Exploiting relational tag expansion for dynamic user profile in a tag-aware ranking recommender system

Pan, Yinghui; Huo, Yongfeng; Tang, Jing; Zeng, Yifeng; Chen, Bilian

doi:10.1016/j.ins.2020.09.001

Cited by 23 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This gap involves a lack of knowledge with respect to a large spectrum of models and applications that have different functions than classification. These functions are of high importance in many domains, e.g., ranking in natural language processing [ 102 ] and recommender systems [ 103 ]. It is an open question of how the existing attacks impact these functions.…”

Section: Discussionmentioning

confidence: 99%

Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setups

Wainakh

Zimmer

Subedi

et al. 2022

Sensors

View full text Add to dashboard Cite

Deep learning pervades heavy data-driven disciplines in research and development. The Internet of Things and sensor systems, which enable smart environments and services, are settings where deep learning can provide invaluable utility. However, the data in these systems are very often directly or indirectly related to people, which raises privacy concerns. Federated learning (FL) mitigates some of these concerns and empowers deep learning in sensor-driven environments by enabling multiple entities to collaboratively train a machine learning model without sharing their data. Nevertheless, a number of works in the literature propose attacks that can manipulate the model and disclose information about the training data in FL. As a result, there has been a growing belief that FL is highly vulnerable to severe attacks. Although these attacks do indeed highlight security and privacy risks in FL, some of them may not be as effective in production deployment because they are feasible only given special—sometimes impractical—assumptions. In this paper, we investigate this issue by conducting a quantitative analysis of the attacks against FL and their evaluation settings in 48 papers. This analysis is the first of its kind to reveal several research gaps with regard to the types and architectures of target models. Additionally, the quantitative analysis allows us to highlight unrealistic assumptions in some attacks related to the hyper-parameters of the model and data distribution. Furthermore, we identify fallacies in the evaluation of attacks which raise questions about the generalizability of the conclusions. As a remedy, we propose a set of recommendations to promote adequate evaluations.

show abstract

Section: Discussionmentioning

confidence: 99%

Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setups

Wainakh

Zimmer

Subedi

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…This gap introduces a lack of knowledge with respect to a large spectrum of models and applications that have different functions than classification. These functions are of high importance in many domains, e.g., ranking in natural language processing [151] and recommender systems [100]. It is an open question how the existing attacks impact these functions.…”

Section: Poisoning Attacksmentioning

confidence: 99%

Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setups

Wainakh¹,

Zimmer²,

Subedi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Federated learning (FL) enables a set of entities to collaboratively train a machine learning model without sharing their sensitive data, thus, mitigating some privacy concerns. However, an increasing number of works in the literature propose attacks that can manipulate the model and disclose information about the training data in FL. As a result, there has been a growing belief in the research community that FL is highly vulnerable to a variety of severe attacks. Although these attacks do indeed highlight security and privacy risks in FL, some of them may not be as effective in production deployment because they are feasible only under special-sometimes impractical-assumptions. Furthermore, some attacks are evaluated under limited setups that may not match real-world scenarios. In this paper, we investigate this issue by conducting a systematic mapping study of attacks against FL, covering 48 relevant papers from 2016 to the third quarter of 2021. On the basis of this study, we provide a quantitative analysis of the proposed attacks and their evaluation settings. This analysis reveals several research gaps with regard to the type of target ML models and their architectures. Additionally, we highlight unrealistic assumptions in the problem settings of some attacks, related to the hyper-parameters of the ML model and data distribution among clients. Furthermore, we identify and discuss several fallacies in the evaluation of attacks, which open up questions on the generalizability of the conclusions. As a remedy, we propose a set of recommendations to avoid these fallacies and to promote adequate evaluations.

show abstract

“…To increase recommendation performance, Pan et al [21] proposed a new social tag expansion model to create a user profile. so instead of including the most appropriate tags, the new model presented the completeness of user-profiles by increasing tags and utilizing their relationships.…”

Section: Related Workmentioning

confidence: 99%

An enhanced framework for solving cold start problem in movie recommendation systems

Elzeheiry

Mekky²,

Atwan³

et al. 2021

IJEECS

View full text Add to dashboard Cite

<p>Recommendation systems (RSs) are used to obtain advice regarding decision-making. RSs have the shortcoming that a system cannot draw inferences for users or items regarding which it has not yet gathered sufficient information. This issue is known as the cold start issue. Aiming to alleviate the user’s cold start issue, the proposed recommendation algorithm combined tag data and logistic regression classification to predict the probability of the movies for a new user. First using alternating least square to extract product feature, and then diminish the feature vector by combining principal component analysis with logistic regression to predict the probability of genres of the movies. Finally, combining the most relevant tags based on similarity score with probability and find top N movies with high scores to the user. The proposed model is assessed using the root mean square error (RMSE), the mean absolute error (MAE), recall@N and precision@N and it is applied to 1M, 10M and 20M MovieLens datasets, resulting in an accuracy of 0.8806, 0.8791 and 0.8739.</p>

show abstract

Exploiting relational tag expansion for dynamic user profile in a tag-aware ranking recommender system

Abstract: Exploiting relational tag expansion for dynamic user profile in a tag-aware ranking recommender system. Information Sciences,

Cited by 23 publications

References 37 publications

Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setups

Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setups

Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setups

An enhanced framework for solving cold start problem in movie recommendation systems

Contact Info

Product

Resources

About