Search

The choice of learning rate (LR) functions and policies has evolved from a simple fixed LR to the decaying LR and the cyclic LR, aiming to improve the accuracy and reduce the training time of Deep Neural Networks (DNNs). This article presents a systematic approach to selecting and composing an LR policy for effective DNN training to meet desired target accuracy and reduce training time within the pre-defined training iterations. It makes three original contributions. First, we develop an LR tuning mechanism for auto-verification of a given LR policy with respect to the desired accuracy goal under the pre-defined training time constraint. Second, we develop an LR policy recommendation system (LRBench) to select and compose good LR policies from the same and/or different LR functions through dynamic tuning, and avoid bad choices, for a given learning task, DNN model, and dataset. Third, we extend LRBench by supporting different DNN optimizers and show the significant mutual impact of different LR policies and different optimizers. Evaluated using popular benchmark datasets and different DNN models (LeNet, CNN3, ResNet), we show that our approach can effectively deliver high DNN test accuracy, outperform the existing recommended default LR policies, and reduce the DNN training time by 1.6-6.7× to meet a targeted model accuracy. [ABSTRACT FROM AUTHOR]

Traditional recommendation systems are faced with two long-standing obstacles, namely data sparsity and cold-start problems, which promote the emergence and development of Cross-Domain Recommendation (CDR). The core idea of CDR is to leverage information collected from other domains to alleviate the two problems in one domain. Since the early 2010s, many efforts have been engaged for cross-domain recommendation. Recently, with the development of deep learning and neural networks, a large number of methods have emerged. However, there is a limited number of systematic surveys on CDR, especially regarding the latest proposed methods as well as the recommendation scenarios and recommendation tasks they address. In this survey article, we first proposed a two-level taxonomy of cross-domain recommendation that classifies different recommendation scenarios and recommendation tasks. We then introduce and summarize existing cross-domain recommendation approaches under different recommendation scenarios in a structured manner. We also organize datasets commonly used. We conclude this survey by providing several potential research directions about this field. [ABSTRACT FROM AUTHOR]

In recommender systems, top-N recommendation is an important task with implicit feedback data. Although the recent success of deep learning largely pushes forward the research on top-N recommendation, there are increasing concerns on appropriate evaluation of recommendation algorithms. It therefore is important to study how recommendation algorithms can be reliably evaluated and thoroughly verified. This work presents a large-scale, systematic study on six important factors from three aspects for evaluating recommender systems. We carefully select 12 top-N recommendation algorithms and eight recommendation datasets. Our experiments are carefully designed and extensively conducted with these algorithms and datasets. In particular, all the experiments in our work are implemented based on an open sourced recommendation library, Recbole [139], which ensures the reproducibility and reliability of our results. Based on the large-scale experiments and detailed analysis, we derive several key findings on the experimental settings for evaluating recommender systems. Our findings show that some settings can lead to substantial or significant differences in performance ranking of the compared algorithms. In response to recent evaluation concerns, we also provide several suggested settings that are specially important for performance comparison. [ABSTRACT FROM AUTHOR]

The sequential recommendation (also known as the next-item recommendation), which aims to predict the following item to recommend in a session according to users’ historical behavior, plays a critical role in improving session-based recommender systems. Most of the existing deep learning-based approaches utilize the recurrent neural network architecture or self-attention to model the sequential patterns and temporal influence among a user’s historical behavior and learn the user’s preference at a specific time. However, these methods have two main drawbacks. First, they focus on modeling users’ dynamic states from a user-centric perspective and always neglect the dynamics of items over time. Second, most of them deal with only the first-order user-item interactions and do not consider the high-order connectivity between users and items, which has recently been proved helpful for the sequential recommendation. To address the above problems, in this article, we attempt to model user-item interactions by a bipartite graph structure and propose a new recommendation approach based on a Position-enhanced and Time-aware Graph Convolutional Network (PTGCN) for the sequential recommendation. PTGCN models the sequential patterns and temporal dynamics between user-item interactions by defining a position-enhanced and time-aware graph convolution operation and learning the dynamic representations of users and items simultaneously on the bipartite graph with a self-attention aggregator. Also, it realizes the high-order connectivity between users and items by stacking multi-layer graph convolutions. To demonstrate the effectiveness of PTGCN, we carried out a comprehensive evaluation of PTGCN on three real-world datasets of different sizes compared with a few competitive baselines. Experimental results indicate that PTGCN outperforms several state-of-the-art sequential recommendation models in terms of two commonly-used evaluation metrics for ranking. In particular, it can make a better trade-off between recommendation performance and model training efficiency, which holds great potential for online session-based recommendation scenarios in the future. [ABSTRACT FROM AUTHOR]

