Search

One-class collaborative filtering (OCCF) problems are prevalent in real-world recommender systems, such as news and music recommendation, but suffer from sparsity issues and particularly lack negatively preferred items. To address the challenge, the state-of-the-art algorithms assigned uninteracted items smaller weights of being negative and performed low-rank approximation over a user-item interaction matrix. However, the prior ratings of uninteracted items are usually set to zero but may not well-defined. To avert the prior ratings of uninteracted items, in this paper, we propose a novel ranking-based implicit regularizer by hypothesizing that users preference scores for uninteracted items are close to each other. The regularizer is then used in a ranking-based OCCF framework to penalize large difference of preference scores between uninteracted items. To optimize model parameters in this framework, we develop a scalable alternating least square algorithm and coordinate descent algorithm, whose time complexity is linearly proportional to data size. Finally, we extensively evaluate the proposed algorithms with six real-world datasets. The results show that the proposed regularizer significantly improves recommendation quality of ranking-based OCCF algorithms, such as BPRMF and RankALS. Moreover, the ranking-based framework with the proposed regularizer outperforms the state-of-the-art recommendation algorithms for implicit feedback.

Cyber-Physical Systems (CPS) is a security real-time embedded system. CPS integrates the information sensed by the current physical sensors, through high-speed real-time transmission, and then carries out powerful information processing to effectively interact and integrate the physical and the information worlds. With the aim to improve the quality of service, optimize the existing physical space, and increase security, collaborative filtering algorithms have also been widely used in various recommendation models for Internet of Things (IoT) services. However, general collaborative filtering algorithms cannot capture complex interactive information in the sparse Mashup-Web service call matrix, which leads to lower recommendation performance. Based on artificial intelligence technology, this study proposes a recommendation algorithm for security collaborative filtering service that integrates content similarity. A security collaborative filtering module is used to capture the complex interaction information between Mashup and Web services. By applying the content similarity module to extract the semantic similarity information between the Mashup and Web services, the two modules are seamlessly integrated into a deep neural network to accurately and quickly predict the rating information of Mashup for the Web services. Real data set on the intelligent CPS is captured and then compared with mainstream service recommendation algorithms. Experimental results show that the proposed algorithm not only efficiently completes the Web service recommendation task under the premise of sparse data but also shows better accuracy, effectivity, and privacy. Thus, the proposed method is highly suitable for the application of intelligence CPS.

Multiple cooperative task assignment is a crucial problem in spatial crowdsourcing, in which each task requires more than one appropriate user to complete. Existing studies generally assume that all users are trustworthy and can reliably perform assigned tasks. However, such assumptions do not hold in the real world. In this paper, we consider an essential crowdsourcing problem, namely Reliability-oriented Socially-Aware Crowdsourcing (R-SAC), which aims to recruit reliable users for multiple cooperative tasks so that the overall reliability of task assignment is maximized. We prove that the R-SAC problem is NP-hard. Then, we propose an approximation algorithm and provide a theoretical guarantee. Specifically, user reliability refers to the probability that a user can reliably perform assigned tasks. To achieve reliable user recruitment during task assignment, we formulate the reliability of a user by combining the matching between the user and tasks, and the reliability feedback from neighbors who share similar behaviors with the user in a social network. Besides, the distributed collaborative filtering technique is utilized to select the reliability feedback from the neighbors. Experiments on two real-world datasets validate that our proposed approach significantly outperforms the representative approaches.

Quality of Service (QoS) guarantee is an important issue in building service-oriented applications. Generally, some QoS values of a service are unknown to its users who have never invoked the service before. Fortunately, collaborative filtering (CF)-based methods are proved feasible for missing QoS prediction and have been widely used. However, these methods seldom took the temporal factors into consideration. Indeed, historical QoS values contain more information about user (or service) similarity. Furthermore, as the application environment is dynamic, obtained QoS values usually have short timeliness. Using outdated QoS values will largely decrease the prediction accuracy. In order to resolve this issue, we proposed a time-aware collaborative filtering approach. Firstly, we proposed a QoS model to filter out outdated QoS values, and divided the obtained QoS values into several time slices. Then, we compute the average value of historical QoS as temporal QoS forecast. In addition, by introducing time-aware similarity computation mechanism, we succeed to select real similar neighbor users (or services) and further predict the CF-based QoS based on CF technology. Finally, we can predict the final missing QoS by combining temporal QoS forecast and CF-based QoS prediction. Experiment results show that our approach can receive better prediction precision.

