Cold-start Problem Research Articles

LogOW: A semi-supervised log anomaly detection model in open-world setting

Log anomaly detection is a method for finding abnormal behavior and faults in systems. However, existing methods face two main challenges: the open-world problem and the cold-start problem. The open-world problem means that the test set may contain new classes that are not in the training set, while the cold-start problem means that the initial training data are scarce, both for normal and abnormal log sequences. Most existing methods assume a closed-world setting and rely on sufficient normal data, which limits their adaptability to new log environments.We propose LogOW, a novel log anomaly detection model that can learn from a few normal log sequences. The model finds emerging normal log sequences in the open-world setting through the open-world sample retrieval module. Through the incremental pre-training module, these log sequences are fine-tuned in an online mode for model parameters.First, we train a basic model from normal log sequences using Masked-Language Modeling(MLM). During the testing phase, we then combine the anomaly score and the uncertainty score obtained through a novel dynamic multi-mask to distinguish closed-world normal log sequences from the test set. Next, we cluster the open-world log sequences based on fused sequence and count features, and identify the abnormal ones and the new normal ones. Finally, we update our model with the new normal sequences in the next time period. Experiments on three log datasets and real-world airport logs show that our model outperforms traditional models in the open-world and lack of training data setting.

A model to address the cold-start in peer recommendation by using k-means clustering and sentence embedding

In academia, research collaboration plays a vital role in enhancing the research quality and enriching the academic profile of the authors. Recommending appropriate collaborators from a vast scholarly database, particularly for newcomers, poses a challenging cold-start problem. This study addresses a cold-start problem in peer recommendation, considering a dynamic coauthorship graph as a network structure of academic collaborators. As the coauthorship graph is quite large and complex, an efficient indexing method is essential for speeding up the initial search of similar coauthors. The study introduces an efficient Global Inverted List (GIL) for indexing research areas and active authors in the coauthorship network. An attribute-based search and filtering mechanism is proposed to identify relevant collaborators, followed by the application of k-means clustering and doc2vec metrics to rank and select top recommendations. A cold user is associated with attributes that identify coauthors with similar research interests. For each attribute of the cold user, the model searches the associated authors from the GIL. Further, two filtering approaches are applied to refine the retrieved author list. The first ensures that the authors have a significant presence in the specified research areas, whereas the second one helps avoid recommending authors with only superficial connections to the cold user. The model creates a feature matrix of filtered authors using the publication features of authors. The k-means clustering applied to the feature matrix generates k clusters, among which the model chooses only those with seed nodes i.e. the clusters which are having seed nodes are selected for further process. Selected clusters are ranked using doc2vec metrics, with the top-ranked cluster providing the final recommendation. The model recommends the top L members of the selected cluster, where L is the length of the recommendations provided to the new user. Our extensive experiments show the efficacy of the proposed model.

CsKT: Addressing cold-start problem in knowledge tracing via kernel bias and cone attention

csKT: Addressing cold-start problem in knowledge tracing via kernel bias and cone attention

An E-Commerce Recommendation System Based on Dynamic Analysis of Customer Behavior

The expansion of e-commerce site platforms has brought about the need for personalized recommendation systems for the betterment of user experience and sales. In this paper, we propose a new approach for the recommendation system which is based on the dynamic behavior analysis of the users of the system. This involves analytics on the current data about customer activities such as buying history, browsing history, and likes to give recommendations that are up to date and very precise. Static models of the recommendation systems are contrasted to dynamic ones with the emphasis on the benefits of using for example collaborative filtering, content based filtering and other machine learning based hybrid systems to such systems. The performance metrics of accuracy, recall and F1 score confirm that the implementation of the system as proposed solves the cold start problem, enhances the scalability of the system and improves the accuracy of recommendations made. This work therefore opens the door to next generation recommendation engines which are more e-commerce oriented and can respond to the changing needs of customers more effectively.

