Showing papers by "Qiang Yang published in 2009"

Can movies and books collaborate?: cross-domain collaborative filtering for sparsity reduction

Abstract: The sparsity problem in collaborative filtering (CF) is a major bottleneck for most CF methods. In this paper, we consider a novel approach for alleviating the sparsity problem in CF by transferring useritem rating patterns from a dense auxiliary rating matrix in other domains (e.g., a popular movie rating website) to a sparse rating matrix in a target domain (e.g., a new book rating website). We do not require that the users and items in the two domains be identical or even overlap. Based on the limited ratings in the target matrix, we establish a bridge between the two rating matrices at a cluster-level of user-item rating patterns in order to transfer more useful knowledge from the auxiliary task domain. We first compress the ratings in the auxiliary rating matrix into an informative and yet compact cluster-level rating pattern representation referred to as a codebook. Then, we propose an efficient algorithm for reconstructing the target rating matrix by expanding the codebook. We perform extensive empirical tests to show that our method is effective in addressing the data sparsity problem by transferring the useful knowledge from the auxiliary tasks, as compared to many state-of-the-art CF methods.

Transfer learning for collaborative filtering via a rating-matrix generative model

Abstract: Cross-domain collaborative filtering solves the sparsity problem by transferring rating knowledge across multiple domains. In this paper, we propose a rating-matrix generative model (RMGM) for effective cross-domain collaborative filtering. We first show that the relatedness across multiple rating matrices can be established by finding a shared implicit cluster-level rating matrix, which is next extended to a cluster-level rating model. Consequently, a rating matrix of any related task can be viewed as drawing a set of users and items from a user-item joint mixture model as well as drawing the corresponding ratings from the cluster-level rating model. The combination of these two models gives the RMGM, which can be used to fill the missing ratings for both existing and new users. A major advantage of RMGM is that it can share the knowledge by pooling the rating data from multiple tasks even when the users and items of these tasks do not overlap. We evaluate the RMGM empirically on three real-world collaborative filtering data sets to show that RMGM can outperform the individual models trained separately.

SNPHarvester: a filtering-based approach for detecting epistatic interactions in genome-wide association studies

Abstract: Motivation: Hundreds of thousands of single nucleotide polymorphisms (SNPs) are available for genome-wide association (GWA) studies nowadays. The epistatic interactions of SNPs are believed to be very important in determining individual susceptibility to complex diseases. However, existing methods for SNP interaction discovery either suffer from high computation complexity or perform poorly when marginal effects of disease loci are weak or absent. Hence, it is desirable to develop an effective method to search epistatic interactions in genome-wide scale. Results: We propose a new method SNPHarvester to detect SNP– SNP interactions in GWA studies. SNPHarvester creates multiple paths in which the visited SNP groups tend to be statistically associated with diseases, and then harvests those significant SNP groups which pass the statistical tests. It greatly reduces the number of SNPs. Consequently, existing tools can be directly used to detect epistatic interactions. By using a wide range of simulated data and a real genome-wide data, we demonstrate that SNPHarvester outperforms its recent competitor significantly and is promising for practical disease prognosis. Availability: http://bioinformatics.ust.hk/SNPHarvester.html

Context-aware query classification

Abstract: Understanding users'search intent expressed through their search queries is crucial to Web search and online advertisement. Web query classification (QC) has been widely studied for this purpose. Most previous QC algorithms classify individual queries without considering their context information. However, as exemplified by the well-known example on query "jaguar", many Web queries are short and ambiguous, whose real meanings are uncertain without the context information. In this paper, we incorporate context information into the problem of query classification by using conditional random field (CRF) models. In our approach, we use neighboring queries and their corresponding clicked URLs (Web pages) in search sessions as the context information. We perform extensive experiments on real world search logs and validate the effectiveness and effciency of our approach. We show that we can improve the F1 score by 52% as compared to other state-of-the-art baselines.

