scholarly journals Blind compressive sensing formulation incorporating metadata for recommender system design

2015 ◽  
Vol 4 ◽  
Author(s):  
Anupriya Gogna ◽  
Angshul Majumdar
Keyword(s):  
Factor Model ◽  
Auxiliary Information ◽  
Dense Matrix ◽  
Latent Factors ◽  
Latent Factor ◽  
Sparsity Pattern ◽  
Additional Information ◽  
Dense Matrices ◽  
Design Result

Standard techniques in matrix factorization (MF) – a popular method for latent factor model-based design – result in dense matrices for both users and items. Users are likely to have some affinity toward all the latent factors – making a dense matrix plausible, but it is not possible for the items to possess all the latent factors simultaneously; hence it is more likely to be sparse. Therefore, we propose to factor the rating matrix into a dense user matrix and a sparse item matrix, leading to the blind compressed sensing (BCS) framework. To further enhance the prediction quality of our design, we aim to incorporate user and item metadata into the BCS framework. The additional information helps in reducing the underdetermined nature of the problem of rating prediction caused by extreme sparsity of the rating dataset. Our design is based on the belief that users sharing similar demographic profile have similar preferences and thus can be described by the similar latent factor vectors. We also use item metadata (genre information) to group together the similar items. We modify our BCS formulation to include item metadata under the assumption that items belonging to common genre share similar sparsity pattern. We also design an efficient algorithm to solve our formulation. Extensive experimentation conducted on the movielens dataset validates our claim that our modified MF framework utilizing auxiliary information improves upon the existing state-of-the-art techniques.

Collaboration Matrix Factorization on Rate and Review for Recommendation

2019 ◽  
Vol 30 (2) ◽  
pp. 27-43
Author(s):  
Zhicheng Wu ◽  
Huafeng Liu ◽  
Yanyan Xu ◽  
Liping Jing
Keyword(s):  
Neural Networks ◽  
Recommender Systems ◽  
Projection Method ◽  
Matrix Factorization ◽  
Auxiliary Information ◽  
Latent Factors ◽  
Latent Factor ◽  
Real World Datasets ◽  
Rating Information

According to the sparseness of rating information, the quality of recommender systems has been greatly restricted. In order to solve this problem, much auxiliary information has been used, such as social networks, review information, and item description. Convolutional neural networks (CNNs) have been widely employed by recommender systems, it greatly improved the rating prediction's accuracy especially when combined with traditional recommendation methods. However, a large amount of research focuses on the consistency between the rating-based latent factor and review-based latent factor. But in fact, these two parts are completely different. In this article, the authors propose a model named collaboration matrix factorization (CMF) that combines a projection method with a convolutional matrix factorization (ConvMF) to extract the collaboration between rating-based latent factors and review-based latent factors that comes from the results of the CNN process. Extensive experiments on three real-world datasets show that the projection method achieves significant improvements over the existing baseline.

scholarly journals DELF: A Dual-Embedding based Deep Latent Factor Model for Recommendation

2018 ◽  
Author(s):  
Weiyu Cheng ◽  
Yanyan Shen ◽  
Yanmin Zhu ◽  
Linpeng Huang
Keyword(s):  
Network Architecture ◽  
Factor Model ◽  
Factor Models ◽  
Superior Performance ◽  
Implicit Feedback ◽  
Latent Factor ◽  
Latent Factor Model ◽  
Latent Factor Models ◽  
Real World Datasets

Among various recommendation methods, latent factor models are usually considered to be state-of-the-art techniques, which aim to learn user and item embeddings for predicting user-item preferences. When applying latent factor models to recommendation with implicit feedback, the quality of embeddings always suffers from inadequate positive feedback and noisy negative feedback. Inspired by the idea of NSVD that represents users based on their interacted items, this paper proposes a dual-embedding based deep latent factor model named DELF for recommendation with implicit feedback. In addition to learning a single embedding for a user (resp. item), we represent each user (resp. item) with an additional embedding from the perspective of the interacted items (resp. users). We employ an attentive neural method to discriminate the importance of interacted users/items for dual-embedding learning. We further introduce a neural network architecture to incorporate dual embeddings for recommendation. A novel attempt of DELF is to model each user-item interaction with four deep representations that are subtly fused for preference prediction. We conducted extensive experiments on real-world datasets. The results verify the effectiveness of user/item dual embeddings and the superior performance of DELF on item recommendation.