The task of point of interest (POI) recommendation aims to recommend unvisited places to users based on their check-in history. A major challenge in POI recommendation is data sparsity, because a user typically visits only a very small number of POIs among all available POIs. In this paper, we propose AUC-MF to address the POI recommendation problem by maximizing Area Under the ROC curve (AUC). AUC has been widely used for measuring classification performance with imbalanced data distributions. To optimize AUC, we transform the recommendation task to a classification problem, where the visited locations are positive examples and the unvisited are negative ones. We define a new lambda for AUC to utilize the LambdaMF model, which combines the lambda-based method and matrix factorization model in collaborative filtering. Many studies have shown that geographic information plays an important role in POI recommendation. In this study, we focus on two levels geographic information: local similarity and global similarity. We further show that AUC-MF can be easily extended to incorporate geographical contextual information for POI recommendation.

CyberPhysicalSocial System (CPSS) technology closely integrates and coordinates computing resources, physical resources, and social information to provide humans with efficient and convenient services. Service recommendation technology satisfies the individual needs of users by collecting, processing, and analyzing user characteristic data. In recent years, service recommendation algorithms based on social networks and collaborative filtering have been widely used in CPSS. However, this type of service recommendation algorithm cannot effectively use the aliasing and auxiliary information in the service, nor can it generate different service recommendation schemes according to different scenarios. We propose a collaborative filtering service recommendation algorithm that combines heterogeneous information networks and topic models for CPSS. The proposed algorithm designs a more effective functional similarity measurement method through the word vectors learned by Word2vec. Then, we use the topic model to cluster the scenario-based service (SBS), thereby greatly reducing the time required for service recommendation. Experimental analysis results show that we finally determine the best combination of Mashup similarity between the two scenarios with better recommendation efficiency and accuracy. Thus, the proposed recommendation algorithm can effectively improve the quality of service of CPSS, and provide a basis for the personalized service of CPSS.

Matrix completion, in essence, involves recovering a low-rank matrix from a subset of its entries. Most existing methods for matrix completion neglect two significant issues. First, in several practical applications, such as collaborative filtering, some samples may be corrupted completely. However, most of the robust algorithms consider only the condition that a few components of each column have been arbitrarily contaminated. Second, many real data are not static in nature. Nevertheless, the conventional batch-based matrix completion methods cannot efficiently deal with the out-of-sample, that is, the vector completion problem. In this article, we first provide a novel robust matrix completion model and then develop an efficient optimization method that only requires conducting one time singular value decomposition for a thin matrix per iteration. Furthermore, by exploiting the essence of online matrix completion algorithms, we develop a vector completion model which can help users predict the missing values of out of sample. Numerical comparisons with traditional batch-based and online matrix completion algorithms demonstrate the benefits of the proposed method on streaming data corrupted by column outliers. Moreover, we show that our model can be used to detect outliers from incomplete information. This advantage is validated via numerous experimental results on synthetic and real-world data.

Collaborative Filtering (CF) filters the flow of data that can be recommended, by a Recommender System (RS), to a target user according to his taste and his preferences. The target user’s profile is built based on his similarity with other users. For this reason, CF technique is very sensitive to the similarity measure used to quantify the dependency strength between two users (or two items). In this paper we provide an in-depth review on similarity measures used for CF-based RS. For each measure, we outline its fundamental background and we test its performance through an experimental study. Experiments are carried out on three standard datasets (MovieLens100k, MovieLens1M and Jester) and reveal many important conclusions. In fact, results show that ITR and IPWR are the most suitable similarity measures for a user-based RS while AMI is the best choice for an item-based RS. Evaluation metrics show that under the user-based approach, ITR obtains an MAE equal to 0.786 and 0.731 on MovieLens100k and MovieLens1M, respectively. Whereas, IPWR reach an MAE equal to 3.256 on Jester. Also, AMI gets under the item-based approach an MAE equal to 0.745, 0.724 and 3.281 on MovieLens100k, MovieLens1M and Jester, respectively.

Numerous state-of-the-art recommendation frameworks employ deep neural networks in Collaborative Filtering (CF). In this paper, we propose a cross feature fusion neural network (CFFNN) for the enhancement of CF. Existing studies overlook either user preferences for various item features or the relationship between item features and user features. To solve this problem, we construct a cross feature fusion network to enable the fusion of user features and item features as well as a self-attention network to determine users' preferences for items. Specifically, we design a feature extraction layer with multiple MLP (Multilayer Perceptrons) modules to extract both user features and item features. Then, we introduce a cross feature fusion mechanism for an accurate determination of the relationship between different user-item interactions. The features of users and items are crossly embedded and then fed into a prediction network. The attention mechanism enables the model to focus on more effective features. The effectiveness of CFFNN model is demonstrated through extensive experiments on four real-world datasets. The experimental results indicate that CFFNN significantly outperforms the existing state-of-the-art models, with a relative improvement of 3.0\% to 12.1\% on hit ratio (HR) and normalized discounted cumulative gain (NDCG) compared with the baselines.