Heterogeneous Transfer Learning for Image Clustering via the SocialWeb

Abstract: In this paper, we present a new learning scenario, heterogeneous transfer learning, which improves learning performance when the data can be in different feature spaces and where no correspondence between data instances in these spaces is provided. In the past, we have classified Chinese text documents using English training data under the heterogeneous transfer learning framework. In this paper, we present image clustering as an example to illustrate how unsupervised learning can be improved by transferring knowledge from auxiliary heterogeneous data obtained from the social Web. Image clustering is useful for image sense disambiguation in query-based image search, but its quality is often low due to imagedata sparsity problem. We extend PLSA to help transfer the knowledge from social Web data, which have mixed feature representations. Experiments on image-object clustering and scene clustering tasks show that our approach in heterogeneous transfer learning based on the auxiliary data is indeed effective and promising.

Probabilistic latent preference analysis for collaborative filtering

Abstract: A central goal of collaborative filtering (CF) is to rank items by their utilities with respect to individual users in order to make personalized recommendations. Traditionally, this is often formulated as a rating prediction problem. However, it is more desirable for CF algorithms to address the ranking problem directly without going through an extra rating prediction step. In this paper, we propose the probabilistic latent preference analysis (pLPA) model for ranking predictions by directly modeling user preferences with respect to a set of items rather than the rating scores on individual items. From a user's observed ratings, we extract his preferences in the form of pairwise comparisons of items which are modeled by a mixture distribution based on Bradley-Terry model. An EM algorithm for fitting the corresponding latent class model as well as a method for predicting the optimal ranking are described. Experimental results on real world data sets demonstrated the superiority of the proposed method over several existing CF algorithms based on rating predictions in terms of ranking performance measure NDCG.

Cross-domain activity recognition

Abstract: In activity recognition, one major challenge is huge manual effort in labeling when a new domain of activities is to be tested. In this paper, we ask an interesting question: can we transfer the available labeled data from a set of existing activities in one domain to help recognize the activities in another different but related domain? Our answer is "yes", provided that the sensor data from the two domains are related in some way. We develop a bridge between the activities in two domains by learning a similarity function via Web search, under the condition that the sensor data are from the same feature space. Based on the learned similarity measures, our algorithm interprets the data from the source domain as the data in the domain with different confidence levels, thus accomplishing the cross-domain knowledge transfer task. Our algorithm is evaluated on several real-world datasets to demonstrate its effectiveness.

EigenTransfer: a unified framework for transfer learning

Abstract: This paper proposes a general framework, called EigenTransfer, to tackle a variety of transfer learning problems, e.g. cross-domain learning, self-taught learning, etc. Our basic idea is to construct a graph to represent the target transfer learning task. By learning the spectra of a graph which represents a learning task, we obtain a set of eigenvectors that reflect the intrinsic structure of the task graph. These eigenvectors can be used as the new features which transfer the knowledge from auxiliary data to help classify target data. Given an arbitrary non-transfer learner (e.g. SVM) and a particular transfer learning task, EigenTransfer can produce a transfer learner accordingly for the target transfer learning task. We apply EigenTransfer on three different transfer learning tasks, cross-domain learning, cross-category learning and self-taught learning, to demonstrate its unifying ability, and show through experiments that EigenTransfer can greatly outperform several representative non-transfer learners.

Cross-domain activity recognition

Abstract: In activity recognition, one major challenge is huge manual effort in labeling when a new domain of activities is to be tested. In this paper, we ask an interesting question: can we transfer the available labeled data from a set of existing activities in one domain to help recognize the activities in another different but related domain? Our answer is "yes", provided that the sensor data from the two domains are related in some way. We develop a bridge between the activities in two domains by learning a similarity function via Web search, under the condition that the sensor data are from the same feature space. Based on the learned similarity measures, our algorithm interprets the data from the source domain as the data in the domain with different confidence levels, thus accomplishing the cross-domain knowledge transfer task. Our algorithm is evaluated on several real-world datasets to demonstrate its effectiveness.

Domain adaptation via transfer component analysis

Abstract: Domain adaptation solves a learning problem in a target domain by utilizing the training data in a different but related source domain. Intuitively, discovering a good feature representation across domains is crucial. In this paper, we propose to find such a representation through a new learning method, transfer component analysis (TCA), for domain adaptation. TCA tries to learn some transfer components across domains in a Reproducing Kernel Hilbert Space (RKHS) using Maximum Mean Discrepancy (MMD). In the subspace spanned by these transfer components, data distributions in different domains are close to each other. As a result, with the new representations in this subspace, we can apply standard machine learning methods to train classifiers or regression models in the source domain for use in the target domain. The main contribution of our work is that we propose a novel feature representation in which to perform domain adaptation via a new parametric kernel using feature extraction methods, which can dramatically minimize the distance between domain distributions by projecting data onto the learned transfer components. Furthermore, our approach can handle large datsets and naturally lead to out-of-sample generalization. The effectiveness and efficiency of our approach in are verified by experiments on two real-world applications: cross-domain indoor WiFi localization and cross-domain text classification.

