Search

Nowadays, the volume of online information is growing and it is difficult to find the required information. Effective strategies such as recommender systems are required to overcome information overload. Collaborative filtering is a widely used type of recommender system in e-commerce environments and can simply provide suggestions for users. Recently, deep learning approaches were applied in collaborative filtering to tackle some drawbacks. This systematic review aims to provide a comprehensive review of recent research efforts on deep learning-based collaborative filtering recommender systems. We explain the research methodology and paper selection process and the search query. 102 papers are selected out of 719 papers that were published between 2019 and May 2023. Furthermore, the approaches in the selected papers are classified into two main categories: memory-based and model-based techniques. The main ideas, advantages, disadvantages, used tools, type of neural network, applications, and evaluation parameters of each selected paper are also discussed in detail. It was found that CNN (Convolutional Neural Network), AE (Autoencoder), DNN (Deep neural network), and Hybrid networks are the four mostly used neural networks in recommender systems. Also, Python, MATLAB, and Java are the most frequently used tools in the reviewed papers. Regarding the applications of the recommender systems in the reviewed papers, movies, products, and music recommendation are three most frequent applications. We point out the open issues and future research directions. Some key challenges such as cold start, data sparsity, scalability, and accuracy are still open to be addressed. [ABSTRACT FROM AUTHOR]

A recommendation system (RS) can help overcome information overload issues by offering personalized predictions for users. Typically, RS considers the overall ratings of users on items to generate recommendations for them. However, users may consider several aspects when evaluating items. Hence, a multi-criteria RS considers n-aspects of items to generate more accurate recommendations than a single-criteria RS. This research paper proposes two deep encoder–decoder models based on shared learning for a multi-criteria RS, multi-modal deep encoder–decoder-based shared learning (MMEDSL) and multi-criteria deep encoder–decoder-based shared learning (MCEDSL). MMEDSL employs the shared learning technique by concentrating on the multi-modality concept in deep learning, while MCEDSL focuses on the training process to apply the shared learning technique. The shared learning captures useful shared information during the learning process since the multi-criteria may have hidden inter-relationships. A set of experiments were conducted to compare the proposed models with recent baseline approaches. The Yahoo! Movies multi-criteria dataset was utilized. The results demonstrate that the proposed models outperform other algorithms. In addition, the results show that integrating the shared learning technique with the RS produces precise recommendation predictions. [ABSTRACT FROM AUTHOR]

Recommendation to groups of users is a challenging subfield of recommendation systems. Its key concept is how and where to make the aggregation of each set of user information into an individual entity, such as a ranked recommendation list, a virtual user, or a multi-hot input vector encoding. This paper proposes an innovative strategy where aggregation is made in the multi-hot vector that feeds the neural network model. The aggregation provides a probabilistic semantic, and the resulting input vectors feed a model that is able to conveniently generalize the group recommendation from the individual predictions. Furthermore, using the proposed architecture, group recommendations can be obtained by simply feedforwarding the pre-trained model with individual ratings; that is, without the need to obtain datasets containing group of user information, and without the need of running two separate trainings (individual and group). This approach also avoids maintaining two different models to support both individual and group learning. Experiments have tested the proposed architecture using three representative collaborative filtering datasets and a series of baselines; results show suitable accuracy improvements compared to the state of the art. [ABSTRACT FROM AUTHOR]

With the explosive growth of online information, many recommendation methods have been proposed. This research direction is boosted with deep learning architectures, especially the recently proposed graph convolutional networks (GCNs). GCNs have shown tremendous potential in graph embedding learning thanks to its inductive inference property. However, most of the existing GCN-based methods focus on solving tasks in the homogeneous graph settings, and none of them considers heterogeneous graph settings. In this paper, we bridge the gap by developing a novel framework called HeteGraph based on the GCN principles. HeteGraph can handle heterogeneous graphs in the recommender systems. Specifically, we propose a sampling technique and a graph convolutional operation to learn high-quality graph's node embeddings, which differs from the traditional GCN approaches where a full graph adjacency matrix is needed for the embedding learning. We design two models based on the HeteGraph framework to evaluate two important recommendation tasks, namely item rating prediction and diversified item recommendations. Extensive experiments show the encouraging performance of HeteGraph on the first task and the state-of-the-art performance on the second task. [ABSTRACT FROM AUTHOR]

