Search

How to construct imperceptible (realistic) fake samples is critical in adversarial attacks. Due to the sample feature diversity of a recommender system (containing both discrete and continuous features), traditional gradient-based adversarial attack methods may fail to construct realistic fake samples. Meanwhile, most recommendation models adopt click-through rate (CTR) predictors, which usually utilize black-box deep models with discrete features as input. Thus, how to efficiently construct realistic fake samples for black-box recommender systems is still full of challenges. In this article, we propose a hierarchical adversarial attack method against black-box CTR models via generating realistic fake samples, named CTRAttack. To better train the generation network, the weights of its embedding layer are shared with those of the substitute model, with both the similarity loss and classification loss used to update the generation network. To ensure that the discrete features of the generated fake samples are all real, we first adopt the similarity loss to ensure that the distribution of the generated perturbed samples is sufficiently close to the distribution of the real features, and then the nearest neighbor algorithm is used to retrieve the most appropriate features for non-existent discrete features from the candidate instance set. Extensive experiments demonstrate that CTRAttack can not only effectively attack the black-box recommender systems but also improve the robustness of these models while maintaining prediction accuracy. [ABSTRACT FROM AUTHOR]

Graph similarity learning is a significant and fundamental issue in the theory and analysis of graphs, which has been applied in a variety of fields, including object tracking, recommender systems, similarity search, and so on. Recent methods for graph similarity learning that utilize deep learning typically share two deficiencies: (1) they leverage graph neural networks as backbones for learning graph representations but have not well captured the complex information inside data, and (2) they employ a cross-graph attention mechanism for graph similarity learning, which is computationally expensive. Taking these limitations into consideration, a method for graph similarity learning is devised in this study, namely, Contrastive Graph Similarity Network (CGSim). To enhance graph similarity learning, CGSim makes use of the complementary information of two input graphs and captures pairwise relations in a contrastive learning framework. By developing a dual contrastive learning module with a node-graph matching and a graph-graph matching mechanism, our method significantly reduces the quadratic time complexity for cross-graph interaction modeling to linear time complexity. Jointly learning in an end-to-end framework, the graph representation embedding module and the well-designed contrastive learning module can be beneficial to one another. A comprehensive series of experiments indicate that CGSim outperforms state-of-the-art baselines on six datasets and significantly reduces the computational cost, which demonstrates our CGSim model's superiority over other baselines. [ABSTRACT FROM AUTHOR]

In this "info-plosion" era, recommendation systems (or recommenders) play a significant role in finding interesting items in the surge of online digital activities and e-commerce. Several techniques have been widely applied for recommendation systems, but the cold-start and sparsity problems remain a major challenge. The cold-start problem occurs when generating recommendations for new users and items without sufficient information. Sparsity refers to the problem of having a large amount of users and items but with few transactions or interactions. In this article, a novel cross-domain recommendation model, Cross-Domain Evolution Learning Recommendation (abbreviated as CD-ELR), is developed to communicate the information from different domains in order to tackle the cold-start and sparsity issues by integrating matrix factorization and recurrent neural network. We introduce an evolutionary concept to describe the preference variation of users over time. Furthermore, several optimization methods are developed for combining the domain features for precision recommendation. Experimental results show that CD-ELR outperforms existing state-of-the-art recommendation baselines. Finally, we conduct experiments on several real-world datasets to demonstrate the practicability of the proposed CD-ELR. [ABSTRACT FROM AUTHOR]

Today's recommender systems are criticized for recommending items that are too obvious to arouse users' interests. Therefore, the research community has advocated some "beyond accuracy" evaluation metrics such as novelty, diversity, and serendipity with the hope of promoting information discovery and sustaining users' interests over a long period of time. While bringing in new perspectives, most of these evaluation metrics have not considered individual users' differences in their capacity to experience those "beyond accuracy" items. Open-minded users may embrace a wider range of recommendations than conservative users. In this article, we proposed to use curiosity traits to capture such individual users' differences. We developed a model to approximate an individual's curiosity distribution over different stimulus levels. We used an item's surprise level to estimate the stimulus level and whether such a level is in the range of the user's appetite for stimulus, called Comfort Zone. We then proposed a recommender system framework that considers both user preference and their Comfort Zone where the curiosity is maximally aroused. Our framework differs from a typical recommender system in that it leverages human's Comfort Zone for stimuli to promote engagement with the system. A series of evaluation experiments have been conducted to show that our framework is able to rank higher the items with not only high ratings but also high curiosity stimulation. The recommendation list generated by our algorithm has a higher potential of inspiring user curiosity compared to the state-of-the-art deep learning approaches. The personalization factor for assessing the surprise stimulus levels further helps the recommender model achieve smaller (better) inter-user similarity. [ABSTRACT FROM AUTHOR]