MegaSNPHunter: a learning approach to detect disease predisposition SNPs and high level interactions in genome wide association study.

Abstract: The interactions of multiple single nucleotide polymorphisms (SNPs) are highly hypothesized to affect an individual's susceptibility to complex diseases. Although many works have been done to identify and quantify the importance of multi-SNP interactions, few of them could handle the genome wide data due to the combinatorial explosive search space and the difficulty to statistically evaluate the high-order interactions given limited samples. Three comparative experiments are designed to evaluate the performance of MegaSNPHunter. The first experiment uses synthetic data generated on the basis of epistasis models. The second one uses a genome wide study on Parkinson disease (data acquired by using Illumina HumanHap300 SNP chips). The third one chooses the rheumatoid arthritis study from Wellcome Trust Case Control Consortium (WTCCC) using Affymetrix GeneChip 500K Mapping Array Set. MegaSNPHunter outperforms the best solution in this area and reports many potential interactions for the two real studies. The experimental results on both synthetic data and two real data sets demonstrate that our proposed approach outperforms the best solution that is currently available in handling large-scale SNP data both in terms of speed and in terms of detection of potential interactions that were not identified before. To our knowledge, MegaSNPHunter is the first approach that is capable of identifying the disease-associated SNP interactions from WTCCC studies and is promising for practical disease prognosis.

Activity recognition: linking low-level sensors to high-level intelligence

Abstract: Sensors provide computer systems with a window to the outside world. Activity recognition "sees" what is in the window to predict the locations, trajectories, actions, goals and plans of humans and objects. Building an activity recognition system requires a full range of interaction from statistical inference on lower level sensor data to symbolic AI at higher levels, where prediction results and acquired knowledge are passed up each level to form a knowledge food chain. In this article, I will give an overview of some of the current activity recognition research works and explore a life-cycle of learning and inference that allows the lowest-level radio-frequency signals to be transformed into symbolic logical representations for AI planning, which in turn controls the robots or guides human users through a sensor network, thus completing a full life cycle of knowledge.

SVM: Support Vector Machines

Abstract: Support vector machines (SVMs), including support vector classifier (SVC) and support vector regressor (SVR), are among the most robust and accurate methods in all well-known data mining algorithms. SVMs, which were originally developed by Vapnik in the 1990s [1-11], have a sound theoretical foundation rooted in statistical learning theory, require only as few as a dozen examples for training, and are often insensitive to the number of dimensions. In the past decade, SVMs have been developed at a fast pace both in theory and practice.

Abnormal activity recognition based on HDP-HMM models

Abstract: Detecting abnormal activities from sensor readings is an important research problem in activity recognition. A number of different algorithms have been proposed in the past to tackle this problem. Many of the previous state-based approaches suffer from the problem of failing to decide the appropriate number of states, which are difficult to find through a trial-and-error approach, in real-world applications. In this paper, we propose an accurate and flexible framework for abnormal activity recognition from sensor readings that involves less human tuning of model parameters. Our approach first applies a Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), which supports an infinite number of states, to automatically find an appropriate number of states. We incorporate a Fisher Kernel into the One-Class Support Vector Machine (OCSVM) model to filter out the activities that are likely to be normal. Finally, we derive an abnormal activity model from the normal activity models to reduce false positive rate in an unsupervised manner. Our main contribution is that our proposed HDP-HMM models can decide the appropriate number of states automatically, and that by incorporating a Fisher Kernel into the OCSVM model, we can combine the advantages from generative model and discriminative model. We demonstrate the effectiveness of our approach by using several real-world datasets to test our algorithm's performance.

