Learning Based Recommender Systems Research Articles

Ownership Verification for Federated Recommendation

Most federated learning-based recommender systems allow clients to access a well-trained high-quality model locally, which provides adversaries with the opportunity to infringe the legitimate copyright of the model. In response, we study an emerging and important problem, i.e., copyright protection of a federated recommendation model, which has not yet been addressed in the community of federated learning or recommender systems. We propose the first backdoor-based ownership verification scheme for federated recommendation called OVFR, which enables the server to claim its ownership for a given suspicious recommendation model. Firstly, we propose to generate a trigger set tailored to recommendation scenarios. In particular, we generate some fake users and items, and then construct a set of fake users with fake interaction records as a trigger set. Moreover, we ensure that the distribution of the popularity of the fake items follows a long-tailed distribution for the effectiveness of the incorporated watermarking. To provide robustness assurance, we propose two different hybrid strategies to make the embeddings of the fake items similar to those of the real items. Secondly, we focus on effectively learning from a trigger set for recommendation scenarios. In particular, we design a mean square error (MSE) loss function and a contrastive loss function for incorporating the backdoor-based watermarking into the item embeddings, since the item embeddings are often more valuable and easier to be accessed than other parameters of a federated recommendation model. We then design a contrastive loss function to reduce the risk of the fake items being detected. Extensive experiments on three public datasets show the effectiveness of our OVFR in terms of ownership verification, model performance, and robustness.

ELECTIVE RECOMMENDATION SYSTEM

Our digital lives in the modern world are fueled by data. We use recommendation engines to help us choose which goods, services, and information to purchase, and they have become an integral part of our digital life. This paper has covered a lot of ground on the changing field of deep learning-based recommendation systems. The evaluation of recommendation systems, individualized recommendation methods, and the integration of several data sources are the primary areas of study. The ethical and privacy issues surrounding recommendation systems are also covered. A critical evaluation of the state of recommendation systems today has been provided in order to provide insightful information for future developments in this field. Keywords: Recommendation systems, collaborative filtering, elective course recommendation, Singular Value Decomposition (SVD), personalized recommendations, academic decision-making, machine learning, data integration, ethical concerns, performance evaluation, RMSE, MAE

A Review of Applications of Deep Learning Techniques in Recommender Systems

Abstract. Nowadays, with tons of information brought by the development of the Internet, recommender systems are becoming more and more popular, and they are affecting many aspects of peoples daily lives. When people use the search engine, shop on e-commerce platforms or watch videos on video software, they are enjoying the content provided by recommender systems. Deep learning techniques also gained a rapid development recently due to their strengths in dealing with complex tasks. Deep learning techniques have triumphed in many areas. Also, there are more efforts contributed to the deep learning based recommender system. However, very few studies focused on giving a detailed review of deep -learning-based recommender system , and these reviews were usually conducted several years ago, which cannot reflect the latest research trends. Hence, the aim of this paper is to summary the deep learning techniques used in recommender systems. A classification scheme is given, and some possible future directions are pointed out.

A Comprehensive Survey on Deep Learning-based Recommender Systems for Market Analysis

A Comprehensive Survey on Deep Learning-based Recommender Systems for Market Analysis

A Recommendation System for Trigger-Action Programming Rules via Graph Contrastive Learning.

Trigger-action programming (TAP) enables users to automate Internet of Things (IoT) devices by creating rules such as "IF Device1.TriggerState is triggered, THEN Device2.ActionState is executed". As the number of IoT devices grows, the combination space between the functions provided by devices expands, making manual rule creation time-consuming for end-users. Existing TAP recommendation systems enhance the efficiency of rule discovery but face two primary issues: they ignore the association of rules between users and fail to model collaborative information among users. To address these issues, this article proposes a graph contrastive learning-based recommendation system for TAP rules, named GCL4TAP. In GCL4TAP, we first devise a data partitioning method called DATA2DIV, which establishes cross-user rule relationships and is represented by a user-rule bipartite graph. Then, we design a user-user graph to model the similarities among users based on the categories and quantities of devices that they own. Finally, these graphs are converted into low-dimensional vector representations of users and rules using graph contrastive learning techniques. Extensive experiments conducted on a real-world smart home dataset demonstrate the superior performance of GCL4TAP compared to other state-of-the-art methods.