Deep learning provides accurate collaborative filtering models to improve recommender system results. Deep matrix factorization and their related collaborative neural networks are the state of the art in the field; nevertheless, both models lack the necessary stochasticity to create the robust, continuous, and structured latent spaces that variational autoencoders exhibit. On the other hand, data augmentation through variational autoencoder does not provide accurate results in the collaborative filtering field due to the high sparsity of recommender systems. Our proposed models apply the variational concept to inject stochasticity in the latent space of the deep architecture, introducing the variational technique in the neural collaborative filtering field. This method does not depend on the particular model used to generate the latent representation. In this way, this approach can be applied as a plugin to any current and future specific models. The proposed models have been tested using four representative open datasets, three different quality measures, and state-of-the-art baselines. The results show the superiority of the proposed approach in scenarios where the variational enrichment exceeds the injected noise effect. Additionally, a framework is provided to enable the reproducibility of the conducted experiments. [ABSTRACT FROM AUTHOR]

The massive number of research articles on the Web makes it troublesome for researchers to identify related works that could meet their preferences and interests. Consequently, various network representation learning-based models have been proposed to produce citation recommendations. Nevertheless, these models do not exploit semantic relations and contextual information between the objects of bibliographic papers' networks, which can result in inadequate citation recommendations. Moreover, existing citation recommendation methods face problems such as lack of personalization, cold-start, and network sparsity. To mitigate such problems and produce individualized citation recommendations, we propose a heterogeneous network embedding model that jointly learns node representations by exploiting semantics corresponding to the author, time, context, field of study, citations, and topics. Compared to baseline models, the results produced by the proposed model over the DBLP datasets prove 10% and 12% improvement on mean average precision (MAP) and normalized discounted cumulative gain (nDCG@10) metrics, respectively. Also, the effectiveness of our model is analyzed on the cold-start papers and network sparsity problems, where it gains 12% and 9% better MAP and recall@10 scores, respectively. [ABSTRACT FROM AUTHOR]

We propose a tourist attraction IoT-enabled deep learning-based recommendation system to enhance tourist experience in a smart city. Travelers will enter details about their travels (traveling alone or with a companion, type of companion such as partner or family with kids, traveling for business or leisure, etc.) as well as user side information (age of the traveler/s, hobbies, etc.) into the smart city app/website. Our proposed deep learning-based recommendation system will process this personal set of input features to recommend the tourist activities/attractions that best fit his/her profile. Furthermore, when the tourists are in the smart city, content-based information (already visited attractions) and context-related information (location, weather, time of day, etc.) are obtained in real time using IoT devices; this information will allow our proposed deep learning-based tourist attraction recommendation system to suggest additional activities and/or attractions in real time. Our proposed multi-label deep learning classifier outperforms other models (decision tree, extra tree, k-nearest neighbor and random forest) and can successfully recommend tourist attractions for the first case [(a) searching for and planning activities before traveling] with the loss, accuracy, precision, recall and F1-score of 0.5%, 99.7%, 99.9%, 99.9% and 99.8%, respectively. It can also successfully recommend tourist attractions for the second case [(b) looking for activities within the smart city] with the loss, accuracy, precision, recall and F1-score of 3.7%, 99.5%, 99.8%, 99.7% and 99.8%, respectively. [ABSTRACT FROM AUTHOR]