Spatio-temporal event detection using dynamic conditional random fields

Abstract: Event detection is a critical task in sensor networks for a variety of real-world applications Many real-world events often exhibit complex spatio-temporal patterns whereby they manifest themselves via observations over time and space proximities These spatio-temporal events cannot be handled well by many of the previous approaches In this paper, we propose a new Spatio-Temporal Event Detection (STED) algorithm in sensor networks based on a dynamic conditional random field (DCRF) model Our STED method handles the uncertainty of sensor data explicitly and permits neighborhood interactions in both observations and event labels Experiments on both real data and synthetic data demonstrate that our STED method can provide accurate event detection in near real time even for large-scale sensor networks

User language model for collaborative personalized search

Abstract: Traditional personalized search approaches rely solely on individual profiles to construct a user model. They are often confronted by two major problems: data sparseness and cold-start for new individuals. Data sparseness refers to the fact that most users only visit a small portion of Web pages and hence a very sparse user-term relationship matrix is generated, while cold-start for new individuals means that the system cannot conduct any personalization without previous browsing history. Recently, community-based approaches were proposed to use the group's social behaviors as a supplement to personalization. However, these approaches only consider the commonality of a group of users and still cannot satisfy the diverse information needs of different users. In this article, we present a new approach, called collaborative personalized search. It considers not only the commonality factor among users for defining group user profiles and global user profiles, but also the specialties of individuals. Then, a statistical user language model is proposed to integrate the individual model, group user model and global user model together. In this way, the probability that a user will like a Web page is calculated through a two-step smoothing mechanism. First, a global user model is used to smooth the probability of unseen terms in the individual profiles and provide aggregated behavior of global users. Then, in order to precisely describe individual interests by looking at the behaviors of similar users, users are clustered into groups and group-user models are constructed. The group-user models are integrated into an overall model through a cluster-based language model. The behaviors of the group users can be utilized to enhance the performance of personalized search. This model can alleviate the two aforementioned problems and provide a more effective personalized search than previous approaches. Large-scale experimental evaluations are conducted to show that the proposed approach substantially improves the relevance of a search over several competitive methods.

Learning HTN method preconditions and action models from partial observations

Abstract: To apply hierarchical task network (HTN) planning to real-world planning problems, one needs to encode the HTN schemata and action models beforehand. However, acquiring such domain knowledge is difficult and time-consuming because the HTN domain definition involves a significant knowledge-engineering effort. A system that can learn the HTN planning domain knowledge automatically would save time and allow HTN planning to be used in domains where such knowledgeengineering effort is not feasible. In this paper, we present a formal framework and algorithms to acquire HTN planning domain knowledge, by learning the preconditions and effects of actions and preconditions of methods. Our algorithm, HTN-learner, first builds constraints from given observed decomposition trees to build action models and method preconditions. It then solves these constraints using a weighted MAX-SAT solver. The solution can be converted to action models and method preconditions. Unlike prior work on HTN learning, we do not depend on complete action models or state information. We test the algorithm on several domains, and show that our HTN-learner algorithm is both effective and efficient.

Semantic Sensor Net: an extensible framework

Abstract: Existing approaches for sensor networks suffer from a number of serious drawbacks, including assumption of homogeneous sensor nodes, application-dependency, engineering-orientation, and lack of interoperability. To overcome these drawbacks, we propose an extensive framework: Semantic Sensor Net (SSN). It is a framework catering for heterogeneous sensor networks, which enables dynamic tagging of semantic information to sensory data to allow more efficient and systematic monitoring and handling of environmental dynamics to provide diverse services. Semantics refers to the important meaning of sensory data, sensor nodes and application requirements. Essential semantics enables integration, exchange, and reuse of sensory data across various applications.

Joint learning user's activities and profiles from GPS data

Abstract: As the GPS-enabled mobile devices become extensively available, we are now given a chance to better understand human behaviors from a large amount of the GPS trajectories representing the mobile users' location histories. In this paper, we aim to establish a framework, which can jointly learn the user activities (what is the user doing) and profiles (what is the user's background, such as occupation, gender, age, etc.) from the GPS data. We will show that, learning user activities and learning user profiles can be beneficial to each other in nature, so we try to put them together and formulate a joint learning problem under a probabilistic collaborative filtering framework. In particular, for activity recognition, we manage to extract the location semantics from the raw GPS data and use it, together with the user profile, as the input; and we will output the corresponding activities of daily living. For user profile learning, we build a mobile social network among the users by modeling their similarities with the performed activities and known user backgrounds. Compared with the other work on solely learning user activities or profiles from GPS data, our approach is advantageous by exploiting the connections between the user activities and profiles for joint learning.