On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems

Reinforcement learning serves as a potent tool for modeling dynamic user interests within recommender systems, garnering increasing research attention of late. However, a significant drawback persists: its poor data efficiency, stemming from its interactive nature. The training of reinforcement learning-based recommender systems demands expensive online interactions to amass adequate trajectories, essential for agents to learn user preferences. This inefficiency renders reinforcement learning-based recommender systems a formidable undertaking, necessitating the exploration of potential solutions. Recent strides in offline reinforcement learning present a new perspective. Offline reinforcement learning empowers agents to glean insights from offline datasets and deploy learned policies in online settings. Given that recommender systems possess extensive offline datasets, the framework of offline reinforcement learning aligns seamlessly. Despite being a burgeoning field, works centered on recommender systems utilizing offline reinforcement learning remain limited. This survey aims to introduce and delve into offline reinforcement learning within recommender systems, offering an inclusive review of existing literature in this domain. Furthermore, we strive to underscore prevalent challenges, opportunities, and future pathways, poised to propel research in this evolving field.

GraphRec-based Korean expert recommendation using author contribution index and the paper abstracts in marine

GraphRec-based Korean expert recommendation using author contribution index and the paper abstracts in marine

Performance analysis of three recommendation algorithms on Amazon datasets

Recommendation systems play a crucial role in enhancing user satisfaction and driving sales for businesses. They are essential in todays marketplaces, as they are able to suggest products and services that may interest a particular individual based on their past purchases. In this paper, empirical research is conducted on three distinct subsets of the Amazon dataset, namely Sports & Outdoors, Movies & TV, and Video Games, to comprehensively evaluate the performance of three distinct recommendation methods based on deep learning algorithms. These methods include the dot product method, (an updated version of the singular value decomposition algorithm), the neural network method, and the neural collaborative filtering model with natural language processing method. The results of this study reveal that deep learning-based recommendation systems can achieve more accurate results compared to traditional recommendation systems for three types of products. The implementation of these methods on Amazons dataset can help improve sales by correctly identifying customers interests and suggesting relevant items.

Enhanced Analysis of Hierarchical Clustering Techniques for Recommendation Systems using Integrated Deep Learning

Machine learning is an effective technique for optimizing real-time electronics product data analysis. It can efficiently handle large electronics product datasets, reducing processing time and resource requirements for generating insights. This study assesses the current status of methods and applications for optimizing real-time data analysis by examining existing research in machine learning-based recommendation systems for electronic products. The indicated subjects encompass using machine learning algorithms to discern characteristics and correlations from large datasets, applying machine learning for prognostic analytics and projection, and utilizing machine learning to identify anomalies. The paper provides examples of machine learning-based evaluation optimization solutions that focus on utilizing unorganized data and delivering real-time dashboards. Presented here is a discussion on the complex challenges and potential benefits associated with utilizing machine learning to optimize real-time data processing. Machine learning may efficiently expedite real-time data assessment while delivering precise and timely outcomes

Latest advances in deep learning-based recommender systems

Latest advances in deep learning-based recommender systems

A multi-task deep reinforcement learning-based recommender system for co-optimizing energy, comfort, and air quality in commercial buildings with humans-in-the-loop

Abstract We introduce a novel human-centric deep reinforcement learning recommender system designed to co-optimize energy consumption, thermal comfort, and air quality in commercial buildings. Existing approaches typically optimize these objectives separately or focus solely on controlling energy-consuming building resources without directly engaging occupants. We develop a deep reinforcement learning architecture based on multitask learning with humans-in-the-loop and demonstrate how it can jointly learn energy savings, comfort, and air quality improvements for different building and occupant actions. In addition to controlling typical building resources (e.g., thermostat setpoint), our system provides real-time actionable recommendations that occupants can take (e.g., move to a new location) to co-optimize energy, comfort, and air quality. Through real deployments across multiple commercial buildings, we show that our multitask deep reinforcement learning recommender system has the potential to reduce energy consumption by up to 8% in energy-focused optimization, improve all objectives by 5–10% in joint optimization, and improve thermal comfort by up to 21% in comfort and air quality-focused optimization compared to existing solutions.

Deep learning-based recommendation system for metal-organic frameworks (MOFs).