IMPROVING LATENT FACTOR MODEL BASED COLLABORATIVE FILTERING VIA INTEGRATED FOLKSONOMY FACTORS

2011 ◽  
Vol 19 (02) ◽  
pp. 307-327 ◽  
Author(s):  
LUO XIN ◽  
YUANXIN OUYANG ◽  
XIONG ZHANG
Keyword(s):  
Collaborative Filtering ◽  
Matrix Factorization ◽  
Factor Model ◽  
State Of The Art ◽  
Latent Factors ◽  
Latent Factor ◽  
Rating Data ◽  
Latent Factor Model ◽  
Probabilistic Matrix Factorization ◽  
Recommendation Accuracy

Latent Factor Model (LFM) based approaches are becoming popular when implementing Collaborative Filtering (CF) recommenders, due to their high recommendation accuracy. However, current LFM approaches address the accuracy issue only based on the rating data, whereas early research indicates that integrating information from additional data sources is helpful to the recommendation accuracy. In this work we focus on improving the recommendation accuracy of a LFM based CF recommender by integrating folksonomy information. To implement this approach, we first propose a novel model named Item Folsonomy Relevance (IFR) to analyze the item relevance inside the folksonomy; we subsequently integrate the latent factors of the IFR model and rating data through probabilistic matrix factorization (PMF), a state-of-the-art matrix factorization technique, to produce recommendations based on information from both the ratings and folksonomy simultaneously. The experiments on MovieLens dataset showed that compared to two state-of-the-art LFM approaches and another folksonomy-augmented recommder, our approach could obtain advantage in recommendation accuracy.

Integral approach to the quality of life conditioned by health

2011 ◽  
Vol 18 (2) ◽  
pp. 79-85 ◽  
Author(s):  
Algirdas JUOZULYNAS ◽  
Mindaugas BUTIKIS ◽  
Algirdas VENALIS ◽  
Laura NARKAUSKAITĖ ◽  
Antanas JURGELĖNAS
Keyword(s):  
Quality Of Life ◽  
Social Indicators ◽  
Integral Approach ◽  
Modern Concept ◽  
Social Risk ◽  
Latent Factors ◽  
Latent Factor ◽  
Social Construct ◽  
General Dispersion

Background. Currently, there are a lot of methodologies for evaluating the quality of life both in West Europe and in the USA. The majority of them are grounded on the multi-disciplinary, systemic principles. Meanwhile, in some countries and in Lithuania, the studies of the quality of life are more focused on the fields of health and medicine. According to the modern conception of sustainable development, the quality of life is a result of an integral interaction of quality of life indicators. The modern concept of the quality of life is a particular social construct comprising different social dimensions. Materials and methods. A sample of 1 200 persons was formed under the quota of age and gender. Its main point is that the health, social, economic, environmental and age elements of the quality of life comprise an integral, purposeful social system. Statistical analysis was carried out using SPSS 17.0. The data were analyzed using the method of factorial analysis which accounts for the correlations among all indicators. Six latent factors were determined, and they explained 45.55% of the general dispersion. The position of beliefs was determined as the underlying latent factor formed by spiritual and social indicators. This factor explained 10.51% of the general dispersion. Also, in the systematic process, another latent factor – the need for medical services – plays an important role which increases with age, especially in people aged over 50 years. Results. The results showed that at about 50 years all latent factors acquire negative values, i. e. at the age of about 46–50 years the social risk of the quality of life, determined by health, becomes greater. Conclusions. The research helped to determine qualitative changes in the quality of life at the age of 45–50 years when essential changes in the priorities of the quality of life occur in all its domains. Keywords: integral approach, quality of life, social link, integrity

A Latent Factor Model for Forecasting Realized Variances

2020 ◽  
Author(s):  
Giorgio Calzolari ◽  
Roxana Halbleib ◽  
Aygul Zagidullina
Keyword(s):  
Method Of Moments ◽  
Maximum Likelihood Method ◽  
Factor Model ◽  
Real Data ◽  
Likelihood Method ◽  
Latent Factors ◽  
Latent Factor ◽  
Efficient Method Of Moments ◽  
Standard Models ◽  
Parsimonious Model

