Social Collaborative Filtering by Trust

Yang, Bo; Yu, Lei; Liu, Jiming; Li, Wenjie

doi:10.1109/tpami.2016.2605085

Cited by 479 publications

(344 citation statements)

References 30 publications

Supporting

Mentioning

312

Contrasting

Unclassified

Order By: Relevance

“…For the sake of generality, we consider only positive links in this study. The elimination of negative links is consistent with other studies [8], [12].…”

Section: Introductionsupporting

confidence: 93%

“…Studies [10], [11], [8] suggested that user opinions are influenced by not only their own preferences but also their trusted friends. Social recommendation attracted a lot of attention in recent studies [6], [8], [12] and several e-commerce systems tried to leverage user social information to improve the quality of their recommender systems [11], [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

dTrust: A Simple Deep Learning Approach for Social Recommendation

Dang

Ignat

2017

2017 IEEE 3rd International Conference on Collaboration and Internet Computing (CIC)

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. dTrust: a simple deep learning approach for social recommendationQuang-Vinh Dang, Claudia-Lavinia IgnatTo cite this version: Abstract-Rating prediction is a key task of e-commerce recommendation mechanisms. Recent studies in social recommendation enhance the performance of rating predictors by taking advantage of user relationships. However, these prediction approaches mostly rely on user personal information which is a privacy threat.In this paper, we present dTrust, a simple social recommendation approach that avoids using user personal information. It relies uniquely on the topology of an anonymized trust-useritem network that combines user trust relations with user rating scores. This topology is fed into a deep feed-forward neural network. Experiments on real-world data sets showed that dTrust outperforms state-of-the-art in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores for both warmstart and cold-start problems.

show abstract

“…For the sake of generality, we consider only positive links in this study. The elimination of negative links is consistent with other studies [8], [12].…”

Section: Introductionsupporting

confidence: 93%

Section: Introductionmentioning

confidence: 99%

dTrust: A Simple Deep Learning Approach for Social Recommendation

Dang

Ignat

2017

2017 IEEE 3rd International Conference on Collaboration and Internet Computing (CIC)

View full text Add to dashboard Cite

show abstract

“…To enhance recommender systems with explicit social information, novel social recommendation models are studied in [3,4,9,10,11,14,20,22] [3], the authors proposed a trust-based MF technique by considering both the explicit and implicit influences of the neighborhood structure of user trust and the user-item ratings. Yang et al [20] designed a hybrid MF model that combines both a truster model and a trustee model with the assumption that a specific user's truster and trustee will affect their ratings. In [11], a user social regularization term is introduced to constrain the basic MF.…”

Section: Related Workmentioning

confidence: 99%

“…Various approaches [5,6,15,16,17,18] based on low-rank matrix factorization (MF) or Bayesian personalized ranking (BPR) have been proposed to solve the problems of ratings prediction or items ranking. To improve the recommendation performance, recent works [1,3,20,22] incorporate the observed explicit social information (e.g., trust connections of users) into MF or BPR frameworks to build novel systems (the so-called social recommender systems).…”

Section: Introductionmentioning

confidence: 99%

Collaborative User Network Embedding for Social Recommender Systems

Zhang¹,

Yu²,

Wang³

et al. 2017

Proceedings of the 2017 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

To address the issue of data sparsity and cold-start in recommender system, social information (e.g., user-user trust links) has been introduced to complement rating data for improving the performances of traditional model-based recommendation techniques such as matrix factorization (MF) and Bayesian personalized ranking (BPR). Although effective, the utilization of the explicit user-user relationships extracted directly from such social information has three main limitations. First, it is difficult to obtain explicit and reliable social links. Only a small portion of users indicate explicitly their trusted friends in recommender systems. Second, the "cold-start" users are "cold" not only on rating but also on socializing. There is no significant amount of explicit social information that can be useful for "cold-start" users. Third, an active user can be socially connected with others who have different taste/preference. Direct usage of explicit social links may mislead recommendation. To address these issues, we propose to extract implicit and reliable social information from user feedbacks and identify top-k semantic friends for each user. We incorporate the top-k semantic friends information into MF and BPR frameworks to solve the problems of ratings prediction and items ranking, respectively. The experimental results on three real-world datasets show that our proposed approaches achieve better results than the state-of-the-art MF with explicit social links (with 3.0% improvement on RMSE), and social BPR (with 9.1% improvement on AUC).

show abstract

“…Cloud service providers often hope to exploit the accumulated user-service quality data (i.e., users' experienced service quality) to assist in the decision of cloud service recommendation to provide better services or to maximize revenue. Specifically, a recommendation method, e.g., the seminal collaborative filtering (CF) [1], can be used directly on the data to find a target user's similar users (i.e., neighbors) based on historical user-service quality data.…”

Section: Introductionmentioning

confidence: 99%

A Distributed Locality-Sensitive Hashing-Based Approach for Cloud Service Recommendation From Multi-Source Data

Zhang

Dou

et al. 2017

IEEE J. Select. Areas Commun.

193

143

View full text Add to dashboard Cite

Abstract-To maximize the economic benefits, a cloud service provider needs to recommend its services to as many users as possible based on the historical user-service quality data. However, when a cloud platform (e.g., Amazon) intends to make a service recommendation decision, considering only its own user-service quality data is insufficient because a cloud user may invoke services from multiple distributed cloud platforms (e.g., Amazon and IBM). In this situation, it is promising for Amazon to collaborate with other cloud platforms (e.g., IBM) to utilize the integrated data for the service recommendation to improve the recommendation accuracy. However, two challenges are present in the above collaboration process, where we attempt to use multi-source data for the service recommendation. First, protecting users' privacy is challenging when IBM releases its own data to Amazon. Second, the recommendation efficiency and scalability are often low when the user-service quality data of Amazon and IBM update frequently. Considering these challenges, a privacy-preserving and scalable service recommendation approach based on distributed locality-sensitive hashing (LSH), i.e., SerRec distri-LSH , is proposed in this paper to handle the service recommendation in a distributed cloud environment. Extensive experiments on the WS-DREAM dataset validate the feasibility of our approach in terms of service recommendation accuracy, scalability and privacy preservation.

show abstract

Social Collaborative Filtering by Trust

Cited by 479 publications

References 30 publications

dTrust: A Simple Deep Learning Approach for Social Recommendation

dTrust: A Simple Deep Learning Approach for Social Recommendation

Collaborative User Network Embedding for Social Recommender Systems

A Distributed Locality-Sensitive Hashing-Based Approach for Cloud Service Recommendation From Multi-Source Data

Contact Info

Product

Resources

About