Search

Knowledge graphs (KGs) play a vital role in natural language processing (NLP), which can serve several downstream tasks. Because different views of KGs are usually constructed independently, the multi-view knowledge graph fusion (MVKGF) becomes a hotspot. Although multi-view learning studied very well in past decades, MVKGF is still not well tackled because of the heterogeneous relations and the multi-view KGs. To overcome MVKGF, entity alignment is the most studied. Existing entity alignment methods are dominated by embedding based methods, such as TransE and Graph Neural Networks (GNNs), where the alignment is achieved by measuring the similarities between entity embeddings. However, most previous approaches suffer from the issues of the diverse knowledge facts and the complex neighboring structures. In this paper, we propose a novel K nowledge-aware A ttentional G raph N eural N etwork (KAGNN) model to carefully incorporate both knowledge facts and neighboring structures. In particular, a knowledge-aware attention mechanism is designed to preserve the original semantics and determine the importance of each knowledge fact. Furthermore, a three-layered GCN with highway gates is adopted to learn better entity representations from the neighboring structure information. Thus, our model can be regarded as a multi-view extension of GNN. We validate our model on three cross-lingual datasets and the results show our model beats the state-of-the-art baselines by a large margin. [ABSTRACT FROM AUTHOR]

Introduction: Emerging evidence showed that adipocytes are important regulators in controlling insulin resistance in type 2 diabetes mellitus (T2DM). So far, compounds isolated from natural plants have been widely studied for their roles in alleviating T2DM-associated complications. This work evaluated the actions of astragaloside IV (AS-IV) on insulin resistance and inflammatory biomarker expression in adipocytes and explored the potential mechanisms. Methods: Glucose consumption of the adipocytes was determined by a glucose assay kit; the mRNA expression levels of glucose transporter type 4 (GLUT-4), interleukin-6 (IL-6), TNF-α and C1q tumor necrosis factor-related protein 3 (CTRP3) were measured by quantitative real-time PCR (qRT-PCR); the protein levels were determined by western blot assay and enzyme-linked immunosorbent assay. Results: AS-IV concentration-dependently increased glucose consumption in the insulin resistance adipocytes. Further qRT-PCR results showed that AS-IV concentration-dependently reduced adipocyte IL-6 and TNF-α expression. Moreover, GLUT-4 expression in adipocytes was also significantly upregulated by AS-IV. Furthermore, we found that AS-IV concentration-dependently increased CTRP3 expression in adipocytes. CTRP3 silence decreased glucose consumption, upregulated IL-6 and TNF-α expression and downregulated GLUT-4 mRNA expression in 200 µM AS-IV-treated adipocytes. Moreover, AS-IV treatment enhanced the activity of phosphoinositide 3-kinase (PI3K)/AKT signaling in adipocytes, which was markedly attenuated by CTRP3 silencing. Importantly, inhibition of PI3K/AKT signaling also attenuated AS-IV induced an increase in glucose consumption and GLUT-4 expression and a decrease in IL-6 and TNF-α expression of adipocytes. Conclusions: Collectively, our data indicated that AS-IV attenuated insulin resistance and inflammation in adipocytes via targeting CTRP3/PI3K/Akt signaling. [ABSTRACT FROM AUTHOR]

Typhoons are one of the most destructive types of disasters. Several statistical models have been designed to predict their paths to reduce damage, casualties, and economic loss. To further increase prediction accuracy, two key challenges are (1) to extract better nonlinear 3D features of typhoons, which is hard due to their complex high-dimensional properties, and (2) to combine suitable 2D and 3D features in a proper way to improve predictions. To address these challenges, this paper presents a novel spatio-temporal deep learning model named Attention-based Multi ConvGRU (AM-ConvGRU). To automatically select high response isobaric planes of typhoons when considering their whole 3D structures, AM-ConvGRU leverages the Residual Channel Attention Block (RCAB). Furthermore, it integrates a novel model named Multi-ConvGRU to extract large-scale nonlinear spatial features of typhoons. Moreover, the approach relies on a Wide & Deep framework to fuse the traditional Generalized Linear Model (GLM) with the proposed AM-ConvGRU model. To evaluate the designed approach, extensive experiments have been conducted using real-world typhoons data from the Western North Pacific (WNP) basin obtained from both the China Meteorological Administration (CMA) dataset and the EAR-Interim dataset maintained by the European Centre for Medium-Range Weather Forecasts (ECMWF). Results show that the proposed method outperforms state-of-the-art deep learning typhoon prediction methods. The source code is available on GitHub with the following link:https://github.com/xuguangning1218/Typhoon_Path. [ABSTRACT FROM AUTHOR]

The original article can be found online at https://doi.org/10.1007/s00521-021-06724-x. B Correction to: Neural Computing and Applications (2022) 34:5905-5921 b https://doi.org/10.1007/s00521-021-06724-x The Eq. (10) in the article is corrected as below: 10 HT ht Graph Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. [Extracted from the article]