Singular value decomposition (SVD) is one of the most effective algorithms in recommender systems (RSs). Due to the iterative nature of SVD algorithms, one big challenge is initialization that has a major impact on the convergence and performance of RSs. Unfortunately, existing SVD algorithms in the literature typically initialize the user and item features in a random manner; thus, data information is not fully utilized. This work addresses the challenge of developing an efficient initialization method for SVD algorithms. We propose a general neural embedding initialization framework, where a low-complexity probabilistic autoencoder neural network initializes the features of user and item. This framework supports explicit and implicit feedback data sets. The design details of our proposed framework are elaborated and discussed. Experimental results show that RSs based on our proposed initialization framework outperform the state-of-the-art methods in rating prediction. Moreover, regarding item ranking, our proposed framework shows an improvement of at least 2.20% ~ 5.74% than existing SVD algorithms and other matrix factorization methods in the literature.

Citation recommendation is important in the environment of scholarly big data, where finding relevant papers has become more difficult because of information overload. Applying traditional collaborative filtering (CF) to citation recommendation is rather challenging due to the cold start problem and the lack of paper ratings. To address these two challenges, in this paper, we propose a Collaborative filtering with Network representation learning framework for Citation Recommendation dubbed as CNCRec, which is a hybrid user-based CF considering both paper content and network topology. It aims at recommending citations in heterogeneous academic information networks. CNCRec creates the paper rating matrix based on attributed citation network representation learning, where the attributes are topics extracted from the paper text information. Meanwhile, the learned representations of attributed collaboration network is utilized to improve the selection of nearest neighbors. By harnessing the power of network representation learning, CNCRec is able to make full use of the whole citation network topology compared with previous context-aware network-based models. Extensive experiments on both DBLP and APS datasets show that the proposed method outperforms state-of-the-art methods in terms of precision, recall, and Mean Reciprocal Rank. Moreover, CNCRec can better solve the data sparsity problem compared with other CF-based baselines.

A recommendation system saves the user the trouble of searching for information and analyzes their profile to recommend the most suitable content. A variety of techniques, including content-based, collaborative, and knowledge-based techniques, have been proposed for performing recommendations. Recommendation systems are employed to suggest content, such as books, music, and videos; furthermore, they are often used in e-commerce. In particular, the South Korean film industry recommends movies using a collaborative filtering method based on genres, which is commonly used in film recommendation systems. However, this method can be ineffective when users initially encounter film recommendation services or have specific preferences with respect to movies, such as preferences regarding actors or directors. This motivated us to propose an actor-based recommendation system using the content-based filtering that considers actors' filmography information and the genres of 509 South Korean movies. The effectiveness and performance of the suggested system are evaluated in comparison with those of a traditional genre-oriented recommendation system.

Now a day’s recommendation system take care of the issue of the massive amount of information overload problem and it provides the services to the candidates to concentrate on relevant information on job domain only. The job recommender system plays an important role in the recruitment process of fresher as well as experienced today. Existing job recommender system mainly focuses on content-based filtering to extricate profile content and on collaborative filtering to capture the behaviour of the user in the form of rating. Dynamic nature of job market leads cold start and scalability issues. This problem can be addressed by item-based collaborative filtering with a machine learning technique, it learns job embedding vector and finds similar jobs content-wise. Existing model in job recommender domain uses the confining model to address the cold start and scalability issue and provide better recommendation, but they fail to accept the complex relationships between job description and candidate profile. In this paper, we are proposing a Deep Semantic Structure Algorithm that overcome the issue of the existing system. Deep semantic structure modelling (DSSM) system uses the semantic representation of sparse data and it represent the job description and skill entities in character trigram format which increases the efficacy of the system. We are comparing the results to three variation of DSSM model with two different dataset (Naukari.com and CareerBuilder. com) and it gives satisfactory results. Experimental results shows that the DSSM Embedding model and its other variants are provides promising results in solving cold start problem in comparison with several variants of embedding model. We used Xavier initializer to initialise the model parameter and Adam optimizer to optimize the system performance.

Visual media, in today’s world, has swept across most forms of day to day communication. In the paradigm of generative modelling, restricted Boltzmann machines (RBMs) are used to solve complex tasks such as feature extraction, neuroimaging, collaborative filtering, radar target cognition, etc. In this paper, we implement an unsupervised Boltzmann machine-based time-aware recommendation system (UBMTR) which detects underlying hidden features in user-movie ratings data in connection with the time at which each rating was made (temporal information). The model takes ratings and time as a dual-input and outputs binary values via the contrastive divergence algorithm which samples from a Monte Carlo Markov Chain. Arguably, there exists a correlation between the content requested and the temporal conditions, which is exactly what our model tries to exploit. There is seldom any work in the field of recommender systems built using Boltzmann machines that incorporate temporal information, which necessitates research in this domain. RBMs are adept at pattern completion to tackle missing values, and can deal with imbalanced datasets and unstructured data by encoding raw data into latent variables. Using RBM, the UBMTR outperforms many earlier made attempts made at recommendation systems done through CF and deep learning or their hybridized models.