In recent years, the ever-growing contents (movies, clothes, books, etc.) accessible and buyable via the Internet have led to the information overload issue and therefore the item targeting problem. Indeed, the huge mass of contents complexifies the identification of items fitting users' expectations. As powerful filtering tools, recommender systems efficiently alleviate the item targeting issue. Collaborative filtering-based methods are among the most influential algorithms adopted in recommender systems. Among collaborative filtering-based methods, model-based approaches are widely used in recent powerful recommendation methods. Due to its efficiency, the matrix factorization technique is spreadly employed in model-based approaches. However, those methods badly deal with issues such as data sparseness and cold-start problems that severely affect the recommendation quality. To overcome these limitations shown by state-of-the-art methods, we propose in this paper a recommender approach that couples the effectiveness of an enhanced matrix factorization technique to the power of a deep neural network model. In the first step, the user's latent factors and item latent factors are extracted from a doubly-regularized matrix factorization process. Thereafter, those latent factors are used to feed a deep learning structure in a forward-propagation process, and a normalized cross-entropy method is used to increase the precision of the deep neural network through a backpropagation process. The end prediction is made by combining results from the matrix factorization step and the deep neural structure. Extensive experiments are conducted on real-world datasets and show that our proposal outperforms other methods in terms of prediction accuracy and recommendation quality. [ABSTRACT FROM AUTHOR]

E-commerce platforms apply recommendation technology to a wide variety of commercial websites to help users quickly find the product they need from a large number of products. At present, recommendation systems have been widely used in large-scale e-commerce websites, and most e-commerce shopping websites attract customers through the image information of goods. In this paper, the research status of content-based image retrieval algorithms is analysed, and how to use image content information to recommend goods is studied. A hierarchical commodity classification and retrieval system are designed. A class decision layer is used to determine the category of commodity images and then precisely retrieve the corresponding category of commodity image features. The corresponding relationship between different commodity visual features is used to recommend commodities, and a matching recommendation algorithm for commodities is proposed. Experiments show that the proposed image content-based recommendation method can coordinate with features, and its recommendation results have high accuracy in practical applications. [ABSTRACT FROM AUTHOR]

In recent years, studies have revealed that introducing knowledge graphs (KGs) into recommendation systems as auxiliary information can improve recommendation accuracy. However, KGs are usually based on third-party data that may be manipulated by malicious individuals. In this study, we developed a poisoning attack strategy applied on a KG-based recommendation system to analyze the influence of fake links. The aim of an attacker is to recommend specific products to improve their visibility. Most related studies have focused on adversarial attacks on graph data; KG-based recommendation systems have rarely been discussed. We propose an attack model corresponding to recommendations. In the model, the current recommended status and a specified item are analyzed to estimate the effects of different attack decisions (addition or deletion of facts), thereby generating the optimal attack combination. Finally, the KG is contaminated by the attack combination so that the trained recommendation model recommends a specific item to as many people as possible. We formulated the process into a deep reinforcement learning method. Conducting experiments on the movie and the fund data sets enabled us to systematically analyze our poisoning attack strategy. The experimental results proved that the proposed strategy can effectively improve an item's ranking in a recommendation list. [ABSTRACT FROM AUTHOR]

In the context of recommender systems based on collaborative filtering (CF), obtaining accurate neighborhoods of the items of the datasets is relevant. Beyond particular individual recommendations, knowing these neighbors is fundamental for adding differentiating factors to recommendations, such as explainability, detecting shilling attacks, visualizing item relations, clustering, and providing reliabilities. This paper proposes a deep learning architecture to efficiently and accurately obtain CF neighborhoods. The proposed design makes use of a classification neural network to encode the dataset patterns of the items, followed by a generative process that obtains the neighborhood of each item by means of an iterative gradient localization algorithm. Experiments have been conducted using five popular open datasets and five representative baselines. The results show that the proposed method improves the quality of the neighborhoods compared to the K-Nearest Neighbors (KNN) algorithm for the five selected similarity measure baselines. The efficiency of the proposed method is also shown by comparing its computational requirements with that of KNN. [ABSTRACT FROM AUTHOR]

