Qiang Yang

The Hong Kong University of Science and Technology, Chiu-lung, Kowloon City, Hong Kong

Are you Qiang Yang?

Claim your profile

Publications (375)182.65 Total impact

  • [show abstract] [hide abstract]
    ABSTRACT: Friendship prediction is an important task in social network analysis (SNA). It can help users identify friends and improve their level of activity. Most previous approaches predict users' friendship based on their historical records, such as their existing friendship, social interactions, etc. However, in reality, most users have limited friends in a single network, and the data can be very sparse. The sparsity problem causes existing methods to overfit the rare observations and suffer from serious performance degradation. This is particularly true when a new social network just starts to form. We observe that many of today's social networks are composite in nature, where people are often engaged in multiple networks. In addition, users' friendships are always correlated, for example, they are both friends on Facebook and Google+. Thus, by considering those overlapping users as the bridge, the friendship knowledge in other networks can help predict their friendships in the current network. This can be achieved by exploiting the knowledge in different networks in a collective manner. However, as each individual network has its own properties that can be incompatible and inconsistent with other networks, the naive merging of all networks into a single one may not work well. The proposed solution is to extract the common behaviors between different networks via a hierarchical Bayesian model. It captures the common knowledge across networks, while avoiding negative impacts due to network differences. Empirical studies demonstrate that the proposed approach improves the mean average precision of friendship prediction over state-of-the-art baselines on nine real-world social networking datasets significantly.
    02/2014;
  • Hankz Hankui Zhuo, Qiang Yang
    [show abstract] [hide abstract]
    ABSTRACT: Applying learning techniques to acquire action models is an area of intense research interest. Most previous work in this area has assumed that there is a significant amount of training data available in a planning domain of interest. However, it is often difficult to acquire sufficient training data to ensure the learnt action models are of high quality. In this paper, we seek to explore a novel algorithm framework, called TRAMP, to learn action models with limited training data in a target domain, via transferring as much of the available information from other domains (called source domains) as possible to help the learning task, assuming action models in source domains can be transferred to the target domain. TRAMP transfers knowledge from source domains by first building structure mappings between source and target domains, and then exploiting extra knowledge from Web search to bridge and transfer knowledge from sources. Specifically, TRAMP first encodes training data with a set of propositions, and formulates the transferred knowledge as a set of weighted formulas. After that it learns action models for the target domain to best explain the set of propositions and the transferred knowledge. We empirically evaluate TRAMP in different settings to see their advantages and disadvantages in six planning domains, including four International Planning Competition (IPC) domains and two synthetic domains.
    Artificial Intelligence. 01/2014;
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: BACKGROUND: The detection of epistasis among genetic markers is of great interest in genome-wide association studies (GWAS). In recent years, much research has been devoted to find disease associated epistasis in GWAS. However, due to the high computational cost involved, most methods focus on specific epistasis models, making the potential loss of power when the underlying epistasis models are not examined in these analyses. RESULTS: In this work, we propose a computational efficient approach based on complete enumeration of two-locus epistasis models. This approach uses a two-stage (screening and testing) search strategy and the enumeration of all epistasis patterns is guaranteed. The implementation is done on graphic processing units (GPU), which can finish the analysis on a GWAS data (with around 5, 000 subjects and around 350, 000 markers) within two hours. CONCLUSIONS: This work demonstrates that the complete compositional epistasis detection is computationally feasible in GWAS.
    BMC Genetics 02/2013; 14(1):7. · 2.81 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: Genome-wide association study (GWAS) has been successful in identifying genetic variants that are associated with complex human diseases. In GWAS, multilocus association analyses through linkage disequilibrium (LD), named haplotype-based analyses, may have greater power than single-locus analyses for detecting disease susceptibility loci. However, the large number of SNPs genotyped in GWAS poses great computational challenges in the detection of haplotype associations. We present a fast method named HapBoost for finding haplotype associations, which can be applied to quickly screen the whole genome. The effectiveness of HapBoost is demonstrated by using both synthetic and real data sets. The experimental results show that the proposed approach can achieve comparably accurate results while it performs much faster than existing methods.
    IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM 01/2013; 10(1):207-212. · 2.25 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: Demographics prediction is an important component of user profile modeling. The accurate prediction of users’ demographics can help promote many applications, ranging from web search, personalization to behavior targeting. In this paper, we focus on how to predict users’ demographics, including “gender”, “job type”, “marital status”, “age” and “number of family members”, based on mobile data, such as users’ usage logs, physical activities and environmental contexts. The core idea is to build a supervised learning framework, where each user is represented as a feature vector and users’ demographics are considered as prediction targets. The most important component is to construct features from raw data and then supervised learning models can be applied. We propose a feature construction framework, CFC (contextual feature construction), where each feature is defined as the conditional probability of one user activity under the given contexts. Consequently, besides employing standard supervised learning models, we propose a regularized multi-task learning framework to model different kinds of demographics predictions collectively. We also propose a cost-sensitive classification framework for regression tasks, in order to benefit from the existing dimension reduction methods. Finally, due to the limited training instances, we employ ensemble to avoid overfitting. The experimental results show that the framework achieves classification accuracies on “gender”, “job” and “marital status” as high as 96%, 83% and 86%, respectively, and achieves Root Mean Square Error (RMSE) on “age” and “number of family members” as low as 0.69 and 0.66 respectively, under the leave-one-out evaluation.
    Pervasive and Mobile Computing. 01/2013; 9(6):823–837.
  • [show abstract] [hide abstract]
    ABSTRACT: We present in this paper our winning solution to Dedicated Task 1 in Nokia Mobile Data Challenge (MDC). MDC Task 1 is to infer the semantic category of a place based on the smartphone sensing data obtained at that place. We approach this task in a standard supervised learning setting: we extract discriminative features from the sensor data and use state-of-the-art classifiers (SVM, Logistic Regression and Decision Tree Family) to build classification models. We have found that feature engineering, or in other words, constructing features using human heuristics, is very effective for this task. In particular, we have proposed a novel feature engineering technique, Conditional Feature (CF), a general framework for domain-specific feature construction. In total, we have generated 2,796,200 features and in our final five submissions we use feature selection to select 100 to 2000 features. One of our key findings is that features conditioned on fine-granularity time intervals, e.g. every 30 min, are most effective. Our best 10-fold CV accuracy on training set is 75.1% by Gradient Boosted Trees, and the second best accuracy is 74.6% by L1-regularized Logistic Regression. Besides the good performance, we also report briefly our experience of using F# language for large-scale (∼70 GB raw text data) conditional feature construction.
    Pervasive and Mobile Computing. 01/2013; 9(6):772–783.
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Collaborative filtering (CF) aims to predict users' ratings on items according to historical user-item preference data. In many real-world applications, preference data are usually sparse, which would make models overfit and fail to give accurate predictions. Recently, several research works show that by transferring knowledge from some manually selected source domains, the data sparseness problem could be mitigated. However for most cases, parts of source domain data are not consistent with the observations in the target domain, which may misguide the target domain model building. In this paper, we propose a novel criterion based on empirical prediction error and its variance to better capture the consistency across domains in CF settings. Consequently, we embed this criterion into a boosting framework to perform selective knowledge transfer. Comparing to several state-of-the-art methods, we show that our proposed selective transfer learning framework can significantly improve the accuracy of rating prediction tasks on several real-world recommendation tasks.
    10/2012;
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: In this paper, we infer the statuses of a taxi, consisting of occupied, non-occupied and parked, in terms of its GPS trajectory. The status information can enable urban computing for improving a city's transportation systems and land use planning. In our solution, we first identify and extract a set of effective features incorporating the knowledge of a single trajectory, historical trajectories and geographic data like road network. Second, a parking status detection algorithm is devised to find parking places (from a given trajectory), dividing a trajectory into segments (i.e., sub-trajectories). Third, we propose a two-phase inference model to learn the status (occupied or non-occupied) of each point from a taxi segment. This model first uses the identified features to train a local probabilistic classifier and then carries out a Hidden Semi-Markov Model (HSMM) for globally considering long term travel patterns. We evaluated our method with a large-scale real-world trajectory dataset generated by 600 taxis, showing the advantages of our method over baselines.