The remarkable progress of machine learning has led to some state-of-the-art algorithms in personalized recommendation. Previous recommendation algorithms generally learn users' and items' representations based on a user-item rating matrix. However, these methods only consider a user's own preference, but ignore the influence of the user's social circles. In this paper, we propose a novel recommendation algorithm, Self-Attentive Graph Convolution Network with Latent Group Mining and Collaborative Filtering, which consists of Latent Group Mining (LGM) module, Collaborative Embedding (CE) module and Self-Attentive Graph Convolution (SAGC) module. The LGM module analyzes users' social circles by exploring their latent groups and generates group embedding for users and items. The CE module uses a graph embedding method to provide semantic collaborative embedding for users and items. The SAGC module fuses users' (items') collaborative embedding and group embedding by a self-attentive graph convolution network to learn their fine-grained representations for rating prediction. We conduct experiments on different real-world datasets, which validates that our algorithm outperforms the state-of-the-art algorithms.

With the tremendous growth in online information, capturing dynamic users' preferences based on their historical interactions and providing a few desirable items to users have become an urgent service for all businesses. Recurrent neural networks (RNNs) and item-based collaborative filtering (CF) models are commonly used in industries due to their simplicity and efficiency. However, they fail to different contexts that could differently influence current users' decision-making. Also, they are not sufficient to capture multiple users' interests based on features of the interacting items. Besides, they have a limited modeling capability for the evolution of diversity and dynamic user preferences. In this article, we exploit long- and short-term preferences for deep context-aware recommendations (LSCAR) to enhance the next item recommendation's performance by introducing three novel components as follows: 1) the user-contextual interaction module is proposed to capture and differentiate the interaction between contexts and users; 2) the encoded multi-interest module is introduced to capture various types of user interests; and 3) the integrator fusion gate module is used to effectively fuse the related long-term interests to the current short-term part, and the module returns the final user interest representation. Extensive experiments and results for two public datasets demonstrate that the proposed LSCAR outperforms the state-of-the-art models in almost all metrics and could provide interpretable recommendation results.

The ever-increasing popularity of recommendation systems allows users to find appropriate services without excessive effort. However, due to the unstable and complex network environment, the historical behavior data of users are quite sparse in most cases. The inherent drawbacks render preference prediction infeasible for cold-start users and have become a crucial issue to be resolved in recommendation systems. To deal with the problems, we first present a Trust-based Collaborative Filtering (TbCF) algorithm to perform basic rating prediction in a manner consistent with the existing CF methods. Then, we propose the Hybrid Collaborative Filtering Recommendation approach with User-Item-Trust Records (UIThybrid), a novel approach that incorporates user trust into the existing CF-based methods in a harmonious way to supplement rating information. UIThybrid employs multiple perspectives to extract proper services and achieves a good tradeoff between the robustness, accuracy, and diversity of the recommendation. We conduct extensive real-world experiments on the Epinions data set to demonstrate the feasibility and efficiency of UIThybrid.

With the growing number of competing Web services that provide similar functionality, Quality-of-Service (QoS) prediction is becoming increasingly important for various QoS-aware approaches of Web services. Collaborative filtering (CF), which is among the most successful personalized prediction techniques for recommender systems, has been widely applied to Web service QoS prediction. In addition to using conventional CF techniques, a number of studies extend the CF approach by incorporating additional information about services and users, such as location, time, and other contextual information from the service invocations. There are also some studies that address other challenges in QoS prediction, such as adaptability, credibility, privacy preservation, and so on. In this survey, we summarize and analyze the state-of-the-art CF QoS prediction approaches of Web services and discuss their features and differences. We also present several Web service QoS datasets that have been used as benchmarks for evaluating the predition accuracy and outline some possible future research directions.

Modern resource management frameworks guarantee low tail latency for long-running services using the resource over-provisioning method, resulting in serious waste of resources and increasing the service costs greatly. To reduce the over-provisioning cost, we present HRSE, a hybrid resource scaling engine that enables much more efficient resource provisioning for both periodic and non-periodic workloads of long-running services while guaranteeing the tail latency Service Level Objective (SLO). HRSE employs a convolution-based time series analysis to identify periodic patterns in workloads. If periodic patterns are discovered, HRSE estimates the just-right amount of resources based on the periodic features through a top-K based collaborative filtering approach. Otherwise, it leverages wavelet-clustering to capture the short-term patterns in non-periodic workloads and predict the resource demands for the near future. To further enforce the tail latency SLO, HRSE uses an online reprovisioning mechanism that dynamically adjusts the resources to mitigate the performance uncertainty due to workload burstinesses. We fully implement HRSE on top of Docker and conduct extensive experiments using traces from production systems. Testbed experiments show that HRSE is able to increase the average resource utilization to 43% and 45% for periodic and non-periodic workloads respectively while guaranteeing the same tail latency objective.

