Haoran Xie

Least Squares Generative Adversarial Networks

Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson X2 divergence. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We evaluate LSGANs on LSUN and CIFAR-10 datasets and the experimental results show that the images generated by LSGANs are of better quality than the ones generated by regular GANs. We also conduct two comparison experiments between LSGANs and regular GANs to illustrate the stability of LSGANs.

2014 Special Issue: Community-aware user profile enrichment in folksonomy

In the era of big data, collaborative tagging (a.k.a. folksonomy) systems have proliferated as a consequence of the growth of Web 2.0 communities. Constructing user profiles from folksonomy systems is useful for many applications such as personalized search and recommender systems. The identification of latent user communities is one way to better understand and meet user needs. The behavior of users is highly influenced by the behavior of their neighbors or community members, and this can be utilized in constructing user profiles. However, conventional user profiling techniques often encounter data sparsity problems as data from a single user is insufficient to build a powerful profile. Hence, in this paper we propose a method of enriching user profiles based on latent user communities in folksonomy data. Specifically, the proposed approach contains four sub-processes: (i) tag-based user profiles are extracted from a folksonomy tripartite graph; (ii) a multi-faceted folksonomy graph is constructed by integrating tag and image affinity subgraphs with the folksonomy tripartite graph; (iii) random walk distance is used to unify various relationships and measure user similarities; (iv) a novel prototype-based clustering method based on user similarities is used to identify user communities, which are further used to enrich the extracted user profiles. To evaluate the proposed method, we conducted experiments using a public dataset, the results of which show that our approach outperforms previous ones in user profile enrichment.

Incorporating sentiment into tag-based user profiles and resource profiles for personalized search in folksonomy

We present a framework SenticRank to incorporate sentiment for personalized search.Content-based and collaborative sentiment ranking methods are proposed.We compare the proposed sentiment-based search with baselines experimentally.We study the influence of sentiment corpora by using some sentiment dictionaries.Sentiment-based information can significantly improve performance in folksonomy. In recent years, there has been a rapid growth of user-generated data in collaborative tagging (a.k.a. folksonomy-based) systems due to the prevailing of Web 2.0 communities. To effectively assist users to find their desired resources, it is critical to understand user behaviors and preferences. Tag-based profile techniques, which model users and resources by a vector of relevant tags, are widely employed in folksonomy-based systems. This is mainly because that personalized search and recommendations can be facilitated by measuring relevance between user profiles and resource profiles. However, conventional measurements neglect the sentiment aspect of user-generated tags. In fact, tags can be very emotional and subjective, as users usually express their perceptions and feelings about the resources by tags. Therefore, it is necessary to take sentiment relevance into account into measurements. In this paper, we present a novel generic framework SenticRank to incorporate various sentiment information to various sentiment-based information for personalized search by user profiles and resource profiles. In this framework, content-based sentiment ranking and collaborative sentiment ranking methods are proposed to obtain sentiment-based personalized ranking. To the best of our knowledge, this is the first work of integrating sentiment information to address the problem of the personalized tag-based search in collaborative tagging systems. Moreover, we compare the proposed sentiment-based personalized search with baselines in the experiments, the results of which have verified the effectiveness of the proposed framework. In addition, we study the influences by popular sentiment dictionaries, and SenticNet is the most prominent knowledge base to boost the performance of personalized search in folksonomy.

Community-Aware Resource Profiling for Personalized Search in Folksonomy

In recent years, there is a fast proliferation of collaborative tagging (a.k.a. folksonomy) systems in Web 2.0 communities. With the increasingly large amount of data, how to assist users in searching their interested resources by utilizing these semantic tags becomes a crucial problem. Collaborative tagging systems provide an environment for users to annotate resources, and most users give annotations according to their perspectives or feelings. However, users may have different perspectives or feelings on resources, e.g., some of them may share similar perspectives yet have a conflict with others. Thus, modeling the profile of a resource based on tags given by all users who have annotated the resource is neither suitable nor reasonable. We propose, to tackle this problem in this paper, a community-aware approach to constructing resource profiles via social filtering. In order to discover user communities, three different strategies are devised and discussed. Moreover, we present a personalized search approach by combining a switching fusion method and a revised needs-relevance function, to optimize personalized resources ranking based on user preferences and user issued query. We conduct experiments on a collected real life dataset by comparing the performance of our proposed approach and baseline methods. The experimental results verify our observations and effectiveness of proposed method.

Personalized search for social media via dominating verbal context

With the rapid development of Web 2.0 communities, there has been a tremendous increase in user-generated content. Confronting such a vast volume of resources in collaborative tagging systems, users require a novel method for fast exploring and indexing so as to find their desired data. To this end, contextual information is indispensable and critical in understanding user preferences and intentions. In sociolinguistics, context can be classified as verbal context and social context. Compared with verbal context, social context requires not only domain knowledge to build pre-defined contextual attributes but also additional user data. However, to the best of our knowledge, no research has addressed the issue of irrelevant contextual factors for the verbal context model. To bridge this gap, the dominating set obtained from verbal context is proposed in this paper. We present (i) the verbal context graph to model contents and interrelationships of verbal context in folksonomy and thus capture the user intention; (ii) a method of discovering dominating set that provides a good balance of essentiality and integrality to de-emphasize irrelevant contextual factors and to keep the major characteristics of the verbal context graph; and (iii) a revised ranking method for measuring the relevance of a resource to an issued query, a discovered context and an extracted user profile. The experimental results obtained for a public dataset illustrate that the proposed method is more effective than existing baseline approaches.

