User Cold-start Problem Research Articles

IBCFaiCDR: Auxiliary data-driven item-based collaborative filtering in cross-domain RSs to address user cold start problem

The adoption of Recommender Systems (RSs) in various services is imperative in the present era. One of the inherent challenge faced by RSs is the user cold start problem (UCS) and it occurs when there is a lack of enough data available for a new user, which restricts the capacity to provide accurate recommendations. Researchers have conducted investigations into the utilization of auxiliary data like social network data, review text, demographic information etc., to augment the RSs ability to learn and understand the user's preferences, with the aim of solving this issue. The provided information is inadequate due to the restricted level of user engagement within the specified domain. The researchers utilize a Cross-Domain RS (CDR) that incorporates information from multiple domains to provide personalized suggestions to users. Item Based Collaborative Filtering (IBCF), which utilizes item-item similarity, is commonly used when dealing with sparse data. The suggested collaborative filtering technique employs IBCF which uses the item similarity obtained with item features. These features are generated by the proposed approach IBCFaiCDR's model, trained on source domain data such as product images and reviews. The efficacy of the proposed approach is assessed using a large dataset from Amazon, consisting of user interactions across many categories. The results on target domain, evaluated using MAE and RMSE, indicate that the inclusion of auxiliary information (image + text) enhances the RS performance for new users.

EduLGCL: Local-global contrastive learning model for education recommendation

Contrastive learning has been used in recommendations to learn user and item representations from sparse and long-tail user-item interaction histories. Recommendations applied in education have several key challenges. Firstly, the frequency of student-course interactions is lower, resulting in limited data. Secondly, existing models rely on multimodal data for multi-objective recommendations and they limit the model’s generalizability. Lastly, it is important to consider the impact of static features on different students. Aiming at addressing these challenges, a novel course recommendation system based on Local-Global Contrastive Learning called as EduLGCL is proposed, in which the mutual information between course features and student features is computed to select course features. After expanding the connections, the relationship between students and courses is described from different perspectives. Multiple graph convolutional operations are performed on the interaction history graph which can connect students and courses and represent student clusters. Through the feature extraction layer, the final student representation is obtained. Extensive experiments were conducted on three public datasets and a course dataset collected from a real-world environment to validate the performance of the EduLGCL. The results demonstrate that EduLGCL outperforms baseline methods, particularly in handling user cold-start problems. Our code is available at https://github.com/mintZYJ/EduLGCL.

SSTP: Social and Spatial-Temporal Aware Next Point-of-Interest Recommendation

The expansion of available information in location-based social networks (LBSNs) has led to information overload, making it urgent to discover users’ next point-of-interest (POI). Some existing works only consider certain modal information in LBSNs and do not transform them into high-dimensional structures, which hinders the alleviation of the data sparsity problem. Moreover, many approaches rely solely on social relationships, making it difficult to recommend POIs to new users without association information. To tackle these challenges, we propose a social- and spatial–temporal-aware next point-of-Interest (SSTP) recommendation model. SSTP uses two feature encoders based on self-attention mechanism and gate recurrent unit to model users’ check-in enhancement sequence hierarchically. We also design a random neighborhood sampling approach to mine user social relationships, thus alleviating the user cold start problem. Finally, we propose a geographical-aware graph attention network to learn the sensitivity of users to distance. Extensive experiments on two real-world datasets show that SSTP outperforms state-of-the-art models, improving Hit@k by 2.26–6.55% and MAP@k by 3.49–6.55%. Moreover, SSTP has better performance on sparse data, with an average improvement of 6.09% on the Hit@k. The code can be downloaded at https://github.com/Rih0/sstp.

A Deep Learning Approach towards Cold Start Problem in Movie Recommendation System

Recommendation systems play an important role for e-commerce websites to make profits. It has a variety of applications in different domains. There are three types of categories in which recommendation systems are classified i.e. content based, collaborative and hybrid systems. These systems suffer when a redundant amount of information is not available to provide recommendations. This problem is known as the cold start problem. In this digital era, it is possible to collect meta information about a user and provide rich recommendations. Various approaches such as social media analysis, graph networks have been proposed to solve this problem. But they lack personalization and generate irrelevant recommendations affecting the system performance. The objective of this work is to resolve new user cold start problem in movie recommendation systems using a deep learning approach that utilizes demographic attributes to cluster similar users. This embedding is given to the deep neural network to generate the recommendations. From the analysis done, we verify the effectiveness of our approach..