Conversational recommender systems (CRS) have garnered significant attention in academia and industry because of their ability to capture user preferences via system questions and user responses. Typically, in a CRS, reinforcement learning (RL) is utilized to determine the optimal timing for requesting attribute information or suggesting items. However, existing methods consider user-preferred attributes independently and ignore that attributes may be of different importance to the same user, in the attribute and item selection phases, which limits the accuracy and interpretability of CRS. Inspired by this, we propose deep conversational path reasoning (DeepCPR), which involves constructing a reasoning path on a graph with a series of user-favored attributes. It utilizes the attention mechanism to thoroughly examine the connections between these attributes and provide improved explanations for which attributes to inquire about or which items to recommend. In DeepCPR, two deep-learning-based modules are proposed to realize attribute and item selection. In the first module, the sequence of attributes confirmed by the user in conversation is encoded with a gated graph neural network to obtain the user's long-term preference using a self-attentionmechanism for the selection of candidate attributes. In the second module, a self-attention approach with more appropriate strategies is developed to dynamically select candidate items. In addition, to achieve fine-grained user preference modeling, a recurrent neural network is employed to aggregate the sequence of attributes that interact with the users. Numerous experimental evaluations conducted on four real CRS datasets show that the proposed method significantly outperforms existing advanced methods in terms of conversational recommendations. [ABSTRACT FROM AUTHOR]

Cross-domain recommender systems could potentially improve the recommendation performance by means of transferring abundant knowledge from the auxiliary domain to the target domain. They could help address some key challenges in recommender systems, such as data sparsity and cold start. However, most existing cross-domain recommendation approaches represent the user preferences based on a single kind of user's feature or behavior and fail to explore the hidden interaction effects of different kinds of features or behaviors. In this article, we propose the Sequential and Graphical Cross-Domain Recommendations with a Multi-View Hierarchical Transfer Gate (SGCross) to transfer user representations from multiple perspectives. The SGCross model constructs a user profile by learning the personal preference from a personal view, the dynamic preference from a temporal view, as well as the collaborative preference from a collaborative view. Specifically, a Multi-view Hierarchical Gate (MHG) is designed to transfer the informative representations of user knowledge on different views from the auxiliary domain separately, aiming to enhance the user representations. Furthermore, a two-stage attentive fusion module is designed to integrate transferred information at two levels: the domain level and the view level. Extensive experiments on the Amazon dataset and the Douban dataset have demonstrated that SGCross effectively improves the accuracy of cross-domain recommendations and outperforms the state-of-the-art baseline models. [ABSTRACT FROM AUTHOR]

Recommendation systems have been widely embedded into many Internet services. For example, Meta's deep learning recommendation model (DLRM) shows high prefictive accuracy of click-through rate in processing large-scale embedding tables. The SparseLengthSum (SLS) kernel of the DLRM dominates the inference time of the DLRM due to intensive irregularmemory accesses to the embedding vectors. Some prior works directly adopt near data processing (NDP) solutions to obtain higher memory bandwidth to accelerate SLS. However, their inferior memory hierarchy induces low performance-cost ratio and fails to fully exploit the data locality. Although some software-managed cache policies were proposed to improve the cache hit rate, the incurred cache miss penalty is unacceptable considering the high overheads of executing the corresponding programs and the communication between the host and the accelerator. To address the issues aforementioned, we propose EMS-i, an efficient memory system design that integrates Solide State Drive (SSD) into the memory hierarchy using Compute Express Link (CXL) for recommendation system inference. We specialize the caching mechanism according to the characteristics of various DLRM workloads and propose a novel prefetching mechanism to further improve the performance. In addition, we delicately design the inference kernel and develop a customized mapping scheme for SLS operation, considering the multi-level parallelism in SLS and the data locality within a batch of queries. Compared to the state-of-the-art NDP solutions, EMS-i achieves up to 10.9x speedup over RecSSD and the performance comparable to RecNMP with 72% energy savings. EMS-i also saves up to 8.7x and 6.6 x memory cost w.r.t. RecSSD and RecNMP, respectively. [ABSTRACT FROM AUTHOR]