Generating Incidental Word-Learning Tasks via Topic-Based and Load-Based Profiles

Compared to intentional word learning, incidental word learning better motivates learners, integrates development of more language skills, and provides richer contexts. The effectiveness of incidental word learning tasks can also be increased by employing materials that learners are more familiar with or interested in. Here, the authors present a framework to generate incidental word learning tasks via load-based profiles measured through the involvement load hypothesis, and topic-based profiles obtained from social media. They also conduct an experiment on real participants and find that the proposed framework promotes more effective and enjoyable word learning than intentional word learning. This article is part of a special issue on social media for learning.

Empirical analysis: stock market prediction via extreme learning machine

Abstract How to predict stock price movements based on quantitative market data modeling is an attractive topic. In front of the market news and stock prices that are commonly believed as two important market data sources, how to extract and exploit the hidden information within the raw data and make both accurate and fast predictions simultaneously becomes a challenging problem. In this paper, we present the design and architecture of our trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently. Comprehensive experimental comparisons between ELM and the state-of-the-art learning algorithms, including support vector machine (SVM) and back-propagation neural network (BP-NN), have been undertaken on the intra-day tick-by-tick data of the H-share market and contemporaneous news archives. The results have shown that (1) both RBF ELM and RBF SVM achieve higher prediction accuracy and faster prediction speed than BP-NN; (2) the RBF ELM achieves similar accuracy with the RBF SVM and (3) the RBF ELM has faster prediction speed than the RBF SVM. Simulations of a preliminary trading strategy with the signals are conducted. Results show that strategy with more accurate signals will make more profits with less risk.

Social emotion classification of short text via topic-level maximum entropy model

With the rapid proliferation of Web 2.0, the identification of emotions embedded in user-contributed comments at the social web is both valuable and essential. By exploiting large volumes of sentimental text, we can extract user preferences to enhance sales, develop marketing strategies, and optimize supply chain for electronic commerce. Pieces of information in the social web are usually short, such as tweets, questions, instant messages, messages, and news headlines. Short text differs from normal text because of its sparse word co-occurrence patterns, which hampers efforts to apply social emotion classification models. Most existing methods focus on either exploiting the social emotions of individual words or the association of social emotions with latent topics learned from normal documents. In this paper, we propose a topic-level maximum entropy (TME) model for social emotion classification over short text. TME generates topic-level features by modeling latent topics, multiple emotion labels, and valence scored by numerous readers jointly. The overfitting problem in the maximum entropy principle is also alleviated by mapping the features to the concept space. An experiment on real-world short documents validates the effectiveness of TME on social emotion classification over sparse words.

The Load-Based Learner Profile for Incidental Word Learning Task Generation

In recent years, the popularity and prosperity of mobile technologies and e-learning applications offer brand-new learning ways for people. English, as the most widely used language and the essential communication skill for people in the ‘earth village’ nowadays, has been widely learned by speakers of other languages. The importance of word knowledge in learning a second language is broadly acknowledged in the second language research literature. However, comparing with incidental word learning, the intentional learning method has the shortages of motivating reduction, simple acquisition and contextual deficiency. To address these problems, in this paper, we therefore proposed an incidental word learning model for e-learning. In particular, we measure the load of various incidental word learning tasks from the perspective of involvement load hypothesis so as to construct load-based learner profiles. To increase the effectiveness of various word learning activities and motivate learners better, a task generation method is developed based on the load-based learner profile. Moreover, we conduct experiments on real participants, and empirical results of which have further verified the effectiveness of the task generation method and the enjoyment of word learning.

A Hybrid Semantic Item Model for Recipe Search by Example

As a necessary part of our daily life, choose what dishes to cook that is a problem and troubles many people every day. In recent years, there has been a proliferation of multimedia recipe data on the Web 2.0 communities. To assist people to navigate and search on from large amounts of recipes, a suitable recipe model is crucial and indispensable. However, recipes have some distinct characteristics that conventional data models are inadequate to represent them for such data. For example, it is unreasonable and insufficient to measure how similar the cooking procedures of two dishes are only through text descriptions and/or their extracted terms. The main reason is that this raw data (or low-level features extracted from the raw data, e.g. term for text, color for image) do not map to the high-level semantics readily. In this paper, we argue that a recipe model should be semantic-based and behavior-oriented, preferably with domain knowledge support. A hybrid semantic item (HSI) model is next presented for addressing this problem. Based on HSI model, we devise a corresponding approach for recipe search by example. The experiment on our multimedia recipe retrieval system demonstrates that our HSI approach outperforms baseline methods.