• Publications
  • Influence
Least Squares Generative Adversarial Networks
TLDR
This paper proposes the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator, and shows that minimizing the objective function of LSGAN yields minimizing the Pearson X2 divergence. Expand
Multi-class Generative Adversarial Networks with the L2 Loss Function
TLDR
This work proposes the multi-class generative adversarial networks for the purpose of image generation with multiple classes, and demonstrates that theMulti-class GANs can generate elegant images on datasets with a large number of classes. Expand
News impact on stock price return via sentiment analysis
TLDR
Results show that at individual stock, sector and index levels, the models with sentiment analysis outperform the bag-of-words model in both validation set and independent testing set, and the models which use sentiment polarity cannot provide useful predictions. Expand
On the Effectiveness of Least Squares Generative Adversarial Networks
TLDR
The Least Squares Generative Adversarial Networks (LSGANs) are proposed which adopt the least squares loss for both the discriminator and the generator, and LSGANs are able to generate higher quality images than regular GANs. Expand
A novel binary artificial bee colony algorithm for the set-union knapsack problem
TLDR
The results verify that the proposed approach is significantly superior to the baseline evolutionary algorithms for solving SUKP such as A-SUKP, ABC bin and binDE in terms of both time complexity and solution performance. Expand
A Big Data Framework for Early Identification of Dropout Students in MOOC
TLDR
This paper proposed a framework that applies big data methods to identify the students who are likely to dropout in MOOC in early stage and demonstrated that the framework is effective and helpful. Expand
Cross-Domain Sentiment Classification via Topic-Related TrAdaBoost
TLDR
A boosting-based learning framework named TR-TrAdaBoost for cross-domain sentiment classification is proposed, which firstly explores the topic distribution of documents, and then combines it with the unigram TrAdABoost. Expand
Detail-recovery Image Deraining via Context Aggregation Networks
TLDR
This paper introduces two parallel sub-networks with a comprehensive loss function which synergize to derain and recover the lost details caused by deraining, and proposes an end-to-end detail-recovery image deraining network (termed a DRDNet) to solve the problem. Expand
Incorporating sentiment into tag-based user profiles and resource profiles for personalized search in folksonomy
TLDR
This is the first work of integrating sentiment information to address the problem of the personalized tag-based search in collaborative tagging systems and a novel generic framework SenticRank is presented to incorporate various sentiment Information to various sentiment-based information for personalized search by user profiles and resource profiles. Expand
Empirical analysis: stock market prediction via extreme learning machine
TLDR
The design and architecture of the trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently are presented and results show that strategy with more accurate signals will make more profits with less risk. Expand
...
1
2
3
4
5
...