Nowadays, there are many Web services with similar functionality on the Internet. Users consider Quality of Service (QoS) of the services to select the best service from among them. The prediction of QoS values of the Web services and recommendations of the best service based on these values to the users is one of the major challenges in the web service area. Major studies in this field use collaboration filtering based methods for prediction. The paper introduced prediction methods and divided them into three main categories: memory-based methods, model-based methods, and Collaborative Filtering (CF) methods combined with other methods. In each category, some of the most famous studies were introduced, and then the problems and benefits of each category were reviewed. Finally, we have a discussion about these methods and propose suggestions for future works.

Extensive growth in developing new and efficient methods for tensor factorizations has made their intelligent applications in cyber-physical-social systems (CPSS) a hot research topic. Tensor factorizations facilitate the need for recommendations that are accurate and circumstantial, which pushes the limits of traditional collaborative filtering methods to multifaceted versions based on real intelligent environments. Nevertheless, recommenders in edge-cloud computing require information encapsulated in user models to give useful suggestions on user preferred items, which presents stern privacy trepidations. In this paper, a novel edge-cloud-aided differentially private tucker decomposition scheme is proposed to avert data owner’s private data from being learned by other data owners, untrusted edge and cloud during tucker decomposition for CPSS. Our design dissevers users’ private data computations in tucker decomposition to edges from the cloud, and the cloud is forced to perform perturbed results aggregation while preserving privacy. The scheme employs perturbation to ensure differential privacy, and the perturbation noise components are decomposed into small manageable parts that can be locally and independently resolved by edges. Our extensive experiments on two real datasets show the proposed scheme is efficient and has tolerable side-effects on the results’ utility.

Matrix factorization is a powerful method to implement collaborative filtering recommender systems. This article addresses two major challenges, privacy and efficiency, which matrix factorization is facing. We based our work on DS-ADMM, a distributed matrix factorization algorithm with decent efficiency, to achieve the following two pieces of work: (1) Integrated local differential privacy paradigm into DS-ADMM to provide the privacy-preserving property; (2) Introduced a stochastic quantized function to reduce transmission overheads in ADMM to further improve efficiency. We named our work DS-ADMM++, in which one ’+’ refers to differential privacy, and the other ’+’ refers to quantized techniques. DS-ADMM++ is the first to perform efficient and private matrix factorization under the scenarios of differential privacy and DS-ADMM. We conducted experiments with benchmark data sets to demonstrate that our approach provides differential privacy and excellent scalability with a decent loss of accuracy.

Recommendation systems (RS) play an important role in e-commerce applications as they help the consumers in choosing the required items within reduced time. The traditional methods of collaborative filtering, fail to capture the visual data associated with the items. Visually-aware recommendation systems are upcoming in e-commerce applications that use the visual features of the products rather than the user profiles. Deep learning techniques are used for the classification and prediction in visual recommendation systems. However, the criticality of the visual recommendation system lies in identifying the similar images for a given target image. In this paper, a visual recommendation system is proposed based on Deep Visual Ensemble similarity metric (DVESM) using Convolutional Autoencoder (CAE) neural network for classification. The basic idea is to get a set of trained feature vectors for the image catalogue using CAE and find the similarity between the trained feature vectors and the target feature vector using DVESM method. The proposed methodology of using DVESM has been demonstrated with the state-of-the-art methods on Amazon 2014, 2015 and Street2Shop datasets. The results show that the DVESM method is most suitable for visually aware recommendation systems as it learns an ensemble of metrics to provide recommendations.

Coordination failure reduces match quality among employers and candidates in the job market, resulting in a large number of unfilled positions and/or unstable, short-term employment. Centralized job search engines provide a platform that connects directly employers with job-seekers. However, they require users to disclose a significant amount of personal data, i.e., build a user profile, in order to provide meaningful recommendations. In this paper, we present PrivateJobMatch -- a privacy-oriented deferred multi-match recommender system -- which generates stable pairings while requiring users to provide only a partial ranking of their preferences. PrivateJobMatch explores a series of adaptations of the game-theoretic Gale-Shapley deferred-acceptance algorithm which combine the flexibility of decentralized markets with the intelligence of centralized matching. We identify the shortcomings of the original algorithm when applied to a job market and propose novel solutions that rely on machine learning techniques. Experimental results on real and synthetic data confirm the benefits of the proposed algorithms across several quality measures. Over the past year, we have implemented a PrivateJobMatch prototype and deployed it in an active job market economy. Using the gathered real-user preference data, we find that the match-recommendations are superior to a typical decentralized job market---while requiring only a partial ranking of the user preferences.

