HTC

About: HTC is a company organization based out in Banqiao District, Taiwan. It is known for research contribution in the topics: Mobile device & Signal. The organization has 3371 authors who have published 2739 publications receiving 29574 citations. The organization is also known as: HTC & High Tech Computer Corporation.

Network representation learning with rich text information

Abstract: Representation learning has shown its effectiveness in many tasks such as image classification and text mining. Network representation learning aims at learning distributed vector representation for each vertex in a network, which is also increasingly recognized as an important aspect for network analysis. Most network representation learning methods investigate network structures for learning. In reality, network vertices contain rich information (such as text), which cannot be well applied with algorithmic frameworks of typical representation learning methods. By proving that DeepWalk, a state-of-the-art network representation method, is actually equivalent to matrix factorization (MF), we propose text-associated DeepWalk (TADW). TADW incorporates text features of vertices into network representation learning under the framework of matrix factorization. We evaluate our method and various baseline methods by applying them to the task of multi-class classification of vertices. The experimental results show that, our method outperforms other baselines on all three datasets, especially when networks are noisy and training ratio is small. The source code of this paper can be obtained from https://github.com/albertyang33/TADW.

Genetic Ancestry and Natural Selection Drive Population Differences in Immune Responses to Pathogens

Abstract: Individuals from different populations vary considerably in their susceptibility to immune-related diseases. To understand how genetic variation and natural selection contribute to these differences, we tested for the effects of African versus European ancestry on the transcriptional response of primary macrophages to live bacterial pathogens. A total of 9.3% of macrophage-expressed genes show ancestry-associated differences in the gene regulatory response to infection, and African ancestry specifically predicts a stronger inflammatory response and reduced intracellular bacterial growth. A large proportion of these differences are under genetic control: for 804 genes, more than 75% of ancestry effects on the immune response can be explained by a single cis- or trans-acting expression quantitative trait locus (eQTL). Finally, we show that genetic effects on the immune response are strongly enriched for recent, population-specific signatures of adaptation. Together, our results demonstrate how historical selective events continue to shape human phenotypic diversity today, including for traits that are key to controlling infection.

Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks

Abstract: With the revival of neural networks, many studies try to adapt powerful sequential neural models, ie Recurrent Neural Networks (RNN), to sequential recommendation. RNN-based networks encode historical interaction records into a hidden state vector. Although the state vector is able to encode sequential dependency, it still has limited representation power in capturing complicated user preference. It is difficult to capture fine-grained user preference from the interaction sequence. Furthermore, the latent vector representation is usually hard to understand and explain. To address these issues, in this paper, we propose a novel knowledge enhanced sequential recommender. Our model integrates the RNN-based networks with Key-Value Memory Network (KV-MN). We further incorporate knowledge base (KB) information to enhance the semantic representation of KV-MN. RNN-based models are good at capturing sequential user preference, while knowledge-enhanced KV-MNs are good at capturing attribute-level user preference. By using a hybrid of RNNs and KV-MNs, it is expected to be endowed with both benefits from these two components. The sequential preference representation together with the attribute-level preference representation are combined as the final representation of user preference. With the incorporation of KB information, our model is also highly interpretable. To our knowledge, it is the first time that sequential recommender is integrated with external memories by leveraging large-scale KB information.

Mobile device interface with dual windows

Abstract: A mobile device having a user interface supporting multiple windows is disclosed. The user interface is suitable for use in any device having a handheld form factor, such as a mobile phone or mobile Internet device. The user interface includes two windows that are displayed on the mobile device's screen. The mobile device may be configured to switch between a single window mode and a dual window mode. The device may also be configured to launch applications in either mode. It may be configured to switch between modes automatically or in response to a user command. The windows may also be re-oriented in response to a change in the device's orientation or to a user's command.

Electronic device and user interface display method thereof

Abstract: An electronic device and a user interface display method thereof are provided. The method includes the following steps. First, organize a plurality of computer programs and a web browser executable on the electronic device into a virtual book. Each page of the virtual book includes a user interface of one of the computer programs or a web page displayed by the web browser. Next, display one of the pages as a current page so that the user interface or the web page of the current page is accessible to a user of the electronic device. Next, display a stand-up view of the virtual book in response to a first operating action performed by the user. The stand-up view includes a plurality of the pages adjacent to the current page and a virtual switch attached to a side of the virtual book.