This work presents a recommendation system for metal-organic frameworks (MOFs) inspired by online content platforms. By leveraging the unsupervised Doc2Vec model trained on document-structured intrinsic MOF characteristics, the model embeds MOFs into a high-dimensional chemical space and suggests a pool of promising materials for specific applications based on user-endorsed MOFs with similarity analysis. This proposed approach significantly reduces the need for exhaustive labeling of every material in the database, focusing instead on a select fraction for in-depth investigation. Ranging from methane storage and carbon capture to quantum properties, this study illustrates the system's adaptability to various applications.

Ontology and Machine Learning-Based Recommender System for Teacher Resource Personalization

Ontology and Machine Learning-Based Recommender System for Teacher Resource Personalization

Contrastive Self-supervised Learning in Recommender Systems: A Survey

Deep learning-based recommender systems have achieved remarkable success in recent years. However, these methods usually heavily rely on labeled data (i.e., user-item interactions), suffering from problems such as data sparsity and cold-start. Self-supervised learning, an emerging paradigm that extracts information from unlabeled data, provides insights into addressing these problems. Specifically, contrastive self-supervised learning, due to its flexibility and promising performance, has attracted considerable interest and recently become a dominant branch in self-supervised learning-based recommendation methods. In this survey, we provide an up-to-date and comprehensive review of current contrastive self-supervised learning-based recommendation methods. Firstly, we propose a unified framework for these methods. We then introduce a taxonomy based on the key components of the framework, including view generation strategy, contrastive task, and contrastive objective. For each component, we provide detailed descriptions and discussions to guide the choice of the appropriate method. Finally, we outline open issues and promising directions for future research.

Ensemble machine learning-based recommendation system for effective prediction of suitable agricultural crop cultivation.

Agriculture is the most critical sector for food supply on the earth, and it is also responsible for supplying raw materials for other industrial productions. Currently, the growth in agricultural production is not sufficient to keep up with the growing population, which may result in a food shortfall for the world's inhabitants. As a result, increasing food production is crucial for developing nations with limited land and resources. It is essential to select a suitable crop for a specific region to increase its production rate. Effective crop production forecasting in that area based on historical data, including environmental and cultivation areas, and crop production amount, is required. However, the data for such forecasting are not publicly available. As such, in this paper, we take a case study of a developing country, Bangladesh, whose economy relies on agriculture. We first gather and preprocess the data from the relevant research institutions of Bangladesh and then propose an ensemble machine learning approach, called K-nearest Neighbor Random Forest Ridge Regression (KRR), to effectively predict the production of the major crops (three different kinds of rice, potato, and wheat). KRR is designed after investigating five existing traditional machine learning (Support Vector Regression, Naïve Bayes, and Ridge Regression) and ensemble learning (Random Forest and CatBoost) algorithms. We consider four classical evaluation metrics, i.e., mean absolute error, mean square error (MSE), root MSE, and R 2, to evaluate the performance of the proposed KRR over the other machine learning models. It shows 0.009 MSE, 99% R 2 for Aus; 0.92 MSE, 90% R 2 for Aman; 0.246 MSE, 99% R 2 for Boro; 0.062 MSE, 99% R 2 for wheat; and 0.016 MSE, 99% R 2 for potato production prediction. The Diebold-Mariano test is conducted to check the robustness of the proposed ensemble model, KRR. In most cases, it shows 1% and 5% significance compared to the benchmark ML models. Lastly, we design a recommender system that suggests suitable crops for a specific land area for cultivation in the next season. We believe that the proposed paradigm will help the farmers and personnel in the agricultural sector leverage proper crop cultivation and production.

Sistem Rekomendasi Program Studi Sarjana Berbasis Machine Learning Untuk Model Klasifikasi Calon Mahasiswa Baru

The Recommendation System can produce system requirements data that is more descriptive and easy to implement into software. Recommendation methods are combined to form more comprehensive recommendations based on fermat points. The education sector has never been indifferent to new technologies, and eventually switched to using the Internet. Prior to conducting this research, a review was carried out on various previous research results related to the lack of the role of knowledge space and user preferences in the data visualization recommendation system [3]. Broadly speaking, this study uses the method of recommending the Analysis and Discussion system. One of the main elements that must be considered in the system analysis stage is software problems, because the software used must be in accordance with the problem to be solved. In this stage, the search and collection of data and knowledge obtained by the expert system are carried out. A machine learning-based recommendation system for undergraduate study programs can help prospective new students choose the right study program according to their interests and talents. The classification model used can produce fairly high accuracy in recommending undergraduate study programs to prospective new students.