Nowadays, most data about social networks, users shopping behaviors, and inter-item relationships etc., can be represented as graph structure. Graph Neural Networks (GNNs) have shown great success in learning meaningful representations for graph data by naturally integrating node information and topological structures. Data used in making social recommendations can also be represented as graph data in the form of user-user social graphs and user-item graphs. In addition, the relationships between items can be represented as graph data, denoted as item-item graph. GNNs provide an unprecedented opportunity to advance social recommendations, yet there are considerable challenges in building GNNs-based social recommendations based on this modelling framework in that (1) users (items) are simultaneously involved in the user-item graph and user-user social graph (item-item graph); (2) user-item graphs not only contain user-item interactions but also include users' opinions on items; and (3) the nature of social relations are heterogeneous among users. In this paper, we propose a novel graph neural network framework (GraphRec+) for social recommendations, which is able to coherently model graph data in order to learn better user and item representations. Comprehensive experiments on three real-world datasets show the effectiveness of the proposed framework.

Nowadays, the Internet is becoming a platform of choice where the number of users and items grows dramatically making recommender systems (RS) the most required and widespread technology. This paper deals with context aware collaborative RS and presents a double contribution that consists of a two Dimensions Contextual Collaborative Recommender System (2DCCRS) and a related application. Our first contribution proposes a new framework for collaborative context aware RS that relies on two key ideas. The first one suggests splitting the context into two parts namely internal and external contexts in order to deal with both internal and external context attributes in different and more appropriate manners. This allows addressing the complexity of the context model in a more effective way. In the second idea, we introduce two concepts; namely the “Stakeholders” and “Aggregation” to effectively alleviate the problems of new user and new item. 2DCCRS is based on a multi-layer architecture. Its highest layer relies on a pre-filtering algorithm that deals with the cold start system problem, and is mainly based on the similarity between the user profile and the items features. The middle layer is based on a collaborative filtering algorithm that takes into account the users’ preferences, interests and priorities; while the deepest layer, which is considered the most relevant in our multilayer architecture, focuses on a post-filtering algorithm in which the recommendations are much more adapted to the user environment. In Our second contribution, we present a case study of 2DCCRS in order to demonstrate the usefulness and effectiveness of the proposed approach. Indeed, we propose a personalized Healthy and Tasty application (H&T) that generates items based on 2DCCRS framework to guide the user toward the healthy and tasty meals that best meet his needs. The obtained results are very promising and show the effectiveness of our proposal.

An effective recommender system can significantly help customers to find desired products and assist business owners to earn more income. Nevertheless, the decision-making process of users is highly complex, not only dependent on the personality and preference of a user, but also complicated by the characteristics of a specific product. For example, for products of different domains (e.g., clothing vs. office products), the product aspects that affect a user's decision are very different. As such, traditional collaborative filtering methods that model only user-item interactions would deliver unsatisfactory recommendation results. In this work, we first divide a product's characteristics into visual and functional aspects. We then contribute a novel probabilistic model, named Visual and Functional Probabilistic Matrix Factorization (VFPMF), to unify the two factors to estimate user preferences on products. Nevertheless, such an expressive model poses efficiency challenge in parameter learning from implicit feedback. To address the technical challenge, we devise a computationally efficient learning algorithm for VFPMF. Furthermore, we provide an online updating procedure of the algorithm, shedding some light on how to adapt our method to real-world recommendation scenario where data continuously streams in. Extensive experiments on four datasets demonstrate the effectiveness of our method.

We propose a novel privacy-preserving QoS forecasting approach - Edge-Laplace QoS (QoS forecasting with Laplace noise in mobile Edge environments). Edge-Laplace QoS is able to accurately and efficiently forecast Quality of Service (QoS) of various Web Services, while effectively protecting user privacy in mobile edge environments. We employ an improved differential privacy method to add dynamic disguises to the original QoS data in the edge environment to protect user data privacy. A collaborative filtering method is adopted to retrieve similar users' accessing records based on geographic locations of their accessed servers for QoS forecasting. We conduct a set of experiments using several public network data sets. The results show that the efficiency of Edge-Laplace QoS is superior to traditional forecasting approaches. Edge-Laplace QoS is also validated to be more suitable for edge environments than traditional privacy-preserving approaches.