Point-of-Interest recommendation is an area of increasing research and development interest within the widely adopted technologies known as Recommender Systems. Among them, those that exploit informa)tion coming from Location-Based Social Networks are very popular nowadays and could work with different information sources, which pose several challenges and research questions to the community as a whole. We present a systematic review focused on the research done over the past 10 years about this topic. We discuss and categorize the algorithms and evaluation methodologies used in these works and point out the opportuni)ties and challenges that remain open in the field. More specifically, we report on the leading recommendation techniques and information sources that have been exploited more often (such as the geographical signal and deep learning approaches) while we also examine the lack of reproducibility in the field that may hinder real performance improvements. [ABSTRACT FROM AUTHOR]

As the deep learning techniques have expanded to real-world recommendation tasks, many deep neural network based Collaborative Filtering (CF) models have been developed to project user-item interactions into latent feature space, based on various neural architectures, such as multi-layer perceptron, autoencoder, and graph neural networks. However, the majority of existing collaborative filtering systems are not well designed to handle missing data. Particularly, in order to inject the negative signals in the training phase, these solutions largely rely on negative sampling from unobserved user-item interactions and simply treating them as negative instances, which brings the recommendation performance degradation. To address the issues, we develop a Collaborative Reflection-Augmented Autoencoder Network (CRANet), that is capable of exploring transferable knowledge from observed and unobserved user-item interactions. The network architecture of CRANet is formed of an integrative structure with a reflective receptor network and an information fusion autoencoder module, which endows our recommendation framework with the ability of encoding implicit user’s pairwise preference on both interacted and non-interacted items. Additionally, a parametric regularizationbased tied-weight scheme is designed to perform robust joint training of the two-stage CRANet model. We finally experimentally validate CRANet on four diverse benchmark datasets corresponding to two recommendation tasks, to show that debiasing the negative signals of user-item interactions improves the performance as compared to various state-of-the-art recommendation techniques. [ABSTRACT FROM AUTHOR]

Vehicle mobility optimization in urban areas is a long-standing problem in smart city and spatial data analysis. Given the complex urban scenario and unpredictable social events, our work focuses on developing a mobile sequential recommendation system to maximize the profitability of vehicle service providers (e.g., taxi drivers). In particular, we treat the dynamic route optimization problem as a long-term sequential decision-making task. A reinforcement-learning framework is proposed to tackle this problem, by integrating a self-check mechanism and a deep neural network for customer pick-up point monitoring. To account for unexpected situations (e.g., the COVID-19 outbreak), our method is designed to be capable of handling related environment changes with a self-adaptive parameter determination mechanism. Based on the yellow taxi data in New York City and vicinity before and after the COVID-19 outbreak, we have conducted comprehensive experiments to evaluate the effectiveness of our method. The results show consistently excellent performance, from hourly to weekly measures, to support the superiority of our method over the state-of-the-art methods (i.e., with more than 98% improvement in terms of the profitability for taxi drivers). [ABSTRACT FROM AUTHOR]

A comprehensive artificial intelligence system needs to not only perceive the environment with different "senses" (e.g., seeing and hearing) but also infer the world's conditional (or even causal) relations and corresponding uncertainty. The past decade has seen major advances in many perception tasks, such as visual object recognition and speech recognition, using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. In recent years, Bayesian deep learning has emerged as a unified probabilistic framework to tightly integrate deep learning and Bayesian models.1 In this general framework, the perception of text or images using deep learning can boost the performance of higher-level inference and, in turn, the feedback from the inference process is able to enhance the perception of text or images. This survey provides a comprehensive introduction to Bayesian deep learning and reviews its recent applications on recommender systems, topic models, control, and so on. We also discuss the relationship and differences between Bayesian deep learning and other related topics, such as Bayesian treatment of neural networks. [ABSTRACT FROM AUTHOR]