    05/2012;
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: With the increasing popularity of location-based services, we have accumu-lated a lot of location data on the Web. In this paper, we are interested in answering two popular location-related queries in our daily life: 1) if we want to do something such as sightseeing or dining in a large city like Bei-jing, where should we go? 2) If we want to visit a place such as the Bird's Nest in Beijing Olympic park, what can we do there? We develop a mobile recommendation system to answer these queries. In our system, we first model the users' location and activity histories as a user-location-activity rating tensor 1 . Because each user has limited data, the resulting rating tensor is essentially very sparse. This makes our recommendation task dif-ficult. In order to address this data sparsity problem, we propose three algorithms 2 based on collaborative filtering. The first algorithm merges all the users' data together, and uses a collective matrix factorization model to provide general recommendation [3]. The second algorithm treats each user differently and uses a collective tensor and matrix factorization model to provide personalized recommendation [4]. The third algorithm is a new algorithm which further improves our previous two algorithms by using a ranking-based collective tensor and matrix factorization model. Instead of trying to predict the missing entry values as accurately as possible, it fo-cuses on directly optimizing the ranking loss w.r.t. user preferences on the locations and activities. Therefore, it is more consistent with our ultimate 1 A "tensor" is a multi-dimensional array [1, 2]. 2 This work is an extension to our previous work [3, 4]. We propose a new model in Section 5.3 and completely re-conduct the experiments for all our three algorithms. goal of ranking locations/activities for recommendations. For these three algorithms, we also exploit some additional information, such as user-user similarities, location features, activity-activity correlations and user-location preferences, to help the CF tasks. We extensively evaluate our algorithms using a real-world GPS dataset collected by 119 users over 2.5 years. We show that all our three algorithms can consistently outperform the compet-ing baselines, and our newly proposed third algorithm can also outperform our other two previous algorithms.
    03/2012;
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Click models have been positioned as an effective approach to interpret user click behavior in search engines. Existing click models mostly focus on traditional Web search that considers only ten homogeneous Web HTML documents that appear on the first search-result page. However, in modern commercial search engines, more and more Web search results are federated from multiple sources and contain non-HTML results returned by other heterogeneous vertical engines, such as video or image search engines. In this paper, we study user click behavior in federated search. We observed that user click behavior in federated search is highly different from that in traditional Web search, making it difficult to interpret using existing click models. In response, we propose a novel federated click model (FCM) to interpret user click behavior in federated search. In particular, we take into considerations two new biases in FCM. The first comes from the observation that users tend to be attracted by vertical results and their visual attention on them may increase the examination probability of other nearby web results. The other illustrates that user click behavior on vertical results may lead to more clues of search relevance due to their presentation style in federated search. With these biases and an effective model to correct them, FCM is more accurate in characterizing user click behavior in federated search. Our extensive experimental results show that FCM can outperform other click models in interpreting user click behavior in federated search and achieve significant improvements in terms of both perplexity and log-likelihood.
    Proceedings of the Fifth International Conference on Web Search and Web Data Mining, WSDM 2012, Seattle, WA, USA, February 8-12, 2012; 01/2012
  • [show abstract] [hide abstract]
    ABSTRACT: Short Message Service text messages are indispensable, but they face a serious problem from spamming. This service-side solution uses graph data mining to distinguish spammers from nonspammers and detect spam without checking a message's contents.
    Intelligent Systems, IEEE 01/2012; 27(6):44-51. · 1.93 Impact Factor
  • Si Shen, Botao Hu, Weizhu Chen, Qiang Yang
    [show abstract] [hide abstract]
    ABSTRACT: Click modeling aims to interpret the users' search click data in order to predict their clicking behavior. Existing models can well characterize the position bias of documents and snippets in relation to users' mainstream click behavior. Yet, current advances depict users' search actions only in a general setting by implicitly assuming that all users act in the same way, regardless of the fact that anyone, motivated with some individual interest, is more likely to click on a link than others. It is in light of this that we put forward a novel personalized click model to describe the user-oriented click preferences, which applies and extends matrix / tensor factorization from the view of collaborative filtering to connect users, queries and documents together. Our model serves as a generalized personalization framework that can be incorporated to the previously proposed click models and, in many cases, to their future extensions. Despite the sparsity of search click data, our personalized model demonstrates its advantage over the best click models previously discussed in the Web-search literature, supported by our large-scale experiments on a real dataset. A delightful bonus is the model's ability to gain insights into queries and documents through latent feature vectors, and hence to handle rare and even new query-document pairs much better than previous click models.