Recommender system suggests a personalized recommendation by filtering the information based on users interest. Nowadays, users like to purchase the best possible items and services to spend the shortest span of time. The cross-domain recommendation system is a method of recommendation wherein knowledge is gathered from multiple domains. With respect to the user’s search term from the source domain, most similar items are recommended from the target domain. Semantic similarity between two different items can be achieved through Wpath method using Ontology. PrefixSpan is used for generating sequential patterns and Topseq rule mining algorithm is used for finding the frequent sequential rule. So, this work tries to extend cross domain recommendation by 1) finding the semantic similarity of items using Ontology; 2) applying Collaborative Filtering for finding similar items and users; 3) generating frequent item sequences using PrefixSpan sequential pattern mining algorithm and 4) recommending user preferred items using Topseq rule mining algorithm. The recommender system is evaluated considering precision, recall and F1 Score measures. It finds CD-SPM which yields better F1 Score. The proposed approach also alleviates the new user problem and sparsity problem to some extent.

The usage of recommenders systems is already widespread. Every day people are exposed to different item offerings based on the prediction of their interests and decisions. Context information, such as location, goals, and close entities, plays a key role in the recommendations' accuracy. The use of context histories allows one to identify similar context histories and predict contexts. This article proposes Vulcont, a recommender system based on a context histories' ontology. Vulcont merges the benefits of ontology reasoning with context histories to measure the context history similarity, based on the semantic and ontology properties provided by the context’s domain. Vulcont considers synonymous and classes' relations to measure similarity. After that, a collaborative filtering approach identifies sequences' frequency to identify potential items for recommendation. The proposed recommendation is evaluated and discussed in four scenarios in an offline experiment, which explores the semantic value of context histories. The main contribution of Vulcont is the use of semantic relations and the properties of ontology in a similarity measurement of context histories, which is a data structure more complete than that of single contexts.

Background: The prediction of drug-protein interaction (DPI) plays an important role in drug discovery and repositioning. Unfortunately, traditional experimental validation of DPIs is expensive and time-consuming. Therefore, it is necessary to develop in silico methods for the identification of potential DPIs. Method: In this work, the identification of DPIs was performed by the generated recommendation of the unexplored interaction of the drug-protein bipartite graph. Three kinds of recommenders were proposed to predict the potential DPIs. Results: The simulation results showed that the proposed models obtained good performance in crossvalidation and independent test. Conclusion: Our recommendation strategy based on collaborative filtering can effectively improve the DPI identification performance, especially for certain DPIs lacking chemical structure similarity or genomic sequence similarity.

To accelerate searching an enjoyable holiday resort from massive-scale tourism spots on social media, the TR-DNNMF tourism spots recommendation system combining neural network and matrix decomposition is developed in this work. The model is built upon the architecture of the neural collaborative filtering model. It leverages the generalized matrix decomposition model coupled with the multi-layer neural network model as the pre-training model for training. Subsequently, it integrates the two models to anticipate user’s rating of tourism spots and further recommends the suitable tourism spots. Our model combines the linearity of matrix factorization and the nonlinearity of deep neural network to uncover the potential features of user-scenic spots. This makes the model exhibit high scalability and strong fitting ability. Experiments are conducted based on the domestic tourist attractions from user interaction data. Features that is non-descriptive to the model are discarded to reduce the time and memory consumption. Conclusively, our designed system can offer satisfactory prediction, as evidenced by the competitive accuracies on six experimental data sets.

With the massive growth of Internet-of-Things (IoT) devices, how to provide users with recommendation services in the IoT environment has become a research hotspot. Group discovery, as a prerequisite step of group recommendation that can be used to assist groups of users to select services in IoT-enriched environments, has an important impact on recommendation performance. However, existing group recommendation solutions assume that a user belongs to a specific group and ignore the possible correlation between the user's preferences and other groups' preferences. In addition, existing solutions treat group members as equal individuals and assign them equal weights, which makes it hard to meet the user's accurate recommendation requirements. Furthermore, these methods focus on group members' explicit preference information while ignoring implicit preferences. To address these problems, we propose a group discovery method based on collaborative filtering and knowledge graph (GD-CFKG). This method first uses the attention mechanism to learn the embedding of service entities from knowledge graphs and interaction between users and services to achieve users' own preferences embedding. Considering that the preferences of similar users will help to attain accurate target user's preferences, we then train users' final preferences embedding by collaborative filtering and word2vec method. We conduct experiments to evaluate our approach using the MovieLens and Douban data sets. Experimental results show that our proposed method has better group recommendation performance than those baseline methods.

Food recommendation has attracted increasing attentions to various food-related applications and services. The food recommender models aim to match users’ preferences with recipes, where the key lies in the representation learning of users and recipes. However, ranging from early content-based filtering and collaborative filtering methods to recent hybrid methods , the existing work overlooks the various food-related relations, especially the ingredient-ingredient relations, leading to incomprehensive representations. To bridge this gap, we propose a novel model Food recommendation with Graph Convolutional Network (FGCN), which exploits ingredient-ingredient, ingredient-recipe, and recipe-user relations deeply. FGCN employs the information propagation mechanism and adopts multiple embedding propagation layers to model high-order connectivity across different food-related relations and enhance the representations. Specifically, we develop three types of information propagation: (1) ingredient-ingredient information propagation, (2) ingredient-recipe information propagation, and (3) recipe-user information propagation. To validate the effectiveness and rationality of FGCN, we conduct extensive experiments on a real-world dataset. The results show that the proposed FGCN outperforms the state-of-the-art baselines. Further in-depth analyses reveal that FGCN could alleviate the sparsity issue in food recommendation.