SGNR: A Social Graph Neural Network Based Interactive Recommendation Scheme for E-Commerce

Interactive Recommendation (IR) formulates the recommendation as a multi-step decision-making process which can actively utilize the individuals' feedback in multiple steps and optimize the long-term user benefit of recommendation. Deep Reinforcement Learning (DRL) has witnessed great application in IR for e-commerce. However, user cold-start problem impairs the learning process of the DRL-based recommendation scheme. Moreover, most existing DRL-based recommendations ignore user relationships or only consider the single-hop social relationships, which cannot fully utilize the social network. The fact that those schemes can not capture the multiple-hop social relationships among users in IR will result in a sub-optimal recommendation. To address the above issues, this paper proposes a Social Graph Neural network-based interactive Recommendation scheme (SGNR), which is a multiple-hop social relationships enhanced DRL framework. Within this framework, the multiple-hop social relationships among users are extracted from the social network via the graph neural network which can sufficiently take advantage of the social network to provide more personalized recommendations and effectively alleviate the user cold-start problem. The experimental results on two real-world datasets demonstrate that the proposed SGNR outperforms other state-of-the-art DRL-based methods that fail to consider social relationships or only consider single-hop social relationships.

MFPCDR: A Meta-Learning-Based Model for Federated Personalized Cross-Domain Recommendation

Cross-domain recommendation systems frequently require the use of rich source domain information to improve recommendations in the target domain, thereby resolving the data sparsity and cold-start problems, whereas the majority of existing approaches frequently require the centralized storage of user data, which poses a substantial risk of privacy breaches. Compared to traditional recommendation systems with centralized data, federated recommendation systems with multiple clients trained collaboratively have significant privacy benefits in terms of user data. While users’ interests are often personalized, meta-learning can be used to learn users’ personalized preferences, and personalized preferences can help models make recommendations in cold-start scenarios. We use meta-learning to learn the personalized preferences of cold-start users. Therefore, we offer a unique meta-learning-based federated personalized cross-domain recommendation model that discovers the personalized preferences for cold-start users via a server-side meta-recommendation module. To avoid compromising user privacy, an attention mechanism is used on each client to find transferable features that contribute to knowledge transfer while obtaining embeddings of users and items; each client then uploads the weights to the server. The server accumulates weights and delivers them to clients for update. Compared to traditional recommendation system models, our model can effectively protect user privacy while solving the user cold-start problem, as we use an attention mechanism in the local embedding module to mine the source domain for transferable features that contribute to knowledge transfer. Extensive trials on real-world datasets have demonstrated that our technique effectively guarantees speed while protecting user privacy.

A Deep Reinforcement Learning Recommender System With Multiple Policies for Recommendations

Deep reinforcement learning (DRL) based recommender systems are suitable for user cold-start problems as they can capture user preferences progressively. However, most existing DRL-based recommender systems are suboptimal, since they use the same policy to suit the dynamics of different users. We reformulate recommendation as a multitask Markov Decision Process, where each task represents a set of similar users. Since similar users have closer dynamics, a task-specific policy is more effective than a single universal policy for all users. To make recommendations for cold-start users, we use a default policy to collect some initial interactions to identify the user task, after which a task-specific policy is employed. We use Q-learning to optimize our framework and consider the task uncertainty by the mutual information regarding tasks. Experiments are conducted on three real-world datasets to verify the effectiveness of our proposed framework.

Collaborative Filtering Model of Graph Neural Network Based on Random Walk

This paper proposes a novel graph neural network recommendation method to alleviate the user cold-start problem caused by too few relevant items in personalized recommendation collaborative filtering. A deep feedforward neural network is constructed to transform the bipartite graph of user–item interactions into the spectral domain, using a random wandering method to discover potential correlation information between users and items. Then, a finite-order polynomial is used to optimize the convolution process and accelerate the convergence of the convolutional network, so that deep connections between users and items in the spectral domain can be discovered quickly. We conducted experiments on the classic dataset MovieLens-1M. The recall and precision were improved, and the results show that the method can improve the accuracy of recommendation results, tap the association information between users and items more effectively, and significantly alleviate the user cold-start problem.