Recommendation system plays an important role in the rapid development of micro-video sharing platform. Micro-video has rich modal features, such as visual, audio, and text. It is of great significance to carry out personalized recommendation by integrating multi-modal features. However, most of the current multi-modal recommendation systems can only enrich the feature representation on the item side, while it leads to poor learning of user preferences. To solve this problem, we propose a novel module named Learning the User’s Deeper Preferences (LUDP), which constructs the item-item modal similarity graph and user preference graph in each modality to explore the learning of item and user representation. Specifically, we construct item-item similar modalities graph using multi-modal features, the item ID embedding is propagated and aggregated on the graph to learn the latent structural information of items; The user preference graph is constructed through the historical interaction between the user and item, on which the multi-modal features are aggregated as the user’s preference for the modal. Finally, combining the two parts as auxiliary information enhances the user and item representation learned from the collaborative signals to learn deeper user preferences. Through a large number of experiments on two public datasets (TikTok, Movielens), our model is proved to be superior to the most advanced multi-modal recommendation methods. [ABSTRACT FROM AUTHOR]

Recommender systems have been successfully used in many domains with the help of machine learning algorithms. However, such applications tend to use multi-dimensional user data, which has raised widespread concerns about the breach of users’ privacy. Meanwhile, wearable technologies have enabled users to collect fitness-related data through embedded sensors to monitor their conditions or achieve personalized fitness goals. In this article, we propose a novel privacy-aware personalized fitness recommender system. We introduce a multi-level deep learning framework that learns important features from a large-scale real fitness dataset that is collected from wearable Internet of Things (IoT) devices to derive intelligent fitness recommendations. Unlike most existing approaches, our approach achieves personalization by inferring the fitness characteristics of users from sensory data, minimizing the need for explicitly collecting user identity or biometric information, such as name, age, height, and weight. Our proposed models and algorithms predict (a) personalized exercise distance recommendations to help users to achieve target calories, (b) personalized speed sequence recommendations to adjust exercise speed given the nature of the exercise and the chosen route, and (c) personalized heart rate sequence to guide the user of the potential health status for future exercises. Our experimental evaluation on a real-world Fitbit dataset demonstrated high accuracy in predicting exercise distance, speed sequence, and heart rate sequence compared with similar studies.1 Furthermore, our approach is novel compared with existing studies, as it does not require collecting and using users’ sensitive information. Thus, it preserves the users’ privacy. [ABSTRACT FROM AUTHOR]

Both accurate and fast mobile recommendation systems based on click behaviors analysis are crucial in ebusiness. Deep learning has achieved state-of-the-art accuracy and the traditional wisdom often hosts these computation-intensive models in powerful cloud centers. However, the cloud-only approaches put significant computational pressure on cloud servers and increase the latency in heavy-load scenarios. Moreover, existing work often adopts RNN structures to model behaviors that suffer from low processing speed for under-utilization of parallel devices such as GPUs. In this work, we propose an efficient internet behaviorbased recommendation framework with edge-cloud collaboration on deep CNNs (CoRec) to improve both the accuracy and speed for mobile recommendation. A novel convolutional interest network (CIN) improves the accuracy by modeling the long- and short-term interests and accelerates the prediction through parallelfriendly convolutions. To further improve the serving throughput and latency, a novel device-cloud collaboration strategy reduces workloads by pre-computing and caching long-term interests in the cloud offline and real-time computation of short-term interests in devices. Extensive experiments on real-world datasets show that CoRec significantly outperforms the state-of-the-art methods in accuracy and has achieved at least an order of magnitude improvement in latency and throughput compared to cloud-only RNN-based approaches for long behaviors. [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 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]