With an increase in online longitudinal users' interactions, capturing users' precise preferences and giving accurate recommendations have become an urgent need for all businesses. Existing sequence-aware methods generally exploit a static low-rank vector for acquiring the overall sequential features, and incorporate context information as auxiliary input. As a result, they have a restricted modeling ability for extracting multi-grained sequential behaviors over contextual information. In other words, they poorly capture the hierarchical relationship between context relations and item relations that currently influence users' preferences in a unified framework. Besides, they usually utilize users' short-term preferences with either static or irrelevant long-term representation for the prediction. To tackle the above issues, in this paper, we propose a novel Context-aware Recommender System Based on a Deep Sequential Learning Approach (CReS) to capture users' dynamic preferences by modeling the hierarchical relationships between contexts and items in a particular session, and for combining users' short-term sessions with the relevant long-term representations. Specifically, within a certain session, we design a hierarchical attention network between the identified context relations and items relations, namely CReSession. Therefore, with CReSession, we could provide a suitable session representation that mimics the hierarchical user interests on multiple granularities of contextual types and its corresponding items. We then introduce a neural attentive bi-directional GRU network to distill only those highly related to the recent short-term session. Finally, the relevant long-term representations and the short-term session are combined with the sequential residual connection to form the final user representation in a unified manner. With extensive experiments on two real-world datasets, CReS not only achieves significant improvement over the state-of-the-art methods in terms of pre-defined metrics, but also provides an interpretable result regarding why we recommend these items to users. [ABSTRACT FROM AUTHOR]

A recommender system plays a vital role in information filtering and retrieval, and its application is omnipresent in many domains. There are some drawbacks such as the cold-start and the data sparsity problems which affect the performance of the recommender model. Various studies help with drastically improving the performance of recommender systems via unique methods, such as the traditional way of performing matrix factorization (MF) and also applying deep learning (DL) techniques in recent years. By using DL in the recommender system, we can overcome the difficulties of collaborative filtering. DL now focuses mainly on modeling content descriptions, but those models ignore the main factor of user–item interaction. In the proposed hybrid Bayesian stacked auto-denoising encoder (HBSADE) model, it recognizes the latent interests of the user and analyzes contextual reviews that are performed through the MF method. The objective of the model is to identify the user's point of interest, recommending products/services based on the user's latent interests. The proposed two-stage novel hybrid deep learning-based collaborative filtering method explores the user's point of interest, captures the communications between items and users and provides better recommendations in a personalized way. We used a multilayer neural network to manipulate the nonlinearities between the user and item communication from data. Experiments were to prove that our HBSADE outperforms existing methodologies over Amazon-b and Book-Crossing datasets. [ABSTRACT FROM AUTHOR]

Deep learning-based recommender systems have gained much attention due to the advantage of encoding content-based information, such as user textual reviews and item descriptions, images, or videos, without the trouble of manually crafting feature vectors. However, those systems are trained from scratch with randomly initialized parameters, where the training process can take a long time to converge. With the most recent breakthroughs in Natural Language Processing using transfer learning, pre-trained transformer-based models now provide a better foundation for textual information encoding. This inspires us to propose a transformer-based recommender system using transfer learning. As the first core contribution in this work, we apply transfer learning to the system, by fine-tuning the pre-trained transformer models for information encoding. The experiment result shows that the proposed system outperforms several other deep learning-based recommender systems on multiple datasets. As the second core contribution, we propose a novel user vector encoding algorithm that assists all the models to achieve a better performance, when the user content information is not available. [ABSTRACT FROM AUTHOR]

Extracting demographic features from hidden factors is an innovative concept that provides multiple and relevant applications. The matrix factorization model generates factors which do not incorporate semantic knowledge. Extracting the existing nonlinear relations between hidden factors and demographic information is a challenging task that can not be adequately addressed by means of statistical methods or using simple machine learning algorithms. This paper provides a deep learning-based method: DeepUnHide, able to extract demographic information from the users and items factors in collaborative filtering recommender systems. The core of the proposed method is the gradient-based localization used in the image processing literature to highlight the representative areas of each classification class. Validation experiments make use of two public datasets and current baselines. The results show the superiority of DeepUnHide to make feature selection and demographic classification, compared to the state-of-art of feature selection methods. Relevant and direct applications include recommendations explanation, fairness in collaborative filtering and recommendation to groups of users. [ABSTRACT FROM AUTHOR]

