Collaborative recommendation is an information-filtering technique that attempts to present information items (movies, music, books, news, images, Web pages, etc.) that are likely of interest to the Internet user. Traditionally, collaborative systems deal with situations with two types of variables, users and items. In its most common form, the problem is framed as trying to estimate ratings for items that have not yet been consumed by a user. Despite wide-ranging literature, little is known about the statistical properties of recommendation systems. In fact, no clear probabilistic model even exists allowing us to precisely describe the mathematical forces driving collaborative filtering. To provide an initial contribution to this, we propose to set out a general sequential stochastic model for collaborative recommendation and analyze its asymptotic performance as the number of users grows. We offer an in-depth analysis of the so-called cosine-type nearest neighbor collaborative method, which is one of the most widely used algorithms in collaborative filtering. We establish consistency of the procedure under mild assumptions on the model. Rates of convergence and examples are also provided.

This paper presents a multilayered architecture that enhances the capabilities of current QA systems and allows different types of complex questions or queries to be processed. The answers to these questions need to be gathered from factual information scattered throughout different documents. Specifically, we designed a specialized layer to process the different types of temporal questions. Complex temporal questions are first decomposed into simple questions, according to the temporal relations expressed in the original question. In the same way, the answers to the resulting simple questions are recomposed, fulfilling the temporal restrictions of the original complex question. A novel aspect of this approach resides in the decomposition which uses a minimal quantity of resources, with the final aim of obtaining a portable platform that is easily extensible to other languages. In this paper we also present a methodology for evaluation of the decomposition of the questions as well as the ability of the implemented temporal layer to perform at a multilingual level. The temporal layer was first performed for English, then evaluated and compared with: a) a general purpose QA system (F-measure 65.47% for QA plus English temporal layer vs. 38.01% for the general QA system), and b) a well-known QA system. Much better results were obtained for temporal questions with the multilayered system. This system was therefore extended to Spanish and very good results were again obtained in the evaluation (F-measure 40.36% for QA plus Spanish temporal layer vs. 22.94% for the general QA system).

We propose a number of techniques for obtaining a global ranking from data that may be incomplete and imbalanced -- characteristics almost universal to modern datasets coming from e-commerce and internet applications. We are primarily interested in score or rating-based cardinal data. From raw ranking data, we construct pairwise rankings, represented as edge flows on an appropriate graph. Our statistical ranking method uses the graph Helmholtzian, the graph theoretic analogue of the Helmholtz operator or vector Laplacian, in much the same way the graph Laplacian is an analogue of the Laplace operator or scalar Laplacian. We study the graph Helmholtzian using combinatorial Hodge theory: we show that every edge flow representing pairwise ranking can be resolved into two orthogonal components, a gradient flow that represents the L2-optimal global ranking and a divergence-free flow (cyclic) that measures the validity of the global ranking obtained -- if this is large, then the data does not have a meaningful global ranking. This divergence-free flow can be further decomposed orthogonally into a curl flow (locally cyclic) and a harmonic flow (locally acyclic but globally cyclic); these provides information on whether inconsistency arises locally or globally. An obvious advantage over the NP-hard Kemeny optimization is that discrete Hodge decomposition may be computed via a linear least squares regression. We also investigated the L1-projection of edge flows, showing that this is dual to correlation maximization over bounded divergence-free flows, and the L1-approximate sparse cyclic ranking, showing that this is dual to correlation maximization over bounded curl-free flows. We discuss relations with Kemeny optimization, Borda count, and Kendall-Smith consistency index from social choice theory and statistics.

Music genre classification is an essential tool for music information retrieval systems and it has been finding critical applications in various media platforms. Two important problems of the automatic music genre classification are feature extraction and classifier design. This paper investigates inter-genre similarity modelling (IGS) to improve the performance of automatic music genre classification. Inter-genre similarity information is extracted over the mis-classified feature population. Once the inter-genre similarity is modelled, elimination of the inter-genre similarity reduces the inter-genre confusion and improves the identification rates. Inter-genre similarity modelling is further improved with iterative IGS modelling(IIGS) and score modelling for IGS elimination(SMIGS). Experimental results with promising classification improvements are provided.

We describe a new method for visualizing topics, the distributions over terms that are automatically extracted from large text corpora using latent variable models. Our method finds significant $n$-grams related to a topic, which are then used to help understand and interpret the underlying distribution. Compared with the usual visualization, which simply lists the most probable topical terms, the multi-word expressions provide a better intuitive impression for what a topic is "about." Our approach is based on a language model of arbitrary length expressions, for which we develop a new methodology based on nested permutation tests to find significant phrases. We show that this method outperforms the more standard use of $\chi^2$ and likelihood ratio tests. We illustrate the topic presentations on corpora of scientific abstracts and news articles.

Many sorts of structured data are commonly stored in a multi-relational format of interrelated tables. Under this relational model, exploratory data analysis can be done by using relational queries. As an example, in the Internet Movie Database (IMDb) a query can be used to check whether the average rank of action movies is higher than the average rank of drama movies. We consider the problem of assessing whether the results returned by such a query are statistically significant or just a random artifact of the structure in the data. Our approach is based on randomizing the tables occurring in the queries and repeating the original query on the randomized tables. It turns out that there is no unique way of randomizing in multi-relational data. We propose several randomization techniques, study their properties, and show how to find out which queries or hypotheses about our data result in statistically significant information. We give results on real and generated data and show how the significance of some queries vary between different randomizations.

Due to their flexible nonparametric nature, Gaussian process models are very effective at solving hard machine learning problems. While existing Gaussian process models focus on modeling one single relation, we present a generalized GP model, named multi-relational Gaussian process model, that is able to deal with an arbitrary number of relations in a domain of interest. The proposed model is analyzed in the context of bipartite, directed, and undirected univariate relations. Experimental results on real-world datasets show that exploiting the correlations among different entity types and relations can indeed improve prediction performance.

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 user-item 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.

Many applications are facing the problem of learning from an objective dataset, whereas information from other auxiliary sources may be beneficial but cannot be integrated into the objective dataset for learning. In this paper, we propose an omni-view learning approach to enable learning from multiple data collections. The theme is to organize heterogeneous data sources into a unified table with global data view. To achieve the omni-view learning goal, we consider that the objective dataset and the auxiliary datasets share some instance-level dependency structures. We then propose a relational k-means to cluster instances in each auxiliary dataset, such that clusters can help build new features to capture correlations between the objective and auxiliary datasets. Experimental results demonstrate that omni-view learning can help build models which outperform the ones learned from the objective dataset only. Comparisons with the co-training algorithm further assert that omni-view learning provides an alternative, yet effective, way for semi-supervised learning.

We propose a new topic model for tracking time-varying consumer purchase behavior, in which consumer interests and item trends change over time. The proposed model can adaptively track changes in interests and trends based on current purchase logs and previously estimated interests and trends. The online nature of the proposed method means we do not need to store past data for current inferences and so we can considerably reduce the computational cost and the memory requirement. We use real purchase logs to demonstrate the effectiveness of the proposed method in terms of the prediction accuracy of purchase behavior and the computational cost of the inference.