Semi-supervised protein subcellular localization

Abstract: Protein subcellular localization is concerned with predicting the location of a protein within a cell using computational method. The location information can indicate key functionalities of proteins. Accurate predictions of subcellular localizations of protein can aid the prediction of protein function and genome annotation, as well as the identification of drug targets. Computational methods based on machine learning, such as support vector machine approaches, have already been widely used in the prediction of protein subcellular localization. However, a major drawback of these machine learning-based approaches is that a large amount of data should be labeled in order to let the prediction system learn a classifier of good generalization ability. However, in real world cases, it is laborious, expensive and time-consuming to experimentally determine the subcellular localization of a protein and prepare instances of labeled data. In this paper, we present an approach based on a new learning framework, semi-supervised learning, which can use much fewer labeled instances to construct a high quality prediction model. We construct an initial classifier using a small set of labeled examples first, and then use unlabeled instances to refine the classifier for future predictions. Experimental results show that our methods can effectively reduce the workload for labeling data using the unlabeled data. Our method is shown to enhance the state-of-the-art prediction results of SVM classifiers by more than 10%.

A High-voltage and High-power Amplifier for Driving Piezoelectric Stack Actuators

Abstract: Aiming at the strong capacitive impedance of piezoelectric stack actuators, the principle to improve the dynamic performance of piezoelectric stack actuators through increasing the peak values of t...

HIPS: A calibration-less hybrid indoor positioning system using heterogeneous sensors

Abstract: Positioning is a crucial task in pervasive computing, aimed at estimating the user's positions to provide location-based services. In this paper, we study an interesting problem: when we wish to obtain hybrid positioning granularities in an office environment, how can we incorporate heterogeneous sensors to build an indoor positioning system with minimal human calibration effort? We propose a calibration-less solution by incorporating the ultrasound sensors with the radio-frequency sensors. In our solution, we use these two different types of sensors to satisfy the different granularities requirement; and meanwhile, we use the ultrasound sensors to help calibrate the radio-frequency sensors for positioning, so that we can minimize, or even eliminate the labeling effort for the radio-frequency positioning. Finally, we develop a system prototype with real-world sensor networks, and verify the feasibility and effectiveness of our proposed solution.

Joint learning user's activities and profiles from GPS data

Abstract: As the GPS-enabled mobile devices become extensively available, we are now given a chance to better understand human behaviors from a large amount of the GPS trajectories representing the mobile users' location histories. In this paper, we aim to establish a framework, which can jointly learn the user activities (what is the user doing) and profiles (what is the user's background, such as occupation, gender, age, etc.) from the GPS data. We will show that, learning user activities and learning user profiles can be beneficial to each other in nature, so we try to put them together and formulate a joint learning problem under a probabilistic collaborative filtering framework. In particular, for activity recognition, we manage to extract the location semantics from the raw GPS data and use it, together with the user profile, as the input; and we will output the corresponding activities of daily living. For user profile learning, we build a mobile social network among the users by modeling their similarities with the performed activities and known user backgrounds. Compared with the other work on solely learning user activities or profiles from GPS data, our approach is advantageous by exploiting the connections between the user activities and profiles for joint learning.

Relaxed Transfer of Different Classes via Spectral Partition

Abstract: Most existing transfer learning techniques are limited to problems of knowledge transfer across tasks sharing the same set of class labels. In this paper, however, we relax this constraint and propose a spectral-based solution that aims at unveiling the intrinsic structure of the data and generating a partition of the target data, by transferring the eigenspace that well separates the source data. Furthermore, a clustering-based KL divergence is proposed to automatically adjust how much to transfer. We evaluate the proposed model on text and image datasets where class categories of the source and target data are explicitly different, e.g., 3-classes transfer to 2-classes, and show that the proposed approach improves other baselines by an average of 10% in accuracy. The source code and datasets are available from the authors.

