No abstract

Session-based recommendation, which aims to predict the user's immediate next action based on anonymous sessions, is a key task in many online services (e.g., e-commerce, media streaming).  Recently, Self-Attention Network (SAN) has achieved significant success in various sequence modeling tasks without using either recurrent or convolutional network. However, SAN lacks local dependencies that exist over adjacent items and limits its capacity for learning contextualized representations of items in sequences.  In this paper, we propose a graph contextualized self-attention model (GC-SAN), which utilizes both graph neural network and self-attention mechanism, for session-based recommendation. In GC-SAN, we dynamically construct a graph structure for session sequences and capture rich local dependencies via graph neural network (GNN).  Then each session learns long-range dependencies by applying the self-attention mechanism. Finally, each session is represented as a linear combination of the global preference and the current interest of that session. Extensive experiments on two real-world datasets show that GC-SAN outperforms state-of-the-art methods consistently.

Permanent and peripheral embolization is a requirement of embolic materials in the transcatheter arterial embolization of liver tumors. So far, it has been difficult to find materials that have both good flowability and high mechanical strength. In the present work, a temperature‐sensitive p(N ‐isopropylacrylamide‐co‐butyl methylacrylate) (PIB) nanogel is explored as a novel blood‐vessel‐embolic material in the interventional therapy of liver tumors. With increasing temperature, the PIB nanogel dispersion sequentially exhibits three phase states; swollen gel, flowable sol, and finally shrunken gel. Iohexol, a nonionic X‐ray contrast agent, increases the volume‐phase transition temperature of the PIB nanogel and decreases the critical gelation concentration. Angiographical and histological studies on the embolization in the liver arteries of VX2 tumor‐bearing rabbits indicate that the PIB nanogel dispersion mixed with iohexol (designated as PIB‐I‐6150) completely occludes all levels of blood vessels, including peripheral vessels. In addition, data on tumor volume, necrosis level, and the number of metastatic foci indicate that PIB‐I‐6150 has better peripheral embolization than Lipiodol. Experiments concerning cytotoxicity, hemolysis, histology, and liver function indicate that PIB‐I‐6150 has good biocompability.

Severe acute respiratory syndrome–associatedcoronavirus (SARS-CoV) was isolated from a pig during a survey for possible routes of viral transmission after a SARS epidemic. Sequence and epidemiology analyses suggested that the pig was infected by a SARS-CoV of human origin.