User Cold-start Problem in Multi-armed Bandits: When the First Recommendations Guide the User’s Experience

Nowadays, Recommender Systems have played a crucial role in several entertainment scenarios by making personalised recommendations and guiding the entire users’ journey from their first interaction. Recent works have addressed it as a Contextual Bandit by providing a sequential decision model to explore items not tried yet (or not tried enough) or exploit the best options learned so far. However, this work noticed these current algorithms are limited to naive non-personalised approaches in the first interactions of a new user, offering random or most popular items. Through experiments in three domains, we identify a negative impact of these first choices. Our study indicates that the bandit performance is directly related to the choices made in the first trials. Then, we propose a new approach to balance exploration and exploitation in the first interactions and handle these drawbacks. This approach is based on the Active Learning theory to catch more information about the new users and improve their long-term experience. Our idea is to explore the potential information gain of items that can also please the user’s taste. This method is named Warm-Starting Contextual Bandits, and it statistically outperforms 10 benchmarks in the literature in the long run.

HyperRS: Hypernetwork-Based Recommender System for the User Cold-Start Problem

Meta-learning has been proven to be effective for the cold-start problem of recommender systems. Many meta-learning recommender systems that are designed for the user cold-start problem are gradient-based. They use a global parameter learned from existing users to initialize the recommender system parameter for new users that provides a personalized recommendation with limited user-item interactions. Many systems require users’ demographic information to learn the global parameter. This requirement raises privacy concerns, and demographic information is not always available. In addition, some of the gradient-based systems need dozens or even hundreds of user-item interactions from existing users to learn the global parameter. This requirement is difficult to satisfy in specific scenarios in which active users and their item interactions are rare. Moreover, gradient-based meta-learning systems rarely capture user preferences over different item attributes, as updating the corresponding weights requires many optimization steps. We proposed HyperRS, a Hypernetwork-based Recommender System, for the user cold-start problem. Our system does not rely on demographic information to provide personalized recommendations. In our system, a hypernetwork generates all weights in the underlying recommender system. The hypernetwork enables the weights to adapt quickly to capture user interest in both item attributes and the contents of the item attributes. The experimental results show that our method outperforms several state-of-the-art meta-learning recommender systems for the user cold-start problem.

Enhancing Personalized Recommendation by Transductive Support Vector Machine and Active Learning

As an important component of information service networks, personalized recommendation technology provides users with better options and enables them to obtain information anytime and anywhere. Collaborative filtering (CF) is a successful and widely used form of this technology. However, the traditional CF recommendation algorithm is ineffective in environments with frequent entry of new users and high levels of data sparsity. For new users in the system, few or no scores, labels, or other such information is available, leading to the user cold start problem. Simultaneously, data sparsity leads to the selection of unreasonable neighbors, which reduces the recommendation accuracy. In addition, the traditional CF recommendation algorithm ignores the inherent connections between users’ preferences and their basic information (such as demographics). Users with similar demographic information are likely to have similar preferences, which can serve as a good basis for finding neighbors. To address the aforementioned problems, we propose a recommendation model that combines active learning (AL) and a semi-supervised transductive support vector machine (TSVM). To enable neighbors to be found quickly and accurately, similar users are clustered together on the basis of their basic information. Then, the TSVM-based classifier is trained on each cluster. To improve the quality of sample labeling and thus the classifier performance, an active learning method based on the distance strategy and a multiclassifier voting mechanism is implemented. Finally, the TSVM-based recommendation model is trained on the labeled samples. The extensive experiments conducted using a real data set from MovieLens demonstrate that the proposed model effectively alleviates the aforementioned cold start and data sparsity problems.

A Machine Learning Approach for Solving the Frozen User Cold-Start Problem in Personalized Mobile Advertising Systems

A domain that has gained popularity in the past few years is personalized advertisement. Researchers and developers collect user contextual attributes (e.g., location, time, history, etc.) and apply state-of-the-art algorithms to present relevant ads. A problem occurs when the user has limited or no data available and, therefore, the algorithms cannot work well. This situation is widely referred in the literature as the ‘cold-start’ case. The aim of this manuscript is to explore this problem and present a prediction approach for personalized mobile advertising systems that addresses the cold-start, and especially the frozen user case, when a user has no data at all. The approach consists of three steps: (a) identify existing datasets and use specific attributes that could be gathered from a frozen user, (b) train and test machine learning models in the existing datasets and predict click-through rate, and (c) the development phase and the usage in a system.