    Proceedings of the Fifth International Conference on Web Search and Web Data Mining, WSDM 2012, Seattle, WA, USA, February 8-12, 2012; 01/2012
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: With the increasing popularity of location-based services, we have accumulated a lot of location data on the Web. In this paper, we are interested in answering two popular location-related queries in our daily life: 1) if we want to do something such as sightseeing or dining in a large city like Beijing, where should we go? 2) If we want to visit a place such as the Bird's Nest in Beijing Olympic park, what can we do there? We develop a mobile recommendation system to answer these queries. In our system, we first model the users' location and activity histories as a user-location-activity rating tensor1. Because each user has limited data, the resulting rating tensor is essentially very sparse. This makes our recommendation task difficult. In order to address this data sparsity problem, we propose three algorithms2 based on collaborative filtering. The first algorithm merges all the users' data together, and uses a collective matrix factorization model to provide general recommendation [3]. The second algorithm treats each user differently and uses a collective tensor and matrix factorization model to provide personalized recommendation [4]. The third algorithm is a new algorithm which further improves our previous two algorithms by using a ranking-based collective tensor and matrix factorization model. Instead of trying to predict the missing entry values as accurately as possible, it focuses on directly optimizing the ranking loss w.r.t. user preferences on the locations and activities. Therefore, it is more consistent with our ultimate goal of ranking locations/activities for recommendations. For these three algorithms, we also exploit some additional information, such as user-user similarities, location features, activity-activity correlations and user-location preferences, to help the CF tasks. We extensively evaluate our algorithms using a real-world GPS dataset collected by 119 users over 2.5 years. We show that all our three algorithms can consistently outperform the competing baselines, and our newly proposed third algorithm can also outperform our other two previous algorithms.
    Artificial Intelligence. 01/2012; s 184–185.
  • [show abstract] [hide abstract]
    ABSTRACT: Mining the frequently visited places of single mobile users, i.e., significant places, is crucial for supporting personalized location-based services. Most of existing works for significance place mining have a need to take advantage the GPS trajectories of users. However, it is difficult to encourage mobile users to contribute GPS trajectories because of the high power consumption of GPS. In this demonstration, we propose a geo-grid based approach for mining significant places from cell ID trajectories. In our approach, the mined significant places are represented as sets of geo-grids which are much smaller than the coverage areas of cell-sites. To be specific, we firstly extract the stay areas where the mobile user used to stay and map them to many geogrids. Then we mine significant places from the geo-grids by considering their significance.
    Mobile Data Management (MDM), 2012 IEEE 13th International Conference on; 01/2012
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Recent advances in click model have established it as an attractive approach to infer document relevance. Most of these advances consider the user click/skip behavior as binary events but neglect the context in which a click happens. We show that real click behavior in industrial search engines is often noisy and not always a good indication of relevance. For a considerable percentage of clicks, users select what turn out to be irrelevant documents and these clicks should not be directly used as evidence for relevance inference. Thus in this paper, we put forward an observation that the relevance indication degree of a click is not a constant, but can be differentiated by user preferences and the context in which the user makes her click decision. In particular, to interpret the click behavior discriminatingly, we propose a Noise-aware Click Model (NCM) by characterizing the noise degree of a click, which indicates the quality of the click for inferring relevance. Specifically, the lower the click noise is, the more important the click is in its role for relevance inference. To verify the necessity of explicitly accounting for the uninformative noise in a user click, we conducted experiments on a billion-scale dataset. Extensive experimental results demonstrate that as compared with two state-of-the-art click models in Web Search, NCM can better interpret user click behavior and achieve significant improvements in terms of both perplexity and NDCG.
