No abstract

No abstract

For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to Subdomain Adaptation which focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods which contain several loss functions and converge slowly. Based on this, we present Deep Subdomain Adaptation Network (DSAN) which learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at: https://github.com/easezyc/deep-transfer-learning

To solve the information explosion problem and enhance user experience in various online applications, recommender systems have been developed to model users' preferences. Although numerous efforts have been made toward more personalized recommendations, recommender systems still suffer from several challenges, such as data sparsity and cold-start problems. In recent years, generating recommendations with the knowledge graph as side information has attracted considerable interest. Such an approach can not only alleviate the above mentioned issues for a more accurate recommendation, but also provide explanations for recommended items. In this paper, we conduct a systematical survey of knowledge graph-based recommender systems. We collect recently published papers in this field, and group them into three categories, i.e., embedding-based methods, connection-based methods, and propagation-based methods. Also, we further subdivide each category according to the characteristics of these approaches. Moreover, we investigate the proposed algorithms by focusing on how the papers utilize the knowledge graph for accurate and explainable recommendation. Finally, we propose several potential research directions in this field.

In mid-December 2019, a novel atypical pneumonia broke out in Wuhan, Hubei Province, China and was caused by a newly identified coronavirus, initially termed 2019 Novel Coronavirus and subsequently severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). As of 19 May 2020, a total of 4,731,458 individuals were reported as infected with SARS-CoV-2 among 213 countries, areas or territories with recorded cases, and the overall case-fatality rate was 6.6% (316,169 deaths among 4,731,458 recorded cases), according to the World Health Organization. Studies have shown that SARS-CoV-2 is notably similar to (severe acute respiratory syndrome coronavirus) SARS-CoV that emerged in 2002–2003 and Middle East respiratory syndrome coronavirus (MERS-CoV) that spread during 2012, and these viruses all contributed to global pandemics. The ability of SARS-CoV-2 to rapidly spread a pneumonia-like disease from Hubei Province, China, throughout the world has provoked widespread concern. The main symptoms of coronavirus disease 2019 (COVID-19) include fever, cough, myalgia, fatigue and lower respiratory signs. At present, nucleic acid tests are widely recommended as the optimal method for detecting SARS-CoV-2. However, obstacles remain, including the global shortage of testing kits and the presentation of false negatives. Experts suggest that almost everyone in China is susceptible to SARS-CoV-2 infection, and to date, there are no effective treatments. In light of the references published, this review demonstrates the biological features, spread, diagnosis and treatment of SARS-CoV-2 as a whole and aims to analyse the similarities and differences among SARS-CoV-2, SARS-CoV and MERS-CoV to provide new ideas and suggestions for prevention, diagnosis and clinical treatment.

Cross-domain text categorization targets on adapting the knowledge learnt from a labeled source domain to an unlabeled target domain, where the documents from the source and target domains are drawn from different distributions. However, in spite of the different distributions in raw-word features, the associations between word clusters (conceptual features) and document classes may remain stable across different domains. In this paper, we exploit these unchanged associations as the bridge of knowledge transformation from the source domain to the target domain by the non-negative matrix tri-factorization. Specifically, we formulate a joint optimization framework of the two matrix tri-factorizations for the source-and target-domain data, respectively, in which the associations between word clusters and document classes are shared between them. Then, we give an iterative algorithm for this optimization and theoretically show its convergence. The comprehensive experiments show the effectiveness of this method. In particular, we show that the proposed method can deal with some difficult scenarios where baseline methods usually do not perform well. 

Helicobacter pylori is one of the most common chronic infections in humans, in whom it is a key etiological factor in peptic ulcer disease, gastric mucosa-associated lymphoid tissue lymphoma, and gastric adenocarcinoma.

In this paper, we show that the edge set of a cubic graph can always be partitioned into 10 subsets, each of which induces a matching in the graph. This result is a special case of a general conjecture made by Erdos and NeSetiil: For each d 2 3, the edge set of a graph of maximum degree d can always be partitioned into [5d2/4] subsets each of which induces a matching. 0 1993 John Wiley & Sons, Inc. INTRODUCTIONThroughout this paper, we consider colorings of the edges of a graph with positive integers. Formally, a t-coloring of a graph G = ( V , E ) is a map $: -{1,2,. . . , t}. A t-coloring is proper if $(e) = $(f) and e # f imply that the edges e and f have no common endpoints. Of course, the chromatic index of a graph G is the least t for which G has a proper tcoloring. Note that whenever qj is a proper t-coloring of a graph G = ( V , E ) and a E {1,2,. . . , t}, then the edges in 34 = {e E E:$(e) = a } form a matching in G.An induced matching 34 in a graph G = ( V , E ) is a matching such that no two edges of 34 are joined by an edge of G. In other words, an induced matching is an induced subgraph in which every vertex has degree one. A