PQC: personalized query classification

Abstract: Query classification (QC) is a task that aims to classify Web queries into topical categories. Since queries are usually short in length and ambiguous, the same query may need to be classified to different categories according to different people's perspectives. In this paper, we propose the Personalized Query Classification (PQC) task and develop an algorithm based on user preference learning as a solution. Users' preferences that are hidden in clickthrough logs are quite helpful for search engines to improve their understandings of users' queries. We propose to connect query classification with users' preference learning from clickthrough logs for PQC. To tackle the sparseness problem in clickthrough logs, we propose a collaborative ranking model to leverage similar users' information. Experiments on a real world clickthrough log data show that our proposed PQC algorithm can gain significant improvement compared with general QC as well as natural baselines. Our method can be applied to a wide range of applications including personalized search and online advertising.

Transfer Learning beyond Text Classification

Abstract: Transfer learning is a new machine learning and data mining framework that allows the training and test data to come from different distributions or feature spaces. We can find many novel applications of machine learning and data mining where transfer learning is necessary. While much has been done in transfer learning in text classification and reinforcement learning, there has been a lack of documented success stories of novel applications of transfer learning in other areas. In this invited article, I will argue that transfer learning is in fact quite ubiquitous in many real world applications. In this article, I will illustrate this point through an overview of a broad spectrum of applications of transfer learning that range from collaborative filtering to sensor based location estimation and logical action model learning for AI planning. I will also discuss some potential future directions of transfer learning.

A communication system architecture for regional control of power distribution networks

Abstract: A large and increasing number of distributed generators connected to the existing UK distribution networks brings enormous challenges to network operation and management. The regional network management system is suggested to tackle these industrial challenges through ubiquitous deployment of autonomous regional controllers with reliable and flexible communication among them. Such regional power network control requires a more advanced communication infrastructure than the existing SCADA system. In this paper, we present a conceptual communication infrastructure for regional control of power distribution networks in the context of an autonomous regional active network management system, and highlight the key communication system requirements. A case study of communication infrastructure supporting radial distribution network regional control is provided with the performance evaluation. Our study shows that TCP/IP based communication would need to be introduced into the communication infrastructure design to support regional network management system.

Context-Aware Online Commercial Intention Detection

Abstract: With more and more commercial activities moving onto the Internet, people tend to purchase what they need through Internet or conduct some online research before the actual transactions happen. For many Web users, their online commercial activities start from submitting a search query to search engines. Just like the common Web search queries, the queries with commercial intention are usually very short. Recognizing the queries with commercial intention against the common queries will help search engines provide proper search results and advertisements, help Web users obtain the right information they desire and help the advertisers benefit from the potential transactions. However, the intentions behind a query vary a lot for users with different background and interest. The intentions can even be different for the same user, when the query is issued in different contexts. In this paper, we present a new algorithm framework based on skip-chain conditional random field (SCCRF) for automatically classifying Web queries according to context-based online commercial intention . We analyze our algorithm performance both theoretically and empirically. Extensive experiments on several real search engine log datasets show that our algorithm can improve more than 10% on F1 score than previous algorithms on commercial intention detection.

Analysis of expressed sequence tags from Chaetomium cupreum grown under conditions associated with mycoparasitism

Abstract: Aims: To elucidate the molecular mechanisms associated with mycoparasitism from Chaetomium cupreum, an effective biocontrol agent with ability against plant pathogenic fungi. Methods and Results: One cDNA library was constructed from conditions predicted to resemble mycoparasitic process. A total of 1876 ESTs were generated and assembled into 1035 unigenes. BlastX search revealed that 585 unigenes had similarities with sequences available from public databases. Based on the ESTs abundance, MFS monosaccharide transporter was found as the gene expressed at the highest level. A KEGG analysis allowed mapping of 60 metabolic pathways well represented by the glycolysis/gluconeogenesis, d-arginine and ornithine metabolism, and tryptophan metabolism. The genes related to mycoparasitism were detected. Conclusions: The results revealed that the cell walls of the fungal pathogen can simulate some aspects of the mycoparasitic interaction between C. cupreum and its targets. Significance and Impact of the Study: This is the first report to study genes expression under conditions associated with the mycoparasitic process. The findings contribute to elucidate the molecular mechanisms involved in mycoparasitism and will help to advance our efforts in developing novel strategies for biocontrol of plant fungal diseases.