The rapid growth of mobile apps has significantly promoted the use of third-party libraries in mobile app development. However, mobile app developers are now facing the challenge of finding useful third-party libraries for improving their apps, e.g., to enhance user interfaces, to add social features, etc. An effective approach is to leverage collaborative filtering (CF) to predict useful third-party libraries for developers. We employed Matrix Factorization (MF) approaches - the classic CF-based prediction approaches - to make the predictions based on a total of 31,432 Android apps from Google Play. However, our investigation shows that there is a significant lack of diversity in the prediction results - a small fraction of popular third-party libraries dominate the prediction results while most other libraries are ill-served. The low diversity in the prediction results limits the usefulness of the prediction because it lacks novelty and serendipity which are much appreciated by mobile app developers. In order to increase the diversity in the prediction results, we designed an innovative MF-based approach, namely LibSeek, specifically for predicting useful third-party libraries for mobile apps. It employs an adaptive weighting mechanism to neutralize the bias caused by the popularity of third-party libraries. In addition, it introduces neighborhood information, i.e., information about similar apps and similar third-party libraries, to personalize the predictions for individual apps. The experimental results show that LibSeek can significantly diversify the prediction results, and in the meantime, increase the prediction accuracy.

There are large personalized differences among human resources, and the resource recommendation process easily encounters the problem of data loss, resulting in a short length of the final recommended resource and less information about the actual human resources included. To solve this problem, this research proposes a human resource recommendation algorithm based on improved frequent itemset mining. The dataset containing single items is called, the human resource is mined to improve frequent itemset, the positive matrix factorization (PMF) model is used to process the implicit features in human resource, and the similarity parameters of the human resource dataset are calculated. The algorithm of collaborative filtering is used to divide the recommendation mechanism, and the loss of data generated during the recommendation is controlled, thereby completing the construction of the human resource recommendation algorithm. The hardware and software environment for algorithm operation were constructed. The human resource dataset was arranged. Tests were conducted using the recommendation algorithm based on neural network, recommendation algorithm based on item weight ranking and the proposed recommendation algorithm. The test results showed that the proposed recommendation algorithm recommended the longest length of resources and the most information contained within the resources.

Understanding user preference on item context is the key to acquire a high-quality multimedia recommendation. Typically, the pre-existing features of items are derived from pre-trained models (visual features of micro-videos extracted from some neural networks), and then introduced into the recommendation framework (collaborative filtering) to capture user preference. However, we argue that such a paradigm is insufficient to output satisfactory user representations, which hardly profile personal interests well. The key reason is that present works largely leave user intents untouched, then failing to encode such informative representation of users. In this work, we aim to learn multi-level user intents from the co-interacted patterns of items, so as to obtain high-quality representations of users and items and further enhance the recommendation performance. Towards this end, we develop a novel framework, named Hierarchical User Intent Graph Network, which exhibits user intents in a hierarchical graph structure, from the fine-grained to coarse-grained intents. In particular, we get the multi-level user intents by recursively performing two operations: 1) intra-level aggregation, which distills the signal pertinent to user intents from co-interacted item graphs; and 2) inter-level aggregation, which constitutes the supernode in higher levels to model coarser-grained user intents via gathering the nodes representations in the lower ones. Then, we refine the user and item representations as a distribution over the discovered intents, instead of simple preexisting features. To demonstrate the effectiveness of our model, we conducted extensive experiments on three public datasets. Our model achieves significant improvements over the state-of-the-art methods, including MMGCN and DisenGCN. Furthermore, by visualizing the item representations, we provide the semantics of user intents.

Template matching between synthetic aperture radar (SAR) and optical image is a meaningful and important topic for remote sensing tasks. In this letter, a deep learning framework based on Siamese structure and U-Net is proposed. First, a sparse 3-D transform-domain collaborative filtering (BM3D) for SAR image denoising is applied. Then, deep features of SAR and optical images are extracted from two branches of the proposed Siamese U-Net network. Finally, a cross correlation layer is used to generate the heatmap of image pairs based on the deep features extracted, and the peak maximal location of the heatmap is seen as the best matching location result. During training, a balanced loss between ground truth and prediction is used to get trained model weights in order to make a balance between positive samples and negative samples. The experiments on the same test dataset demonstrate that the proposed method improves the matching accuracy and precision to some degree in comparison with existing template matching methods for SAR and optical images.