Integrating Transformers into Recommendation Systems: A Hybrid Approach

In recent years, recommendation systems have become essential for various industries, from e-commerce to social media. This paper explores the integration of Transformer models within recommendation systems, which enhances the model's ability to capture long-range dependencies in user interactions. We present a hybrid recommendation approach combining collaborative filtering and Transformer-based content analysis. A case study is included, demonstrating how this integration handles both cold-start problems and typical user-item recommendation tasks.

A deep learning based hybrid recommendation model for internet users

Recommendation Systems (RS) play a crucial role in delivering personalized item suggestions, yet traditional methods often struggle with accuracy, scalability, efficiency, and cold-start challenges. This paper presents the HRS-IU-DL model, a novel hybrid recommendation system that advances the field by integrating multiple sophisticated techniques to enhance both accuracy and relevance. The proposed model uniquely combines user-based and item-based Collaborative Filtering (CF) to effectively analyze user-item interactions, Neural Collaborative Filtering (NCF) to capture complex non-linear relationships, and Recurrent Neural Networks (RNN) to identify sequential patterns in user behavior. Furthermore, it incorporates Content-Based Filtering (CBF) with Term Frequency-Inverse Document Frequency (TF-IDF) for in-depth analysis of item attributes. A key contribution of this work is the innovative fusion of CF, NCF, RNN, and CBF, which collectively address significant challenges such as data sparsity, the cold-start problem, and the increasing demand for personalized recommendations. Additionally, the model employs N-Sample techniques to recommend the top 10 similar items based on user-specified genres, leveraging methods like Cosine Similarity, Singular Value Decomposition (SVD), and TF-IDF. The HRS-IU-DL model is rigorously evaluated on the publicly available Movielens 100k dataset using train-test splits. Performance is assessed using metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Precision, and Recall. The results demonstrate that the HRS-IU-DL model not only outperforms state-of-the-art approaches but also achieves substantial improvements across these evaluation metrics, highlighting its contribution to the advancement of RS technology.

One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems

Sequential recommendation systems aim to predict users’ next likely interaction based on their history. However, these systems face data sparsity and cold-start problems. Utilizing data from other domains, known as multi-domain methods, is useful for alleviating these problems. However, traditional multi-domain methods rely on meaningless ID-based item representation, which makes it difficult to align items with similar meanings from different domains, yielding sup-optimal knowledge transfer. This paper introduces LLM-Rec , a framework that utilizes pre-trained large language models (LLMs) for domain-agnostic recommendation. Specifically, we mix user's behaviors from multiple domains and concatenate item titles into a sentence, then use LLMs for generating user and item representations. By mixing behaviors across different domains, we can exploit the knowledge encoded in LLMs to bridge the semantic across over multi-domain behaviors, thus obtaining semantically rich representations and improving performance in all domains. Furthermore, we explore the underlying reasons why LLMs are effective and investigate whether LLMs can understand the semantic correlations as the recommendation model, and if advanced techniques like scaling laws in NLP also work in recommendations. We conduct extensive experiments with LLMs ranging from 40M to 6.7B to answer the above questions and to verify the effectiveness of LLM-Rec in multi-domain recommendation \({}^{\ddagger}\) .

Deep Learning Based Music Recommendation Systems: A Review of Algorithms and Techniques

Abstract. This paper provides a thorough examination of the utilisation of deep learning in music recommendation systems, which have transformed consumer discovery and engagement with music on streaming platforms. Scalability challenges and the cold-start problem are among the constraints that conventional recommendation methods, such as content-based filtering and collaborative filtering, encounter, which hinder their ability to deliver personalised recommendations that are effective. The processing of multi-modal and sequential data is significantly improved by deep learning methodologies, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, and Autoencoders. This results in more precise and contextually pertinent music recommendations. Moreover, hybrid models that amalgamate deep learning with conventional techniques augment recommendation precision by synthesising user interaction data with acoustic characteristics. This paper examines essential performance metrics employed in the assessment of music recommendation systems, including precision, recall, F1-score, and Mean Reciprocal Rank (MRR). It also tackles issues including computational complexity, bias, and ethical dilemmas pertaining to data privacy.

