With the rapid information explosion of news, making personalized news recommendation for users becomes an increasingly challenging problem. Many existing recommendation methods that regard the recommendation procedure as the static process, have achieved better recommendation performance. However, they usually fail with the dynamic diversity of news and user’s interests, or ignore the importance of sequential information of user’s clicking selection. In this paper, taking full advantages of convolution neural network (CNN), recurrent neural network (RNN) and attention mechanism, we propose a deep attention neural network DAN for news recommendation. Our DAN model presents to use attention-based parallel CNN for aggregating user’s interest features and attention-based RNN for capturing richer hidden sequential features of user’s clicks, and combines these features for new recommendation. We conduct experiment on real-world news data sets, and the experimental results demonstrate the superiority and effectiveness of our proposed DAN model.
Multilingual knowledge graphs constructed by entity alignment are the indispensable resources for numerous AI-related applications. Most existing entity alignment methods only use the triplet-based knowledge to find the aligned entities across multilingual knowledge graphs, they usually ignore the neighborhood subgraph knowledge of entities that implies more richer alignment information for aligning entities. In this paper, we incorporate neighborhood subgraph-level information of entities, and propose a neighborhood-aware attentional representation method NAEA for multilingual knowledge graphs. NAEA devises an attention mechanism to learn neighbor-level representation by aggregating neighbors' representations with a weighted combination. The attention mechanism enables entities not only capture different impacts of their neighbors on themselves, but also attend over their neighbors' feature representations with different importance. We evaluate our model on two real-world datasets DBP15K and DWY100K, and the experimental results show that the proposed model NAEA significantly and consistently outperforms state-of-the-art entity alignment models.
Our previous study and others have demonstrated that autophagy is activated in ischemic astrocytes and contributes to astrocytic cell death. However, the mechanisms of ischemia-induced autophagy remain largely unknown. In this study, we established a rat's model of permanent middle cerebral artery occlusion (pMCAO) and an in vitro oxygen and glucose deprivation (OGD) model. Autophagy was inhibited by either pharmacological treatment with 3-methyladenine (3-MA) and wortmannin (Wort) or genetic treatment with knockdown of Atg5 in primary cultured astrocytes and knockout of Atg5 in mouse embryonic fibroblast (MEF) cells, respectively. We found that pharmacological or genetic inhibition of autophagy reversed pMCAO or OGD-induced increase in LC3-II, active cathepsin B and L, tBid, active caspase-3 and cytoplastic cytochrome c (Cyt-c), and suppressed the injury-induced reduction in mitochondrial Cyt-c in ischemic cortex, in injured astrocytes and MEF cells. Immunofluorescence analysis showed that 3-MA or Wort treatment reversed OGD-induced release of cathepsin B and L from the lysosome to the cytoplasm and activation of caspase-3 in the astrocytes. Furthermore, treatment of 3-MA or Wort decreased OGD-induced increase in lysosomal membrane permeability and enhanced OGD-induced upregulation of lysosomal heat shock protein 70.1B (Hsp70.1B) in astrocytes. Inhibition of autophagy by 3-MA or Wort reduced infarction volume in rats and protected OGD-induced astrocytic cell injury. A non-selective caspase inhibitor z-VAD-fmk or a specific caspase-3 inhibitor Q-DEVD-OPh also rescued OGD-induced astrocytic cell injury. In conclusion, our presenting data suggest that inhibition of autophagy blocks cathepsins–tBid–mitochondrial apoptotic signaling pathway via stabilization of lysosomal membranes, possibly due to upregulation of the lysosomal Hsp70.1B in ischemic astrocytes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.