    Proceedings of the Fifth International Conference on Web Search and Web Data Mining, WSDM 2012, Seattle, WA, USA, February 8-12, 2012; 01/2012
  • Simone Marini, Qian Xu, Qiang Yang
    [show abstract] [hide abstract]
    ABSTRACT: Protein-Protein Interaction (PPI) prediction is a well known problem in Bioinformatics, for which a large number of techniques have been proposed in the past. However, prediction results have not been sufficiently satisfactory for guiding biologists in web-lab experiments. One reason is that not all useful information, such as pairwise protein interaction information based on sequence alignment, has been integrated together in PPI prediction. Alignment is a basic concept to measure sequence similarity in Proteomics that has been used in a number of applications ranging from protein recognition to protein subcellular localization. In this article, we propose a novel integrated approach to predicting PPI based on sequence alignment by jointly using a k-Nearest Neighbor classifier (SA-kNN) and a Support Vector Machine (SVM). SVM is a machine learning technique used in a wide range of Bioinformatics applications, thanks to the ability to alleviate the overfitting problems. We demonstrate that in our approach the two methods, SA-kNN and SVM, are complementary, which are combined in an ensemble to overcome their respective limitations. While the SVM is trained on Amino Acid (AA) compositions and protein signatures mined from literature, the SA-kNN makes use of the similarity of two protein pairs through alignment. Experimentally, our technique leads to a significant gain in accuracy, precision and sensitivity measures at ~5%, 16% and 10% respectively.
    Current Protein and Peptide Science 08/2011; 12(7):614-20. · 2.33 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Recent years have witnessed the growing popularity of sensor and sensor-network technologies, supporting important practical applications. One of the fundamental issues is how to accurately locate a user with few labeled data in a wireless sensor network, where a major difficulty arises from the need to label large quantities of user location data, which in turn requires knowledge about the locations of signal transmitters or access points. To solve this problem, we have developed a novel machine learning-based approach that combines collaborative filtering with graph-based semi-supervised learning to learn both mobile users' locations and the locations of access points. Our framework exploits both labeled and unlabeled data from mobile devices and access points. In our two-phase solution, we first build a manifold-based model from a batch of labeled and unlabeled data in an offline training phase and then use a weighted k-nearest-neighbor method to localize a mobile client in an online localization phase. We extend the two-phase colocalization to an online and incremental model that can deal with labeled and unlabeled data that come sequentially and adapt to environmental changes. Finally, we embed an action model to the framework such that additional kinds of sensor signals can be utilized to further boost the performance of mobile tracking. Compared to other state-of-the-art systems, our framework has been shown to be more accurate while requiring less calibration effort in our experiments performed on three different testbeds.
    IEEE Transactions on Software Engineering 08/2011; 34(3):587-600. · 2.59 Impact Factor
  • [show abstract] [hide abstract]
    ABSTRACT: Although genome-wide association studies (GWAS) have identified many disease-susceptibility single-nucleotide polymorphisms (SNPs), these findings can only explain a small portion of genetic contributions to complex diseases, which is known as the missing heritability. A possible explanation is that genetic variants with small effects have not been detected. The chance is < 8 that a causal SNP will be directly genotyped. The effects of its neighboring SNPs may be too weak to be detected due to the effect decay caused by imperfect linkage disequilibrium. Moreover, it is still challenging to detect a causal SNP with a small effect even if it has been directly genotyped. In order to increase the statistical power when detecting disease-associated SNPs with relatively small effects, we propose a method using neighborhood information. Since the disease-associated SNPs account for only a small fraction of the entire SNP set, we formulate this problem as Contiguous Outlier DEtection (CODE), which is a discrete optimization problem. In our formulation, we cast the disease-associated SNPs as outliers and further impose a spatial continuity constraint for outlier detection. We show that this optimization can be solved exactly using graph cuts. We also employ the stability selection strategy to control the false positive results caused by imperfect parameter tuning. We demonstrate its advantage in simulations and real experiments. In particular, the newly identified SNP clusters are replicable in two independent datasets. The software is available at: http://bioinformatics.ust.hk/CODE.zip. eeyu@ust.hk Supplementary data are available at Bioinformatics online.
    Bioinformatics 07/2011; 27(18):2578-85. · 5.47 Impact Factor
  • Qian Xu, Evan Wei Xiang, Qiang Yang
    [show abstract] [hide abstract]
    ABSTRACT: Protein-protein interactions (PPIs) play an important role in cellular processes within a cell. An important task is to determine the existence of interactions among proteins. Unfortunately, the existing biological experimental techniques are expensive, time-consuming and labor-intensive. The network structures of many such networks are sparse, incomplete and noisy. Thus, state-of-the-art methods for link prediction in these networks often cannot give satisfactory prediction results, especially when some networks are extremely sparse. Noticing that we typically have more than one PPI network available, we naturally wonder whether it is possible to 'transfer' the linkage knowledge from some existing, relatively dense networks to a sparse network, to improve the prediction performance. Noticing that a network structure can be modeled using a matrix model, we introduce the well-known collective matrix factorization technique to 'transfer' usable linkage knowledge from relatively dense interaction network to a sparse target network. Our approach is to establish a correspondence between a source network and a target network via network-wide similarities. We test this method on two real PPI networks, Helicobacter pylori (as a target network) and human (as a source network). Our experimental results show that our method can achieve higher performance as compared with some baseline methods.