Optimizing E-commerce Recommender Systems: A Comprehensive Review of Techniques and Future Directions

Abstract. This paper examines recommender systems in e-commerce by reviewing technologies and real-world applications and identifying the importance of big data analytics in recommender systems. In the study, three kinds of recommendation algorithms are discussed: collaborative filtering, content-based recommendation, and hybrid models. Collaborative filtering methods did well in the case of large-scale user data, but had cold-start and sparsity problems. Based on the content, recommended methods have strong personalized suggestion functions, but the information cocoon phenomenon is a risk, which decreases the contents diversity. Hybrid models are a combination approach between the two techniques, providing a flexible and robustness solution, but only a more complex computationally. This article also looks at the technology trends that have emerged lately, for example, the use of deep learning models, as well as the privacy-preserving techniques utilized in recommender systems. By analyzing and summarizing the existing research, this paper provides a reference basis for future optimization and application of recommender systems and points out potential research directions.

A collaborative filtering recommender systems: Survey

In the current digital landscape, both information consumers and producers encounter numerous challenges, underscoring the importance of recommender systems (RS) as a vital tool. Among various RS techniques, collaborative filtering (CF) has emerged as a highly effective method for suggesting products and services. However, traditional CF methods face significant obstacles in the era of big data, including issues related to data sparsity, accuracy, cold start problems, and high dimensionality. This paper offers a comprehensive survey of CF-based RS enhanced by machine learning (ML) and deep learning (DL) algorithms. It aims to serve as a valuable resource for both novice and experienced researchers in the field of RS. The survey is structured into two main sections: the first elucidates the fundamental concepts of RS, while the second delves into solutions for CF-based RS challenges, examining the specific tasks addressed by various studies, as well as the metrics and datasets employed.

DemogCF model of personalized recommendations based on demographic characteristics for overcoming data sparsity and cold start problems

DemogCF model of personalized recommendations based on demographic characteristics for overcoming data sparsity and cold start problems

Time-aware cross-domain point-of-interest recommendation in social networks

Point-of-Interest recommendation within the single domain is quite easy compared to the cross-domain recommendation, as there is an acute dearth of check-in records for the target regions, aggravating the cold start problem. We propose a self-ensembled contextual Thompson sampling for cross-domain Point-of-Interest recommendation to solve this. This approach utilizes user preference transfer and user preference drift in the target domain for enhanced recommendation by deploying enhanced contextual sampling. As the user-context pairs of the target domain are not labeled for the given user, domain adaptation is highly sought. The approach has four major steps: i) Mining Point-of-Interests based on the long-term preferences of the target user and the user with a similar trajectory in the source domain, ii) Computing rewards for the Point-of-Interests in the source domain using multi-layer perceptron, iii) Estimate the rewards for unlabeled Point-of-Interests in the target domain and iv) Form the ensemble of rewards that are used to decide the final arm pulls. The rewards obtained for Point-of-Interests in the source and target domain are combined to form an ensemble of rewards with the help of self ensembling domain adaptation technique. Each Point-of-Interest in the ensemble rewards is termed an arm of action. We use this ensemble of rewards to control the diversity measure and the switching probability of the various arms, potential Point-of-Interests, in the contextual Thompson Sampling. Contextual Thompson sampling is modified to incorporate exploitation-exploration tradeoffs using this reward ensemble. The implicit weight measure of the different arms decides the probability of exploitation or exploration. The final arm pulls results in the final Point-of-Interest recommendation. For experimentation, we have used two real-world datasets, namely, Gowalla and Foursquare, and extracted the data for seven domains. We have obtained an accuracy of approximately 65% for Point-of-Interest recommendations on cold-start users.