Learning to Learn a Cold-start Sequential Recommender

The cold-start recommendation is an urgent problem in contemporary online applications. It aims to provide users whose behaviors are literally sparse with as accurate recommendations as possible. Many data-driven algorithms, such as the widely used matrix factorization, underperform because of data sparseness. This work adopts the idea of meta-learning to solve the user’s cold-start recommendation problem. We propose a meta-learning-based cold-start sequential recommendation framework called metaCSR, including three main components: Diffusion Representer for learning better user/item embedding through information diffusion on the interaction graph; Sequential Recommender for capturing temporal dependencies of behavior sequences; and Meta Learner for extracting and propagating transferable knowledge of prior users and learning a good initialization for new users. metaCSR holds the ability to learn the common patterns from regular users’ behaviors and optimize the initialization so that the model can quickly adapt to new users after one or a few gradient updates to achieve optimal performance. The extensive quantitative experiments on three widely used datasets show the remarkable performance of metaCSR in dealing with the user cold-start problem. Meanwhile, a series of qualitative analysis demonstrates that the proposed metaCSR has good generalization.

Exploiting MUSIC model to solve cold-start user problem in content-based music recommender systems

The new user cold-start problem is a grand challenge in content-based music recommender systems. This happens when the systems do not have sufficient information regarding the user’s preferences. Towards solving this problem, in this study, a rating prediction framework is proposed. The proposed framework allows the systems to predict the user’s rating scores for unrated musical pieces, by which good recommendations can be generated. The core idea here is to leverage the so-called MUSIC model, i.e., a five-factor musical preference model, which is characterized by Mellow, Unpretentious, Sophisticated, Intense, and Contemporary as the user’s musical preference profiles. When a user newly joins the systems, the first five-factor musical preference profile is established based on the user’s age and brain type information which is extracted from questionnaires. When the user experiences the systems for a certain period, his/her rating scores for experienced musical pieces are utilized for generating the second five-factor musical preference profile. The recommendations are then provided based on the rating scores predicted from a non-linear combination of these two five-factor musical preference profiles. The results demonstrated the effectiveness of the five-factor musical preference in alleviating the new user cold-start problem. In addition, the proposed method can potentially provide high-quality recommendations.

WhatsNextApp: LSTM-Based Next-App Prediction With App Usage Sequences

Next app prediction can help enhance user interface design, pre-loading of apps, and network optimizations. Prior work has explored this topic, utilizing multiple different approaches but challenges like the user cold-start problem, data sparsity, and privacy concerns related to contextual data like location histories, persist. The user cold-start problem occurs when a user has recently registered to the smartphone app system and there is not enough information about his/her preferences and his/her history of smartphone usage. In this work, we try to address the above issues. We introduce WhatsNextApp, an approach based on LSTM (Long Short-Term Memory) networks using sequences of app usage logs. Our approach is inspired by Word Embeddings and treats sequences of app usage logs as sequences of words. We collect a real-life data set consisting of 975 Android users with over 22 million app usage events. We build a generic (user-independent) WhatsNextApp model and the evaluation with our data set shows that it outperforms related studies for existing users where we achieve a recall@8 (recall for the top 8 apps) of 92%. For the user cold-start problem with the 500 most frequent apps, we achieve a recall@8 of 82.7%.

New Strategy Based on RBF Network to Develop a Collaborative Filtering Recommender System

Collaborative filtering is a popular recommendation algorithm. It predicts user's interests according to the ratings or behaviour of other users in the system. However, the collaborative filtering recommender system suffers from several major limitations including scalability, sparsity, and cold start. In this paper, a collaborative filtering recommendation approach using radial basis function (RBF) network and power method is proposed. The proposed system has offline and online phases. In the offline phase, the sparse user-item rating matrix is completed by using RBF network based on Cover's theorem on the separability of patterns. RBF network learning is done by unsupervised kernel-based fuzzy c-means clustering algorithm for selecting RBF centers, and supervised gradient descend method for selecting RBF weights. In the offline phase, we predict non-rated items of a user. Then the full rating matrix is used to rank all the users. The ranking is done by solving an eigenvalue problem. This paper overcomes the scalability problem by clustering the users, the sparsity problem by completing the sparse rating matrix, and the new user cold start problem by recommending the top rated items of the high-ranked user. The results of the experiments, on the benchmark data sets, show that the proposed system produces high quality recommendation, in terms of accuracy and quality.