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]

The explosive growth of e-commerce and online service has led to the development of recommender system. Aiming to provide a list of items to meet a user's personalized need by analyzing his/her interaction1 history, recommender system has been widely studied in academic and industrial communities. Different from conventional recommender systems, sequential recommender systems attempt to capture the pattern of users' sequential behaviors and the evolution of users' preferences.Most of the existing sequential recommendation models only focus on user interaction sequence, but neglect item interaction sequence. An item interaction sequence also contains rich contextual information for capturing the item's dynamic characteristic, since an item's dynamic characteristic can be reflected by the users who interact with it in a period. Furthermore, existing dual sequential models use the same method to handle the user interaction sequence and item interaction sequence, and do not consider their different characteristics. Hence, we propose a novel Double Attention Convolution Neural Network (DACNN), which incorporates user interaction sequence and item interaction sequence into an integrated neural network framework. DACNN leverages the strength of attentionmechanism to capture the temporary suitability and adopts CNN to extract local sequential features. Experimental evaluations on the real datasets show that DACNN outperforms the baseline approaches. [ABSTRACT FROM AUTHOR]

Visualization recommendation work has focused solely on scoring visualizations based on the underlying dataset, and not the actual user and their past visualization feedback. These systems recommend the same visualizations for every user, despite that the underlying user interests, intent, and visualization preferences are likely to be fundamentally different, yet vitally important. In this work, we formally introduce the problem of personalized visualization recommendation and present a generic learning framework for solving it. In particular, we focus on recommending visualizations personalized for each individual user based on their past visualization interactions (e.g., viewed, clicked, manually created) along with the data from those visualizations. More importantly, the framework can learn from visualizations relevant to other users, even if the visualizations are generated from completely different datasets. Experiments demonstrate the effectiveness of the approach as it leads to higher quality visualization recommendations tailored to the specific user intent and preferences. To support research on this new problem, we release our user-centric visualization corpus consisting of 17.4k users exploring 94k datasets with 2.3 million attributes and 32k user-generated visualizations. [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]

Many people are interested in taking astonishing photos and sharing them with others. Emerging high-tech hardware and software facilitate the ubiquitousness and functionality of digital photography. Because composition matters in photography, researchers have leveraged some common composition techniques, such as the rule of thirds and the perspective-related techniques, in providing photo-taking assistance. However, composition techniques developed by professionals are far more diverse than well-documented techniques can cover. We present a new approach to leverage the underexplored photography ideas, which are virtually unlimited, diverse, and correlated. We propose a comprehensive fork-join framework, named CAPTAIN (Composition Assistance for Photo Taking), to guide a photographer with a variety of photography ideas. The framework consists of a few components: integrated object detection, photo genre classification, artistic pose clustering, and personalized aesthetics-aware image retrieval. CAPTAIN is backed by a large managed dataset crawled from a Website with ideas from photography enthusiasts and professionals. The work proposes steps to decompose a given amateurish shot into composition ingredients and compose them to bring the photographer a list of useful and related ideas. The work addresses personal preferences for composition by presenting a user-specified preference list of photography ideas. We have conducted many experiments on the newly proposed components and reported findings. A user study demonstrates that the work is useful to those taking photos. [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]

In this article, we study a multi-step interactive recommendation problem for explicit-feedback recommender systems. Different from the existing works, we propose a novel user-specific deep reinforcement learning approach to the problem. Specifically, we first formulate the problem of interactive recommendation for each target user as a Markov decision process (MDP). We then derive a multi-MDP reinforcement learning task for all involved users. To model the possible relationships (including similarities and differences) between different users' MDPs, we construct user-specific latent states by using matrix factorization. After that, we propose a user-specific deepQ-learning (UDQN) method to estimate optimal policies based on the constructed user-specific latent states. Furthermore, we propose Biased UDQN (BUDQN) to explicitly model user-specific information by employing an additional bias parameter when estimating the Q-values for different users. Finally, we validate the effectiveness of our approach by comprehensive experimental results and analysis. [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]

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]