Cold Start Latency in Serverless Computing: A Systematic Review, Taxonomy, and Future Directions

Recently, academics and the corporate sector have paid attention to serverless computing, which enables dynamic scalability and an economic model. In serverless computing, users only pay for the time they actually use resources, enabling zero scaling to optimise cost and resource utilisation. However, this approach also introduces the serverless cold start problem. Researchers have developed various solutions to address the cold start problem, yet it remains an unresolved research area. In this article, we propose a systematic literature review on cold start latency in serverless computing. Furthermore, we create a detailed taxonomy of approaches to cold start latency, which we use to investigate existing techniques for reducing the cold start time and frequency. We have classified the current studies on cold start latency into several categories such as caching and application-level optimisation-based solutions, as well as Artificial Intelligence/Machine Learning-based solutions. Moreover, we have analyzed the impact of cold start latency on quality of service, explored current cold start latency mitigation methods, datasets, and implementation platforms, and classified them into categories based on their common characteristics and features. Finally, we outline the open challenges and highlight the possible future directions.

NCF-based Movie Recommendation System

Abstract. This paper discusses the design and evaluation of a Neural Collaborative Filtering (NCF) model for movie recommendations using the MovieLens dataset. It addresses the limitations of traditional recommendation systems, such as content-based filtering and collaborative filtering, which struggle with data sparsity and the cold start problem. By incorporating deep learning, the NCF model enhances the accuracy and personalization of recommendations by learning the latent features of users and items and capturing complex interactions.

Natural Language Processing and Machine Learning-Based Solution of Cold Start Problem Using Collaborative Filtering Approach

In today’s digital era, the abundance of online services presents users with a daunting array of choices, spanning from streaming platforms to e-commerce websites, leading to decision fatigue. Recommendation algorithms play a pivotal role in aiding users in navigating this plethora of options, among which collaborative filtering (CF) stands out as a prevalent technique. However, CF encounters several challenges, including scalability issues, privacy implications, and the well-known cold start problem. This study endeavors to mitigate the cold start problem by harnessing the capabilities of natural language processing (NLP) applied to user-generated reviews. A unique methodology is introduced, integrating both supervised and unsupervised NLP approaches facilitated by sci-kit learn, utilizing benchmark datasets across diverse domains. This study offers scientific contributions through its novel approach, ensuring rigor, precision, scalability, and real-world relevance. It tackles the cold start problem in recommendation systems by combining natural language processing (NLP) with machine learning and collaborative filtering techniques, addressing data sparsity effectively. This study emphasizes reproducibility and accuracy while proposing an advanced solution that improves personalization in recommendation models. The proposed NLP-based strategy enhances the quality of user-generated content, consequently refining the accuracy of Collaborative Filtering-Based Recommender Systems (CFBRSs). The authors conducted experiments to test the performance of the proposed approach on benchmark datasets like MovieLens, Jester, Book-Crossing, Last.fm, Amazon Product Reviews, Yelp, Netflix Prize, Goodreads, IMDb (Internet movie Database) Data, CiteULike, Epinions, and Etsy to measure global accuracy, global loss, F-1 Score, and AUC (area under curve) values. Assessment through various techniques such as random forest, Naïve Bayes, and Logistic Regression on heterogeneous benchmark datasets indicates that random forest is the most effective method, achieving an accuracy rate exceeding 90%. Further, the proposed approach received a global accuracy above 95%, a global loss of 1.50%, an F-1 Score of 0.78, and an AUC value of 92%. Furthermore, the experiments conducted on distributed and global differential privacy (GDP) further optimize the system’s efficacy.

Exploring drug-target interaction prediction on cold-start scenarios via meta-learning-based graph transformer

Predicting drug-target interaction (DTI) is of great importance for drug discovery and development. With the rapid development of biological and chemical technologies, computational methods for DTI prediction are becoming a promising approach. However, there are few solutions to the cold-start problem in DTI prediction scenarios, as these methods rely on existing interaction information to support their modeling. Consequently, they are unable to effectively predict DTIs for new drugs or targets with limited interaction data in the existing work. To this end, we propose a graph transformer method based on meta-learning named MGDTI (short for Meta-learning-based Graph Transformer for Drug-Target Interaction prediction) to fill this gap. Technically, we employ drug-drug similarity and target-target similarity as additional information to mitigate the scarcity of interactions. Besides, we trained MGDTI via meta-learning to be adaptive to cold-start tasks. Moreover, we employed graph transformer to prevent over-smoothing by capturing long-range dependencies. Extensive results on the benchmark dataset demonstrate that MGDTI is effective on DTI prediction under cold-start scenarios.