Abstract This article proposes a parsimonious model to forecast large vectors of realized variances (RVar) by exploiting their common dynamics within a latent factor structure. Their long persistence is captured by aggregating latent factors with AR(1) dynamics. The model has obvious advantages over standard autoregressive models not only in terms of parametrization, but also in terms of efficiency, when increasing the dimension of the vector, as it provides more information on the commonality of the series’ dynamics. The model easily accommodates further empirical features of RVars, such as conditional heteroskedasticity. For estimation purposes, we use the maximum likelihood method based on Kalman filter and the efficient method of moments, both being easy to implement and providing accurate estimates. Our empirical illustration on real data shows that the model we propose often outperforms standard models, most of which are, for vectors of RVar series, only implementable under heavy parametric restrictions.

scholarly journals Latent traits of impulsivity and compulsivity: toward dimensional psychiatry

2017 ◽  
Vol 48 (5) ◽  
pp. 810-821 ◽  
Author(s):  
S. R. Chamberlain ◽  
J. Stochl ◽  
S. A. Redden ◽  
J. E. Grant
Keyword(s):  
Factor Model ◽  
Classification Systems ◽  
Optimal Model ◽  
Cognitive Measures ◽  
Latent Factors ◽  
Underlying Factor ◽  
Confirmatory Factor ◽  
Latent Traits ◽  
Future Work

BackgroundThe concepts of impulsivity and compulsivity are commonly used in psychiatry. Little is known about whether different manifest measures of impulsivity and compulsivity (behavior, personality, and cognition) map onto underlying latent traits; and if so, their inter-relationship.MethodsA total of 576 adults were recruited using media advertisements. Psychopathological, personality, and cognitive measures of impulsivity and compulsivity were completed. Confirmatory factor analysis was used to identify the optimal model.ResultsThe data were best explained by a two-factor model, corresponding to latent traits of impulsivity and compulsivity, respectively, which were positively correlated with each other. This model was statistically superior to the alternative models of their being one underlying factor (‘disinhibition’) or two anticorrelated factors. Higher scores on the impulsive and compulsive latent factors were each significantly associated with worse quality of life (both p < 0.0001).ConclusionsThis study supports the existence of latent functionally impairing dimensional forms of impulsivity and compulsivity, which are positively correlated. Future work should examine the neurobiological and neurochemical underpinnings of these latent traits; and explore whether they can be used as candidate treatment targets. The findings have implications for diagnostic classification systems, suggesting that combining categorical and dimensional approaches may be valuable and clinically relevant.

scholarly journals Additional Information Delivery to Image Content via Improved Unseen–Visible Watermarking

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2186
Author(s):  
Oswaldo Ulises Juarez-Sandoval ◽  
Laura Josefina Reyes-Ruiz ◽  
Francisco Garcia-Ugalde ◽  
Manuel Cedillo-Hernandez ◽  
Jazmin Ramirez-Hernandez ◽  
...  
Keyword(s):  
High Performance ◽  
Auxiliary Information ◽  
Visual Quality ◽  
Error Measurement ◽  
Display Devices ◽  
Additional Information ◽  
Invisible Watermarking ◽  
Visible Watermarking ◽  
Visual Degradation

In a practical watermark scenario, watermarks are used to provide auxiliary information; in this way, an analogous digital approach called unseen–visible watermark has been introduced to deliver auxiliary information. In this algorithm, the embedding stage takes advantage of the visible and invisible watermarking to embed an owner logotype or barcodes as watermarks; in the exhibition stage, the equipped functions of the display devices are used to reveal the watermark to the naked eyes, eliminating any watermark exhibition algorithm. In this paper, a watermark complement strategy for unseen–visible watermarking is proposed to improve the embedding stage, reducing the histogram distortion and the visual degradation of the watermarked image. The presented algorithm exhibits the following contributions: first, the algorithm can be applied to any class of images with large smooth regions of low or high intensity; second, a watermark complement strategy is introduced to reduce the visual degradation and histogram distortion of the watermarked image; and third, an embedding error measurement is proposed. Evaluation results show that the proposed strategy has high performance in comparison with other algorithms, providing a high visual quality of the exhibited watermark and preserving its robustness in terms of readability and imperceptibility against geometric and processing attacks.

