Collaborative filtering is an important technique for recommendation. Whereas it has been repeatedly shown to be effective in previous work,its performance remains unsatisfactory in many real-world applications, especially those where the items or users are highly diverse. In this paper, we explore an ensemble-based framework to enhance thecapability of a recommender in handling diverse data. Specifically, we formulate a probabilistic model which integrates the items, the users, as well as the associations between them into a generative process. On top of this formulation, we further derive a progressive algorithm to construct an ensemble of collaborative filters. In each iteration, a new filter is derived from re-weighted entries and incorporated into the ensemble. It is noteworthy that while the algorithmic procedure of our algorithm is apparently similar to boosting, it is derived from an essentially different formulation and thus differs in several key technical aspects. We tested the proposed method on three large datasets, and observed substantial improvement over the state of the art, including L 2 Boost, an effective method based on boosting.

Locally Linear Support Vector Machine (LLSVM) has been actively used in classification tasks due to its capability of classifying nonlinear patterns. However, existing LLSVM suffers from two drawbacks: (1) a particular and appropriate regularization for LLSVM has not yet been addressed; (2) it usually adopts a three-stage learning scheme composed of learning anchor points by clustering, learning local coding coordinates by a predefined coding scheme, and finally learning for training classifiers. We argue that this decoupled approaches oversimplifies the original optimization problem, resulting in a large deviation due to the disparate purpose of each step. To address the first issue, we propose a novel diversified regularization which could capture infrequent patterns and reduce the model size without sacrificing the representation power. Based on this regularization, we develop a joint optimization algorithm among anchor points, local coding coordinates and classifiers to simultaneously minimize the overall classification risk, which is termed as Diversified and Unified Locally Linear Support Vector Machine (DU-LLSVM for short). To the best of our knowledge, DU-LLSVM is the first principled method that directly learns sparse local coding and can be easily generalized to other supervised learning models. Extensive experiments showed that DU-LLSVM consistently surpassed several state-of-the-art methods with a predefined local coding scheme (e.g. LLSVM) or a supervised anchor point learning (e.g. SAPL-LLSVM).

Link prediction in social networks is to infer the new links likely to be formed next or to reconstruct the links that are currently missing. Other than the pure topological network structures, social networks are often associated with rich information of social activities of users, such as tweeting, retweeting, and replying. Social theories such as social influence indicate that social activities could have potential impacts on the neighbors, and links in social media could be the results of the social influence among users. It motivates us to learn and model social influence among users to tackle the link prediction problem. However, this is a non-trivial task since it is challenging to model heterogeneous social activities. Traditional methods often define universal metrics of social influence for all users, but even for the same activity of a user, the influence towards different neighbors might not be the same. It motivates a personalized learning schema. In information theory, if a time-series signal influences another, then the uncertainty in the latter one will be reduced, given the distribution of the former one. Thus, we are motivated to learn social influence based on the timestamps of social activities. Given the timestamps of each user, we use entropy to measure the reduction of uncertainty of his/her neighbors. The learned social influence is then incorporated into a graph based link prediction model to perform joint learning. Through comprehensive experiments, we demonstrate that the proposed framework can perform better than the state-of-the-art methods on different real-world networks.

In the past decade, various sparse learning based unsupervised feature selection methods have been developed. However, most existing studies adopt a two-step strategy, i.e., selecting the top-m features according to a calculated descending order and then performing K-means clustering, resulting in a group of sub-optimal features. To address this problem, we propose a Dependence Guided Unsupervised Feature Selection (DGUFS) method to select features and partition data in a joint manner. Our proposed method enhances the inter-dependence among original data, cluster labels, and selected features. In particular, a projection-free feature selection model is proposed based on l20-norm equality constraints. We utilize the learned cluster labels to fill in the information gap between original data and selected features. Two dependence guided terms are consequently proposed for our model. More specifically, one term increases the dependence of desired cluster labels on original data, while the other term maximizes the dependence of selected features on cluster labels to guide the process of feature selection. Last but not least, an iterative algorithm based on Alternating Direction Method of Multipliers (ADMM) is designed to solve the constrained minimization problem efficiently. Extensive experiments on different datasets consistently demonstrate that our proposed method significantly outperforms state-of-the-art baselines.

Representation-based classification methods such as sparse representation-based classification (SRC) and linear regression classification (LRC) have attracted a lot of attentions. In order to obtain the better representation, a novel method called projection representation-based classification (PRC) is proposed for image recognition in this paper. PRC is based on a new mathematical model. This model denotes that the "ideal projection" of a sample point x on the hyper-space H may be gained by iteratively computing the projection of x on a line of hyper-space H with the proper strategy. Therefore, PRC is able to iteratively approximate the "ideal representation" of each subject for classification. Moreover, the discriminant PRC (DPRC) is further proposed, which obtains the discriminant information by maximizing the ratio of the between-class reconstruction error over the within-class reconstruction error. Experimental results on five typical databases show that the proposed PRC and DPRC are effective and outperform other state-of-the-art methods on several vision recognition tasks.