A framework for generating recommendations based on trust in an informal e-learning environment.

Rapid advancement in information technology promotes the growth of new online learning communities in an e-learning environment that overloads information and data sharing. When a new learner asks a question, how a system recommends the answer is the problem of the learner's cold start. In this article, our contributions are: (i) We proposed a Trust-aware Deep Neural Recommendation (TDNR) framework that addresses learner cold-start issues in informal e-learning by modeling complex nonlinear relationships. (ii) We utilized latent Dirichlet allocation for tag modeling, assigning tag categories to newly posted questions and ranking experts related to specific tags for active questioners based on hub and authority scores. (iii) We enhanced recommendation accuracy in the TDNR model by introducing a degree of trust between questioners and responders. (iv) We incorporated the questioner-responder relational graph, derived from structural preference information, into our proposed model. We evaluated the proposed model on the Stack Overflow dataset using mean absolute precision (MAP), root mean squared error (RMSE), and F-measure metrics. Our significant findings are that TDNR is a hybrid approach that provides more accurate recommendations compared to rating-based and social-trust-based approaches, the proposed model can facilitate the formation of informal e-learning communities, and experiments show that TDNR outperforms the competing methods by an improved margin. The model's robustness, demonstrated by superior MAE, RMSE, and F-measure metrics, makes it a reliable solution for addressing information overload and user sparsity in Stack Overflow. By accurately modeling complex relationships and incorporating trust degrees, TDNR provides more relevant and personalized recommendations, even in cold-start scenarios. This enhances user experience by facilitating the formation of supportive learning communities and ensuring new learners receive accurate recommendations.

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.

Exploring the Efficiency of Hybrid Recommender Systems Implemented with TensorFlow Framework

In recent years, the field of recommendation systems has seen significant advancement with the introduction of hybrid approaches. These systems combine the strengths of multiple recommendation techniques to provide more accurate and diverse recommendations to users. In this research, we propose and evaluate the effectiveness of a hybrid recommender system that utilizes TensorFlow, an open-source machine learning framework, to implement the system. The proposed system combines both collaborative and content-based methods to remove the cold start problem and make personalized recommendations that can recommend similar movies to the users based on features extracted by the model. The results of our experiments demonstrate that the proposed hybrid system outperforms traditional singular methods and can be effectively implemented using TensorFlow. This research provides insights into the potential of TensorFlow for building efficient hybrid recommendation systems and the benefits of combining multiple recommendation techniques.

An adaptive meta-imitation learning-based recommendation environment simulator: A case study on ship-cargo matching

High-quality shipping is one of the effective ways for sustainable cities in inland river basins to improve transportation efficiency and reduce energy consumption. Currently, the biggest challenge faced by shipping is the high empty-ship rate, which makes it impossible to directly apply machine learning methods due to the cold-start problem. Although some researchers have tried to utilize deep reinforcement learning(DRL)-based recommendation that do not rely on manually labeled data to alleviate the cold-start problem, progress has been slow due to the lack of available training environment. Therefore, this paper introduces an adaptive meta-imitation learning-based recommendation environment simulator, termed AMIL-Simulator. Specifically, we construct a conditionally guided diffusion model to simulate shipowner behavior in a dynamically changing environment. Moreover, we propose a shipowner reward model based on adaptive meta-imitation learning, enabling the learning of shipowner rewards across multiple tasks, even when confronted with limited samples and imbalanced categories. By conducting extensive quantitative experimental evaluations and shipowner-cargo matching studies, the results demonstrate the effectiveness of AMIL-Simulator, particularly in smaller-scale and cold-start environments.