Convergent Beam Electron Diffraction

1978 ◽  
Vol 36 (3) ◽  
pp. 304-315
Author(s):  
G. Lehmpfuhl
Keyword(s):  
Electron Diffraction ◽  
Diffraction Pattern ◽  
Crystal Surface ◽  
Diffraction Spot ◽  
Crystal Thickness ◽  
Large Area ◽  
Electron Microscopic ◽  
Additional Information ◽  
Microscopic Investigations

Introduction In electron microscopic investigations of crystalline specimens the direct observation of the electron diffraction pattern gives additional information about the specimen. The quality of this information depends on the quality of the crystals or the crystal area contributing to the diffraction pattern. By selected area diffraction in a conventional electron microscope, specimen areas as small as 1 µ in diameter can be investigated. It is well known that crystal areas of that size which must be thin enough (in the order of 1000 Å) for electron microscopic investigations are normally somewhat distorted by bending, or they are not homogeneous. Furthermore, the crystal surface is not well defined over such a large area. These are facts which cause reduction of information in the diffraction pattern. The intensity of a diffraction spot, for example, depends on the crystal thickness. If the thickness is not uniform over the investigated area, one observes an averaged intensity, so that the intensity distribution in the diffraction pattern cannot be used for an analysis unless additional information is available.

A Psychometric Study of the Quality Perception Questionnaire

2012 ◽  
Vol 71 (2) ◽  
pp. 101-106 ◽  
Author(s):  
Raffaele Cioffi† ◽  
Anna Coluccia ◽  
Fabio Ferretti ◽  
Francesca Lorini ◽  
Aristide Saggino ◽  
...  
Keyword(s):  
Structural Equation ◽  
Factor Model ◽  
Equation Modeling ◽  
Fit Indices ◽  
Quality Perception ◽  
Italian Survey ◽  
Confirmatory Factor ◽  
Instrument Measuring ◽  
Hospital Structures

The present paper reexamines the psychometric properties of the Quality Perception Questionnaire (QPQ), an Italian survey instrument measuring patients’ perceptions of the quality of a recent hospital admission experience, in a sample of 4400 patients (Mage = 56.42 years; SD = 19.71 years, 48.8% females). The 14-item survey measures four factors: satisfaction with medical doctors, nursing staff, auxiliary staff, and hospital structures. First, we tested two models using a confirmatory factor analysis (structural equation modeling): a four orthogonal factor and a four oblique factor model. The SEM fit indices and the χ² difference suggested the acceptance of the second model. We then did a simulation using a bootstrap with 1000 replications. Results confirmed the four oblique factor solution. Third, we tested whether there were significant differences with respect to age or sex. The multivariate general linear model showed no significant differences in the factors with respect to sex or age.

An Event Quality Scale for Participatory Running Events

2020 ◽  
Vol 24 (1) ◽  
pp. 139-152 ◽  
Author(s):  
John Armbrecht
Keyword(s):  
Scale Development ◽  
Service Quality ◽  
Development Process ◽  
Factor Model ◽  
Perceived Quality ◽  
Social Aspects ◽  
Factor Solution ◽  
Quality Scale ◽  
Cognitive Dimensions

This study focuses on the perceived quality of participatory event experiences by addressing the following question: What are the important aspects of the event experience? The aim of this research is to develop and refine a scale to measure the quality of the event experience for runners at a participatory event. The objective is to combine, apply, test, and refine the existing scales to increase our understanding of the perceived quality of events among amateur running athletes. Both affective and cognitive dimensions are included in the scale. Based on seven dimensions and 36 items, a formal scale development process is adopted. The data consist of 1,923 observations collected during a participatory event with approximately 60,000 registered participants. The seven-factor model, including immersion, surprise, participation, fun, social aspects, hedonic aspects, and service quality, was gradually revised in favor of a four-factor solution: service quality, hedonic aspects, fun, and immersion. As a result, 73.1% of the variance is extracted. This study contributes to a refined scale measuring the perceived event quality of participatory events. Service quality accounts for more than half of the variance extracted. Researchers should continue to develop research on the critical experiential dimensions in an event context. Furthermore, the links between the constructs need attention. The results suggest that event organizers should evaluate their events and event portfolios based on the scale and take actions to increase the perceived quality of these events.

Sign in / Sign up

Export Citation Format

Share Document