Search

Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in the recommender systems. Recently, some deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. In these work, the attention mechanism is used to select the user interested items in historical behaviors, improving the performance of the CTR predictor. Normally, these attentive modules can be jointly trained with the base predictor by using gradient descents. In this paper, we regard user interest modeling as a feature selection problem, which we call user interest selection. For such a problem, we propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper. More specifically, we use a differentiable module as our wrapping operator and then recast its learning problem as a continuous bilevel optimization. Moreover, we use a meta-learning algorithm to solve the optimization and theoretically prove its convergence. Meanwhile, we also provide theoretical analysis to show that our proposed method 1) efficiencies the wrapper-based feature selection, and 2) achieves better resistance to overfitting. Finally, extensive experiments on three public datasets manifest the superiority of our method in boosting the performance of CTR prediction. [ABSTRACT FROM AUTHOR]

The wide deployment of advanced robots with industrial IoT (IIoT) technologies in smart factories generates a large volume of data during production and a wide variety of data processing workloads are launched to maintain productivity and safety of smart manufacture. The emerging fog computing paradigm offers a promising solution to enhancing data processing performance in a smart factory environment while on the other hand brings in new challenges to resource management, which call for a more effective approach for recommending resource configurations to heterogeneous workloads. In this paper, we propose an Optimized Recommendations of Heterogeneous Resource Configurations (ORHRC) model that employs machine learning techniques to provide resource configuration recommendations for the heterogeneous workloads in a fog computing-based smart factory environment. ORHRC learns a recommendation model by leveraging the operating characteristics and execution time of workloads on fog servers with different configurations. We also design a decision model in ORHRC to further improve prediction accuracy and reduce operational overheads. Experiment results show that ORHRC outperforms the state of art configuration recommendation methods in terms of average prediction accuracy. Note to Practitioners—The various data processing workloads in a smart factory environment need to be processed by the computational resources with optimal configurations for meeting their performance requirements. In this paper, we employ machine learning technologies for enabling automatic recommendation of resource configurations to heterogeneous workloads. Specifically, we develop an Optimized Recommendations of Heterogeneous Resource Configurations (ORHRC) model that can identify the optimal resource configurations for various workloads. We also conducted extensive experiments that verify the effectiveness of the proposed ORHRC model. [ABSTRACT FROM AUTHOR]

Machine learning can provide deep insights into data, allowing machines to make high-quality predictions and having been widely used in real-world applications, such as text mining, visual classification, and recommender systems. However, most sophisticated machine learning approaches suffer from huge time costs when operating on large-scale data. This issue calls for the need of Large-scale Machine Learning (LML), which aims to learn patterns from big data with comparable performance efficiently. In this paper, we offer a systematic survey on existing LML methods to provide a blueprint for the future developments of this area. We first divide these LML methods according to the ways of improving the scalability: 1) model simplification on computational complexities, 2) optimization approximation on computational efficiency, and 3) computation parallelism on computational capabilities. Then we categorize the methods in each perspective according to their targeted scenarios and introduce representative methods in line with intrinsic strategies. Lastly, we analyze their limitations and discuss potential directions as well as open issues that are promising to address in the future. [ABSTRACT FROM AUTHOR]

Tremendous success of machine learning (ML) and the unabated growth in model complexity motivated many ML-specific designs in hardware architectures to speed up the model inference. While these architectures are diverse, highly optimized low-precision arithmetic is a component shared by most. Nevertheless, recommender systems important to Facebook's personalization services are demanding and complex: They must serve billions of users per month responsively with low latency while maintaining high prediction accuracy. Do these low-precision architectures work well with our production recommendation systems? They do. But not without significant effort. In this article, we share our search strategies to adapt reference recommendation models to low-precision hardware, our optimization of low-precision compute kernels, and the tool chain to maintain our models' accuracy throughout their lifespan. We believe our lessons from the trenches can promote better codesign between hardware architecture and software engineering, and advance the state of the art of ML in industry. [ABSTRACT FROM AUTHOR]

Predictive resource allocation (PRA) can leverage machine learning and historical data to boost the performance of mobile networks, say to support high throughput or improve the quality of service. While the large gain of PRA has been demonstrated by assuming perfect prediction or by optimizing with modeled prediction errors, how the prediction errors translate to the performance loss of PRA and how the future information should be predicted are not well understood. In this paper, we consider high throughput PRA policy for non-real-time (NRT) mobile users when the base stations also serve real-time (RT) users, where the future average rates of NRT users in a prediction window need to be predicted. The average rate can be predicted in various ways, where one typical way is to predict the rate directly from the historical average rates and another typical way is to predict the rate indirectly by first predicting traffic load and user trajectory. Given that the traffic load and user location can be gathered easily in cellular networks, we consider such an indirect prediction and analyze the impact of prediction errors of traffic load and trajectory on the prediction errors of average data rate. To this end, we first find the relation between the RT traffic load and the residual bandwidth after serving the RT users by resorting to effective capacity and effective bandwidth theory. To further justify why we analyze the indirect prediction, we compare the predictability of the time series used for the typical direct prediction and indirect prediction with entropy theory. Since different machine learning techniques lead to different prediction bias and prediction error variance, we then derive the relation between the prediction error statistics of the average data rate and those of traffic load and trajectory. We evaluate the performance loss of PRA using both modeled prediction errors and real predictions with deep learning. Our analyses show that for a network busy with RT service, the prediction errors of RT traffic load have larger impact on those of average data rate than the prediction errors of trajectory. The prediction bias has a larger impact on the throughput loss of PRA than the prediction error variance. This provides a guidance of designing learning techniques for predicting the required information. [ABSTRACT FROM AUTHOR]

