the adjacent nodes of each node in a graph. Furthermore, to mine the rich features, we extract high-order information from the nodes to significantly enhance the representation ability of the GCNs for extensive applications. We conduct extensive semisupervised node classification experiments on the noisy benchmark datasets, which clearly show that our model is superior to the existing methods and can achieve state-of-the-art performance.

WalkGAN: Network Representation Learning With Sequence-Based Generative Adversarial Networks.

Network representation learning, also known as network embedding, aims to learn the low-dimensional representations of vertices while capturing and preserving the network structure. For real-world networks, the edges that represent some important relationships between the vertices of a network may be missed and may result in degenerated performance. The existing methods usually treat missing edges as negative samples, thereby ignoring the true connections between two vertices in a network. To capture the true network structure effectively, we propose a novel network representation learning method called WalkGAN, where random walk scheme and generative adversarial networks (GAN) are incorporated into a network embedding framework. Specifically, WalkGAN leverages GAN to generate the synthetic sequences of the vertices that sufficiently simulate random walk on a network and further learn vertex representations from these vertex sequences. Thus, the unobserved links between the vertices are inferred with high probability instead of treating them as nonexistence. Experimental results on the benchmark network datasets demonstrate that WalkGAN achieves significant performance improvements for vertex classification, link prediction, and visualization tasks.

Containing the Transmission of COVID-19: A Modeling Study in 160 Countries.

Background: It is much valuable to evaluate the comparative effectiveness of the coronavirus disease 2019 (COVID-19) prevention and control in the non-pharmacological intervention phase of the pandemic across countries and identify useful experiences that could be generalized worldwide. Methods: In this study, we developed a susceptible-exposure-infectious-asymptomatic-removed (SEIAR) model to fit the daily reported COVID-19 cases in 160 countries. The time-varying reproduction number (R t ) that was estimated through fitting the mathematical model was adopted to quantify the transmissibility. We defined a synthetic index (I AC ) based on the value of R t to reflect the national capability to control COVID-19. Results: The goodness-of-fit tests showed that the SEIAR model fitted the data of the 160 countries well. At the beginning of the epidemic, the values of R t of countries in the European region were generally higher than those in other regions. Among the 160 countries included in the study, all European countries had the ability to control the COVID-19 epidemic. The Western Pacific Region did best in continuous control of the epidemic, with a total of 73.76% of countries that can continuously control the COVID-19 epidemic, while only 43.63% of the countries in the European Region continuously controlled the epidemic, followed by the Region of Americas with 52.53% of countries, the Southeast Asian Region with 48% of countries, the African Region with 46.81% of countries, and the Eastern Mediterranean Region with 40.48% of countries. Conclusion: Large variations in controlling the COVID-19 epidemic existed across countries. The world could benefit from the experience of some countries that demonstrated the highest containment capabilities.

Correntropy-Induced Robust Low-Rank Hypergraph.

Hypergraph learning has been widely exploited in various image processing applications, due to its advantages in modeling the high-order information. Its efficacy highly depends on building an informative hypergraph structure to accurately and robustly formulate the underlying data correlation. However, the existing hypergraph learning methods are sensitive to non- Gaussian noise, which hurts the corresponding performance. In this paper, we present a noise-resistant hypergraph learning model, which provides superior robustness against various non- Gaussian noises. In particular, our model adopts low-rank representation to construct a hypergraph, which captures the globally linear data structure as well as preserving the grouping effect of highly-correlated data. We further introduce a correntropyinduced local metric to measure the reconstruction errors, which is particularly robust to non-Gaussian noises. Finally, the Frobenious-norm based regularization is proposed to combine with the low-rank regularizer, which enables our model to regularize the singular values of the coefficient matrix. By such, the non-zero coefficients are selected to generate a hyperedge set as well as the hyperedge weights. We have evaluated the proposed hypergraph model in the tasks of image clustering and semi-supervised image classification. Quantitatively, our scheme significantly enhances the performance of the state-of-the-art hypergraph models on several benchmark datasets.

A Novel Method of Automatic Plant Species Identification Using Sparse Representation of Leaf Tooth Features.

Automatic species identification has many advantages over traditional species identification. Currently, most plant automatic identification methods focus on the features of leaf shape, venation and texture, which are promising for the identification of some plant species. However, leaf tooth, a feature commonly used in traditional species identification, is ignored. In this paper, a novel automatic species identification method using sparse representation of leaf tooth features is proposed. In this method, image corners are detected first, and the abnormal image corner is removed by the PauTa criteria. Next, the top and bottom leaf tooth edges are discriminated to effectively correspond to the extracted image corners; then, four leaf tooth features (Leaf-num, Leaf-rate, Leaf-sharpness and Leaf-obliqueness) are extracted and concatenated into a feature vector. Finally, a sparse representation-based classifier is used to identify a plant species sample. Tests on a real-world leaf image dataset show that our proposed method is feasible for species identification.