    Proteomics 07/2011; 11(19):3818-25. · 4.43 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Protein subcellular localization is concerned with predicting the location of a protein within a cell using computational methods. The location information can indicate key functionalities of proteins. Thus, accurate prediction of subcellular localizations of proteins can help the prediction of protein functions and genome annotations, as well as the identification of drug targets. Machine learning methods such as Support Vector Machines (SVMs) have been used in the past for the problem of protein subcellular localization, but have been shown to suffer from a lack of annotated training data in each species under study. To overcome this data sparsity problem, we observe that because some of the organisms may be related to each other, there may be some commonalities across different organisms that can be discovered and used to help boost the data in each localization task. In this paper, we formulate protein subcellular localization problem as one of multitask learning across different organisms. We adapt and compare two specializations of the multitask learning algorithms on 20 different organisms. Our experimental results show that multitask learning performs much better than the traditional single-task methods. Among the different multitask learning methods, we found that the multitask kernels and supertype kernels under multitask learning that share parameters perform slightly better than multitask learning by sharing latent features. The most significant improvement in terms of localization accuracy is about 25 percent. We find that if the organisms are very different or are remotely related from a biological point of view, then jointly training the multiple models cannot lead to significant improvement. However, if they are closely related biologically, the multitask learning can do much better than individual learning.
    IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM 07/2011; 8(3):748-59. · 2.25 Impact Factor

Publication Stats

6k Citations
182.65 Total Impact Points

Institutions

  • 1970–2014
    • The Hong Kong University of Science and Technology
      • • Department of Computer Science and Engineering
      • • Department of Electronic and Computer Engineering
      Chiu-lung, Kowloon City, Hong Kong
  • 2013
    • Hong Kong Baptist University
      Chiu-lung, Kowloon City, Hong Kong
  • 2012
    • Microsoft
      Washington, West Virginia, United States
    • The University of Hong Kong
      Hong Kong, Hong Kong
  • 2011
    • Southeast University (China)
      • School of Computer Science and Engineering
      Nanjing, Jiangxi Sheng, China
  • 2005–2011
    • Institute for Infocomm Research
      Tumasik, Singapore
  • 2010
    • Stanford University
      Palo Alto, California, United States
    • IBM
      Armonk, New York, United States
  • 2001–2010
    • Shanghai Jiao Tong University
      • Department of Computer Science and Engineering
      Shanghai, Shanghai Shi, China
  • 2007–2009
    • Nanjing University of Aeronautics & Astronautics
      • Department of Computer Science and Technology
      Nan-ching, Jiangsu Sheng, China
    • Sun Yat-Sen University
      Shengcheng, Guangdong, China
    • University of Wisconsin, Madison
      • Department of Computer Sciences
      Madison, MS, United States
  • 2004–2009
    • Northeast Institute of Geography and Agroecology
      • • Institute of Computing Technology
      • • Institute of Software
      Beijing, Beijing Shi, China
  • 2006–2007
    • Peking University
      • School of Mathematical Sciences
      Peping, Beijing, China
  • 2005–2007
    • The Chinese University of Hong Kong
      • Department of Information Engineering
      Hong Kong, Hong Kong
  • 1996–2006
    • Simon Fraser University
      • School of Computing Science
      Burnaby, British Columbia, Canada
  • 2000
    • Tsinghua University
      Peping, Beijing, China
  • 1999
    • University of Hawaiʻi at Mānoa
      • Department of Electrical Engineering
      Honolulu, HI, United States
  • 1998
    • The University of Western Ontario
      • Department of Computer Science
      London, Ontario, Canada
  • 1992–1998
    • University of Waterloo
      Waterloo, Ontario, Canada
  • 1997
    • Carnegie Mellon University
      • Computer Science Department
      Pittsburgh, PA, United States