Human mobility prediction techniques are instrumental for many important applications including service management and city planning. Previous work looks at the inherent patterns of a user's historical trajectories to predict his/her future location. Such method suffers when only a small number of historical locations are available, which is a main challenge for mobility prediction on sparse trajectory datasets. In this paper, we propose a multi-task learning based algorithm to predict users’ mobility by learning the mobility behaviors of different users at the same time and exploiting the similarities among them to overcome the sparse issue and improve the prediction performance. Specifically, we use a Bayesian mixture model to describe users’ spatio-temporal mobility patterns, where we introduce a novel von Mises distribution to model the temporal distribution of users’ mobility to better preserve its continuity across time. Then, we use the hierarchical Dirichlet process to perform joint prediction of all users’ mobility. This model allows us to leverage similar mobility patterns among users to improve the prediction performance for users with sparse trajectory data. We conduct extensive evaluations using data collected by a cellular network operator and mobile applications. Our evaluations show that our algorithms achieve prediction accuracy of 53.9% on average and 73.2% for users with high-quality mobility data, with the performance gap over 8.7% on average compared with the state-of-the-art algorithms, demonstrating the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

Item-to-item collaborative filtering (aka.item-based CF) has been long used for building recommender systems in industrial settings, owing to its interpretability and efficiency in real-time personalization. It builds a user's profile as her historically interacted items, recommending new items that are similar to the user's profile. As such, the key to an item-based CF method is in the estimation of item similarities. Early approaches use statistical measures such as cosine similarity and Pearson coefficient to estimate item similarities, which are less accurate since they lack tailored optimization for the recommendation task. In recent years, several works attempt to learn item similarities from data, by expressing the similarity as an underlying model and estimating model parameters by optimizing a recommendation-aware objective function. While extensive efforts have been made to use shallow linear models for learning item similarities, there has been relatively less work exploring nonlinear neural network models for item-based CF. In this work, we propose a neural network model namedNeural Attentive Item Similarity model(NAIS) for item-based CF. The key to our design of NAIS is an attention network, which is capable of distinguishing which historical items in a user profile are more important for a prediction. Compared to the state-of-the-art item-based CF methodFactored Item Similarity Model(FISM) , our NAIS has stronger representation power with only a few additional parameters brought by the attention network. Extensive experiments on two public benchmarks demonstrate the effectiveness of NAIS. This work is the first attempt that designs neural network models for item-based CF, opening up new research possibilities for future developments of neural recommender systems. [ABSTRACT FROM AUTHOR]

Most of the previous studies on the user preferences assume that there is a personal transitive preference ranking of the consumable media like images. For example, the transitivity of preferences is one of the most important assumptions in the recommender system research. However, the intransitive relations have also been widely observed, such as the win/loss relations in online video games, in sport matches, and even in rock–paper–scissors games. It is also found that different subjects demonstrate the personalized intransitive preferences in the pairwise comparisons between the applicants for college admission. Since the intransitivity of preferences on images has barely been studied before and has a large impact on the research of personalized image search and recommendation, it is necessary to propose a novel method to predict the personalized intransitive preferences of images. In this paper, we propose the novel Multi-Criterion preference (MuCri) models to predict the intransitive relations in the image preferences. The MuCri models utilize different kinds of image content features as well as the latent features of users and images. Meanwhile, a new data set is constructed in this paper, in order to evaluate the performance of the MuCri models. The experimental evaluation shows that the MuCri models outperform all the baselines. Due to the interdisciplinary nature of this topic, we believe it would widely attract the attention of researchers in the image processing community as well as in other communities, such as machine learning, multimedia, and recommender system. [ABSTRACT FROM AUTHOR]

Personalized review-based rating prediction, a newly emerged research problem, aims at inferring users’ ratings over their unrated items using existing reviews and corresponding ratings. While some researchers proposed to learn topic factor from review text to obtain interpretability for rating prediction, they often overlooked the fact that the learned topic factors are limited to review text and cannot fully reveal the complicated relations between reviews and ratings. Moreover, topic modeling based solutions for this problem usually utilize Gibbs sampling algorithms to learn topics and word distributions, resulting in non-negligible computational overload. To address the above challenges, we propose an integrated topic and latent factor model (ITLFM), which combines topic and latent factors in a linear way to make them complement each other for better accuracies in rating prediction tasks. In addition, ITLFM models review text through an additive topic model to reveal user's and item's topic factors simultaneously. To ensure high learning efficiency, we design a hybrid stochastic learning algorithm for ITLFM. We evaluate ITLFM on several standard benchmarks and compare with representative approaches. The experimental results demonstrate that the proposed ITLFM method is computationally efficient and accurate, as well as scalable for large scale applications. [ABSTRACT FROM PUBLISHER]

A social recommendation system has attracted a lot of attention recently in the research communities of information retrieval, machine learning, and data mining. Traditional social recommendation algorithms are often based on batch machine learning methods which suffer from several critical limitations, e.g., extremely expensive model retraining cost whenever new user ratings arrive, unable to capture the change of user preferences over time. Therefore, it is important to make social recommendation system suitable for real-world online applications where data often arrives sequentially and user preferences may change dynamically and rapidly. In this paper, we present a new framework of online social recommendation from the viewpoint of online graph regularized user preference learning (OGRPL), which incorporates both collaborative user-item relationship as well as item content features into an unified preference learning process. We further develop an efficient iterative procedure, OGRPL-FW which utilizes the Frank-Wolfe algorithm, to solve the proposed online optimization problem. We conduct extensive experiments on several large-scale datasets, in which the encouraging results demonstrate that the proposed algorithms obtain significantly lower errors (in terms of both RMSE and MAE) than the state-of-the-art online recommendation methods when receiving the same amount of training data in the online learning process. [ABSTRACT FROM PUBLISHER]