Recommender systems attempt to provide effective suggestions to each user based on their interests and behaviors. These recommendations usually match the personal user preferences and assist them in the decision-making process. With the ever-expanding growth of information on the web, online education systems, e-commerce, and, eventually, the emergence of social networks, the necessity of developing such systems is unavoidable. Collaborative filtering and content-based filtering are among the most important techniques used in recommender systems. Meanwhile, with the significant advances in deep learning in recent years, the use of this technology has been widely observed in recommender systems. In this study, a hybrid social recommender system utilizing a deep autoencoder network is introduced. The proposed approach employs collaborative and content-based filtering, as well as users' social influence. The social influence of each user is calculated based on his/her social characteristics and behaviors on Twitter. For the evaluation purpose, the required datasets have been collected from MovieTweetings and Open Movie Database. The evaluation results show that the accuracy and effectiveness of the proposed approach have been improved compared to the other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As an important technology of Internet products, the recommender system can help users to obtain the information they need and alleviate the problem of information overload. In the implicit feedback recommender system, the key issue is how to represent users and products. In recent years, deep learning has achieved good performance in many fields including speech recognition, computer vision and natural language processing. We propose a deep learning-enhanced framework for implicit feedback recommendation. In this framework, we simultaneously learn the new distributed representation of users and items via node2vec to improve the negative sampling strategy. Finally, we develop a deep neural network recommendation model to integrate user features, product features and interaction features. Experiments conducted on two real-world datasets demonstrate the effectiveness of the proposed framework and methods. [ABSTRACT FROM AUTHOR]

In the field of artificial intelligence, the development of many technologies requires technical support for relational classification. Recently, deep learning has been applied more and more to text-based entity relationship classification tasks, but most of the previous methods need to use syntax or dependency structure feature. However, due to the time and space complexity of syntactic parsing, the structural features are inconvenient to use directly in the pre-processing stage. In addition, structural features may have serious domain dependence problems. This paper studies the current recommendation algorithm, analyzes the current research status of the recommendation system, and deeply analyzes the research of deep learning in the field of recommendation systems, based on BPSO algorithm, the context complex segmentation method is applied, and then the deep convolutional neural network is applied for feature extraction. The extracted feature set is sent to WordEmbedding, and using the technology to generates the word vector, the input layer of the CBOW is used to represent the size of the training window. The experimental results show that the model has obvious advantages over the methods proposed in other literature. It can adapt to multi-category context semantic analysis, more accurate related recommendations, and obtain a better user experience. [ABSTRACT FROM AUTHOR]

Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train these networks on specific tasks. Many deep learning frameworks have their own implementation of training and sampling procedures for recurrent neural networks, while there are in fact multiple other possibilities to choose from and other parameters to tune. In the existing literature, this is very often overlooked or ignored. In this paper, we therefore give an overview of possible training and sampling schemes for character-level recurrent neural networks to solve the task of predicting the next token in a given sequence. We test these different schemes on a variety of datasets, neural network architectures and parameter settings, and formulate a number of take-home recommendations. The choice of training and sampling scheme turns out to be subject to a number of trade-offs, such as training stability, sampling time, model performance and implementation effort, but is largely independent of the data. Perhaps the most surprising result is that transferring hidden states for correctly initializing the model on subsequences often leads to unstable training behavior depending on the dataset. [ABSTRACT FROM AUTHOR]

Socialized recommender system recommends reliable healthcare services for users. Ratings are predicted on the healthcare services by merging recommendations given by users who has social relations with the active users. However, existing works did not consider the influence of distrust between users. They recommend items only based on the trust relations between users. We therefore propose a novel deep learning-based socialized healthcare service recommender model, which recommends healthcare services with recommendations given by recommenders with both trust relations and distrust relations with the active users. The influences of recommenders, considering both the node information and the structure information, are merged via the deep learning model. Experimental results show that the proposed model outperforms the existing works on prediction accuracy and prediction coverage simultaneously, even for cold start users or users with very sparse trust relations. It is also computational less expensive. [ABSTRACT FROM AUTHOR]