Learn More
In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network. Our model consists of a top-down stack of GANs, each learned to generate lower-level representations conditioned on higher-level representations. A(More)
MicroRNAs are a group of endogenously expressed, single-stranded, 18-24 nt RNAs that regulate diverse cellular pathways. Although documented evidence indicates that some microRNAs can function as oncogenes or tumor-suppressors, the role of miR-214 in regulating human cervical cancer cells remains unexplored. We determined the expression level of miR-214 and(More)
MicroRNAs are short regulatory RNAs that negatively modulate gene expression at the post-transcriptional level, and are deeply involved in the pathogenesis of several types of cancers. To investigate whether specific miRNAs and their target genes participate in the molecular pathogenesis of laryngeal carcinoma, oligonucleotide microarrays were used to(More)
Large graphs arise in a number of contexts and understanding their structure and extracting information from them is an important research area. Early algorithms on mining communities have focused on the global structure, and often run in time functional to the size of the entire graph. Nowadays, as we often explore networks with billions of vertices and(More)
Many tasks in computer vision can be cast as a “label changing” problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership. Although successful task-specific methods have been developed for some label changing applications, to date no general purpose method exists.(More)
Recent successes in training large, deep neural networks (DNNs) have prompted active investigation into the underlying representations learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by millions of learned parameters. However, despite the difficulty, such research is(More)
Based on the definition of local spectral subspace, we propose a novel approach called LOSP for local overlapping community detection. Using the power method for a few steps, LOSP finds an approximate invariant subspace, which depicts the embedding of the local neighborhood structure around the seeds of interest. LOSP then identifies the local community(More)
How can web services that depend on user generated content discern fake social engagement activities by spammers from legitimate ones? In this paper, we focus on the social site of YouTube and the problem of identifying bad actors posting inorganic contents and inflating the count of social engagement metrics. We propose an effective method, Leas (Local(More)
Individuals’ development is a multilayered affair. The influence of family relationship on personality, such as Sulloway’s model (1996, 2001) focusing on birth order, is subject to influence from other social systems in which the families are situated. The current research examined the relation of birth order to personality and life satisfaction in China,(More)
S100P is a member of the S100 family of calcium-binding proteins. Our previous studies have demonstrated its significant downregulation in oxaliplatin-resistant colon cancer cell line. The present study investigated whether it plays a role in the regulation of chemosensitivity to anticancer drugs using human ovarian cancer cell line OVCAR3. We firstly(More)