Genre Familiarity Correlation-Based Recommender Algorithm for New User Cold Start Problem

The advancement of web services paved the way to the accumulation of a tremendous amount of information into the world wide web. The huge pile of information makes it hard for the user to get the required information at the right time. Therefore, to get the right item, recommender systems are emphasized. Recommender algorithms generally act on the user information to render recommendations. In this scenario, when a new user enters the system, it fails in rendering recommendation due to unavailability of user information, resulting in a new user problem. So, in this paper, a movie recommender algorithm is constructed to address the prevailing new user cold start problem by utilizing only movie genres. Unlike other techniques, in the proposed work, familiarity of each movie genre is considered to compute the genre significance value. Based on genre significance value, genre similarity is correlated to render recommendations to a new user. The evaluation of the proposed recommender algorithm on real-world datasets shows that the algorithm performs better than the other similar approaches.

Tag-Aware Recommender System Based on Deep Reinforcement Learning

Recently, the application of deep reinforcement learning in the recommender system is flourishing and stands out by overcoming drawbacks of traditional methods and achieving high recommendation quality. The dynamics, long-term returns, and sparse data issues in the recommender system have been effectively solved. But the application of deep reinforcement learning brings problems of interpretability, overfitting, complex reward function design, and user cold start. This study proposed a tag-aware recommender system based on deep reinforcement learning without complex function design, taking advantage of tags to make up for the interpretability problems existing in the recommender system. Our experiment is carried out on the MovieLens dataset. The result shows that the DRL-based recommender system is superior than traditional algorithms in minimum error, and the application of tags have little effect on accuracy when making up for interpretability. In addition, the DRL-based recommender system has excellent performance on user cold start problems.

An ontology-based hybrid e-learning content recommender system for alleviating the cold-start problem

An e-learning recommender system (RS) aims to generate personalized recommendations based on learner preferences and goals. The existing RSs in the e-learning domain still exhibit drawbacks due to its inability to consider the learner characteristics in the recommendation process. In this paper, we are dealing with the new user cold-start problem, which is a major drawback in e-learning content RSs. This problem can be mitigated by incorporating additional learner data in the recommendation process. This paper proposes an ontology-based (OB) content recommender system for addressing the new user cold-start problem. In the proposed recommendation model, ontology is used to model the learner and learning objects with their characteristics. Collaborative and content-based filtering techniques are used in the recommendation model to generate the top N recommendations based on learner ratings. Experiments were conducted to evaluate the performance and prediction accuracy of the proposed model in cold-start conditions using the evaluation metrics mean absolute error, precision and recall. The proposed model provides more reliable and personalized recommendations by making use of ontological domain knowledge.

On deep neural network for trust aware cross domain recommendations in E-commerce

Over the years, cross-domain and trust-based recommendation systems are proven to be very helpful in solving issues pertaining to data sparsity and cold start. Many e-commerce sites used recommender systems as business tools for increasing their sale productivity and help their customers in finding suitable products. However, due to sparse rating and lack of historical information, such systems cannot generate effective recommendations. Matrix factorization and deep learning techniques have been the focus of research community for the last few years to solve the problem of data sparsity and cold start. In this paper, we have proposed a model called Trust Aware Cross-Domain Deep Neural Matrix Factorization (TCrossDNMF) that predicts rating of an item for an active user and solves user cold start problem in the cross-domain scenario of ‘User Overlap’ in e-commerce system. TCrossDNMF model is divided into four main steps: i) Features learning that learns the users’ features using a latent factor model and then finds the similarity between users of source and target domains. As the users are shared between two domains, the proposed model learns the common information and transfers the knowledge from a source to target domain. ii) Ranking that finds set of similar users (neighbors), and then filters out the dissimilar users based on similarity threshold θ, and then generates a bipartite trust graph from these reduced set of users and executes Ant Colony Optimization, to find trustworthy neighbors for an active user. iii) Weighting computes the trust degree between an active user and his or her top-k neighbors. iv) Prediction that trains the TCrossDNMF model using multilayer perceptron (MLP) and generalized matrix factorization (GMF) by representing user-item interactions in higher dimensions and ensembles the GMF and MLP with trust information for rating prediction. We evaluated proposed model on a real dataset collected from a popular e-commerce retail service ‘AliExpress’. We used categories available in ‘AliExpress’ as source domain and a target domain. For observing the performance of proposed model, we took six domains that have a higher ratio of sparsity. The proposed model is evaluated by using MAE, RMSE and F-measure metrics and compared it with baselines. The experiments show that the proposed model is a viable solution for the mentioned problem with significant improvements in results.