Recommender systems have become a popular and effective means to manage the ever-increasing amount of multimedia content available today and to help users discover interesting new items. Today's recommender systems suggest items of various media types, including audio, text, visual (images), and videos. In fact, scientific research related to the analysis of multimedia content has made possible effective content-based recommender systems capable of suggesting items based on an analysis of the features extracted from the item itself. The aim of this survey is to present a thorough review of the state-of-the-art of recommender systems that leverage multimedia content, by classifying the reviewed papers with respect to their media type, the techniques employed to extract and represent their content features, and the recommendation algorithm. Moreover, for each media type, we discuss various domains in which multimedia content plays a key role in human decision-making and is therefore considered in the recommendation process. Examples of the identi- fied domains include fashion, tourism, food, media streaming, and e-commerce. [ABSTRACT FROM AUTHOR]

The design of algorithms that generate personalized ranked item lists is a central topic of research in the field of recommender systems. In the past fewyears, in particular, approaches based on deep learning (neural) techniques have become dominant in the literature. For all of them, substantial progress over the state-of-the-art is claimed. However, indications exist of certain problems in today's research practice, e.g., with respect to the choice and optimization of the baselines used for comparison, raising questions about the published claims. To obtain a better understanding of the actual progress, we have compared recent results in the area of neural recommendation approaches based on collaborative filtering against a consistent set of existing simple baselines. The worrying outcome of the analysis of these recent works--all were published at prestigious scientific conferences between 2015 and 2018--is that 11 of the 12 reproducible neural approaches can be outperformed by conceptually simple methods, e.g., based on the nearest-neighbor heuristic or linear models. None of the computationally complex neural methods was actually consistently better than already existing learning-based techniques, e.g., using matrix factorization or linear models. In our analysis, we discuss common issues in today's research practice, which, despite the many papers that are published on the topic, have apparently led the field to a certain level of stagnation. [ABSTRACT FROM AUTHOR]

With the dramatic expansion of international markets, consumers write reviews in different languages, which poses a new challenge for Recommender Systems (RSs) dealing with this increasing amount of multilingual information. Recent studies that leverage deep-learning techniques for review-aware RSs have demonstrated their effectiveness in modelling fine-grained user-item interactions through the aspects of reviews. However, most of these models can neither take full advantage of the contextual information from multilingual reviews nor discriminate the inherent ambiguity of words originated from the user's different tendency in writing. To this end, we propose a novel Multilingual Review-aware Deep Recommendation Model (MrRec) for rating prediction tasks. MrRec mainly consists of two parts: (1) Multilingual aspect-based sentiment analysis module (MABSA), which aims to jointly extract aligned aspects and their associated sentiments in different languages simultaneously with only requiring overall review ratings. (2) Multilingual recommendation module that learns aspect importances of both the user and item with considering different contributions of multiple languages and estimates aspect utility via a dual interactive attention mechanism integrated with aspect-specific sentiments from MABSA. Finally, overall ratings can be inferred by a prediction layer adopting the aspect utility value and aspect importance as inputs. Extensive experimental results on nine real-world datasets demonstrate the superior performance and interpretability of our model. [ABSTRACT FROM AUTHOR]

Recommender systems play an important role in providing personalized services for users in the context of information overload. Generally, users' feedback toward items often contain the most significant information reflecting their preferences, which enables accurate personalized recommendation. In real applications, users' feedback are usually heterogeneous (rather than homogeneous) such as purchases and examinations in e-commerce, which reflects users' preferences in different degrees. Effective modeling of such heterogeneous one-class feedback is challenging comparedwith that of homogeneous feedback of ratings. As a response, heterogeneous one-class collaborative filtering (HOCCF) is proposed, which often converts the heterogeneous feedback into two parts (i.e., target feedback and auxiliary feedback), aiming to care more about the target feedback (e.g., purchases) with the assistance of the auxiliary feedback (e.g., examinations). In this survey, we provide an overview of the representative HOCCF methods fromthe perspective of factorization-based methods, transfer learning-based methods, and deep learning-based methods. First, we review the factorizationbased methods according to different strategies. Second, we describe the transfer learning-based methods with different knowledge sharing manners. Third, we discuss the deep learning-based methods according to the neural architectures. Moreover, we include some important example applications, describe the empirical studies, and discuss some promising future directions. [ABSTRACT FROM AUTHOR]