Urban air pollution has attracted much attention these years for its adverse impacts on human health. While monitoring stations have been established to collect pollutant statistics, the number of stations is very limited due to the high cost. Thus, inferring fine-grained urban air quality information is becoming an essential issue for both government and people. In this paper, we propose a generic neural approach, named ADAIN, for urban air quality inference. We leverage both the information from monitoring stations and urban data that are closely related to air quality, including POIs, road networks and meteorology. ADAIN combines feedforward and recurrent neural networks for modeling static and sequential features as well as capturing deep feature interactions effectively. A novel attempt of ADAIN is an attention-based pooling layer that automatically learns the weights of features from different monitoring stations, to boost the performance. We conduct experiments on a real-world air quality dataset and our approach achieves the highest performance compared with various state-of-the-art solutions.

We propose a tensor-based approach to analyze multi-dimensional data describing sample subjects. It simultaneously discovers patterns in features and reveals past temporal points that have impact on current outcomes. The model coefficient, a k-mode tensor, is decomposed into a summation of k tensors of the same dimension. To accomplish feature selection, we introduce the tensor '"atent L F,1 norm" as a grouped penalty in our formulation. Furthermore, the proposed model takes into account within-subject correlations by developing a tensor-based quadratic inference function. We provide an asymptotic analysis of our model when the sample size approaches to infinity. To solve the corresponding optimization problem, we develop a linearized block coordinate descent algorithm and prove its convergence for a fixed sample size. Computational results on synthetic datasets and real-file fMRI and EEG problems demonstrate the superior performance of the proposed approach over existing techniques.

According to (Zhang et Though compressive community sensing can effectively al. 2014a), there are two major roles in community sensing reduce the required incentives and participants, it still aggregates - the organizer and the participants - where the former is the real-time location and sensor data from each the individual or organization that creates the sensing task, participant, so as to first identify the covered subareas, fill recruits participants and collects the sensor data, while the with collected data, and then recover the missing data for latter (i.e., participants) involve in the sensing task and provide the rest. To protect the location privacy of participants, the the sensing data. Frequently, the organizer pursues a same of group of researchers (Wang et al. 2017a; 2016b) proposed high (or even full) spatial-temporal coverage of the collected to leverage the Differential Geo-Obfuscation to replace sensor data. However incentives (e.g., monetary rewards) and each participants' real-time location with a "mock" location the threats to privacy (e.g., exposing real-time locations) are while insuring the recovery accuracy. With the Differential two major concerns that may affect the willingness of the Geo-Obfuscation, the participants' locations are expected to participants to join a community sensing task.

In this paper, we consider the problem of fair statistical inference involving outcome variables. Examples include classification and regression problems, and estimating treatment effects in randomized trials or observational data. The issue of fairness arises in such problems where some covariates or treatments are "sensitive," in the sense of having potential of creating discrimination. In this paper, we argue that the presence of discrimination can be formalized in a sensible way as the presence of an effect of a sensitive covariate on the outcome along certain causal pathways, a view which generalizes (Pearl 2009). A fair outcome model can then be learned by solving a constrained optimization problem. We discuss a number of complications that arise in classical statistical inference due to this view and provide workarounds based on recent work in causal and semi-parametric inference.

We present a system for covert automated deception detection using information available in a video. We study the importance of different modalities like vision, audio and text for this task. On the vision side, our system uses classifiers trained on low level video features which predict human micro-expressions. We show that predictions of high-level micro-expressions can be used as features for deception prediction. Surprisingly, IDT (Improved Dense Trajectory) features which have been widely used for action recognition, are also very good at predicting deception in videos. We fuse the score of classifiers trained on IDT features and high-level micro-expressions to improve performance. MFCC (Mel-frequency Cepstral Coefficients) features from the audio domain also provide a significant boost in performance, while information from transcripts is not very beneficial for our system. Using various classifiers, our automated system obtains an AUC of 0.877 (10-fold cross-validation) when evaluated on subjects which were not part of the training set. Even though state-of-the-art methods use human annotations of micro-expressions for deception detection, our fully automated approach outperforms them by 5%. When combined with human annotations of micro-expressions, our AUC improves to 0.922. We also present results of a user-study to analyze how well do average humans perform on this task, what modalities they use for deception detection and how they perform if only one modality is accessible.