Improving Bug Assignment and Developer Allocation in Software Engineering through Interpretable Machine Learning Models

Software engineering is a comprehensive process that requires developers and team members to collaborate across multiple tasks. In software testing, bug triaging is a tedious and time-consuming process. Assigning bugs to the appropriate developers can save time and maintain their motivation. However, without knowledge about a bug’s class, triaging is difficult. Motivated by this challenge, this paper focuses on the problem of assigning a suitable developer to a new bug by analyzing the history of developers’ profiles and analyzing the history of bugs for all developers using machine learning-based recommender systems. Explainable AI (XAI) is AI that humans can understand. It contrasts with “black box” AI, which even its designers cannot explain. By providing appropriate explanations for results, users can better comprehend the underlying insight behind the outcomes, boosting the recommender system’s effectiveness, transparency, and confidence. The trained model is utilized in the recommendation stage to calculate relevance scores for developers based on expertise and past bug handling performance, ultimately presenting the developers with the highest scores as recommendations for new bugs. This approach aims to strike a balance between computational efficiency and accurate predictions, enabling efficient bug assignment while considering developer expertise and historical performance. In this paper, we propose two explainable models for recommendation. The first is an explainable recommender model for personalized developers generated from bug history to know what the preferred type of bug is for each developer. The second model is an explainable recommender model based on bugs to identify the most suitable developer for each bug from bug history.

Explainable Hyperbolic Temporal Point Process for User-Item Interaction Sequence Generation

Recommender systems which captures dynamic user interest based on time-ordered user-item interactions plays a critical role in the real-world. Although existing deep learning-based recommendation systems show good performances, these methods have two main drawbacks. Firstly, user interest is the consequence of the coaction of many factors. However, existing methods do not fully explore potential influence factors and ignore the user-item interaction formation process. The coarse-grained modeling patterns cannot accurately reflect complex user interest and leads to suboptimal recommendation results. Furthermore, these methods are implicit and largely operate in a black-box fashion. It is difficult to interpret their modeling processes and recommendation results. Secondly, recommendation datasets usually exhibit scale-free distributions and some existing recommender systems take advantage of hyperbolic space to match the data distribution. But they ignore that the operations in hyperbolic space are more complex than that in Euclidean space which further increases the difficulty of model interpretation. To tackle the above shortcomings, we propose an E xplainable H yperbolic T emporal P oint P rocess for User-Item Interaction Sequence Generation (EHTPP) . Specifically, EHTPP regards each user-item interaction as an event in hyperbolic space and employs a temporal point process framework to model the probability of event occurrence. Considering that the complexity of user interest and the interpretability of the model,EHTPP explores four potential influence factors related to user interest and uses them to explicitly guide the probability calculation in the temporal point process. In order to validate the effectiveness of EHTPP, we carry out a comprehensive evaluation of EHTPP on three datasets compared with a few competitive baselines. Experimental results demonstrate the state-of-the-art performances of EHTPP.

Recommending on graphs: a comprehensive review from a data perspective

Recent advances in graph-based learning approaches have demonstrated their effectiveness in modelling users’ preferences and items’ characteristics for Recommender Systems (RSs). Most of the data in RSs can be organized into graphs where various objects (e.g. users, items, and attributes) are explicitly or implicitly connected and influence each other via various relations. Such a graph-based organization brings benefits to exploiting potential properties in graph learning (e.g. random walk and network embedding) techniques to enrich the representations of the user and item nodes, which is an essential factor for successful recommendations. In this paper, we provide a comprehensive survey of Graph Learning-based Recommender Systems (GLRSs). Specifically, we start from a data-driven perspective to systematically categorize various graphs in GLRSs and analyse their characteristics. Then, we discuss the state-of-the-art frameworks with a focus on the graph learning module and how they address practical recommendation challenges such as scalability, fairness, diversity, explainability, and so on. Finally, we share some potential research directions in this rapidly growing area.

RDERL: Reliable deep ensemble reinforcement learning-based recommender system

RDERL: Reliable deep ensemble reinforcement learning-based recommender system