Recommendation systems play a vital role to keep users engaged with personalized contents in modern online platforms. Recently, deep learning has revolutionized many research fields and there is a surge of interest in applying it for recommendation. However, existing studies have largely focused on exploring complex deeplearning architectures for recommendation task, while typically applying the negative sampling strategy for model learning. Despite effectiveness, we argue that these methods suffer from two important limitations: (1) the methods with complex network structures have a substantial number of parameters, and require expensive computations even with a sampling-based learning strategy; (2) the negative sampling strategy is not robust, making sampling-based methods difficult to achieve the optimal performance in practical applications. In this work, we propose to learn neural recommendation models from the whole training data without sampling. However, such a non-sampling strategy poses strong challenges to learning efficiency. To address this, we derive three new optimization methods through rigorous mathematical reasoning, which can efficiently learn model parameters from the whole data (including all missing data) with a rather low time complexity. Moreover, based on a simple Neural Matrix Factorization architecture, we present a general framework named ENMF, short for Efficient Neural Matrix Factorization. Extensive experiments on three real-world public datasets indicate that the proposed ENMF framework consistently and significantly outperforms the state-of-the-art methods on the Top-K recommendation task. Remarkably, ENMF also shows significant advantages in training efficiency, which makes it more applicable to real-world large-scale systems. [ABSTRACT FROM AUTHOR]

With the growing volume of online information, recommender systems have been an effective strategy to overcome information overload. The utility of recommender systems cannot be overstated, given their widespread adoption in many web applications, along with their potential impact to ameliorate many problems related to over-choice. In recent years, deep learning has garnered considerable interest in many research fields such as computer vision and natural language processing, owing not only to stellar performance but also to the attractive property of learning feature representations from scratch. The influence of deep learning is also pervasive, recently demonstrating its effectiveness when applied to information retrieval and recommender systems research. The field of deep learning in recommender system is flourishing. This article aims to provide a comprehensive review of recent research efforts on deep learning-based recommender systems. More concretely, we provide and devise a taxonomy of deep learning-based recommendation models, along with a comprehensive summary of the state of the art. Finally, we expand on current trends and provide new perspectives pertaining to this new and exciting development of the field. [ABSTRACT FROM AUTHOR]

User response prediction is a crucial component for personalized information retrieval and filtering scenarios, such as recommender system and web search. The data in user response prediction is mostly in a multi-field categorical format and transformed into sparse representations via one-hot encoding. Due to the sparsity problems in representation and optimization, most research focuses on feature engineering and shallow modeling. Recently, deep neural networks have attracted research attention on such a problem for their high capacity and end-to-end training scheme. In this article, we study user response prediction in the scenario of click prediction.We first analyze a coupled gradient issue in latent vector-based models and propose kernel product to learn field-aware feature interactions. Then, we discuss an insensitive gradient issue in DNN-based models and propose Product-based Neural Network, which adopts a feature extractor to explore feature interactions. Generalizing the kernel product to a net-in-net architecture,we further propose Productnetwork in Network (PIN), which can generalize previous models. Extensive experiments on four industrial datasets and one contest dataset demonstrate that ourmodels consistently outperform eight baselines on both area under curve and log loss. Besides, PIN makes great click-through rate improvement (relatively 34.67%) in online A/B test. [ABSTRACT FROM AUTHOR]

Integrating external knowledge into the recommendation system has attracted increasing attention in both industry and academic communities. Recent methods mostly take the power of neural network for effective knowledge representation to improve the recommendation performance. However, the heavy deep architectures in existing models are usually incorporated in an embedded manner, which may greatly increase the model complexity and lower the runtime efficiency. To simultaneously take the power of deep learning for external knowledge modeling as well as maintaining the model efficiency at test time, we reformulate the problem of recommendation with external knowledge into a generalized distillation framework. The general idea is to free the complex deep architecture into a separate model, which is only used in the training phrase, while abandoned at test time. In particular, in the training phrase, the external knowledge is processed by a comprehensive teacher model to produce valuable information to teach a simple and efficient student model. Once the framework is learned, the teacher model is abandoned, and only the succinct yet enhanced student model is used to make fast predictions at test time. In this article, we specify the external knowledge as user review, and to leverage it in an effective manner, we further extend the traditional generalized distillation framework by designing a Selective Distillation Network (SDNet) with adversarial adaption and orthogonality constraint strategies to make it more robust to noise information. Extensive experiments verify that our model can not only improve the performance of rating prediction, but also can significantly reduce time consumption when making predictions as compared with several stateof- the-art methods. [ABSTRACT FROM AUTHOR]