Collaborative User Network Embedding for Social Recommender Systems

Zhang, Chuxu; Yu, Lu; Wang, Yan; Shah, Chirag; Zhang, Xiangliang

doi:10.1137/1.9781611974973.43

Cited by 98 publications

(55 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More importantly, the framework can be easily modified or extended by other indirect implicit information. For example, the explicit social constraint can be replaced by implicit correlations generated by predefined similarity measurement [17] or network embedding technique [18] when the explicit social connections are not available. In addition, item based constraints can be introduced to further enhance the model if category or tags information [25] is available.…”

Section: B Social Recommendation Systemsmentioning

confidence: 99%

“…• CUNEMF [18]: this model extends the matrix factorization with implicit constraint generated by random walk based network embedding technique. 4) Experimental Settings: We randomly select 60% or 80% of the dataset as a training set to train the model, and further predict the remaining 40% or 20% of the dataset.…”

Section: ) Baselinesmentioning

confidence: 99%

“…To improve the recommendation performance, recent works [9]- [16] employ the observable explicit social relationships (e.g., trust links among online users) to enhance MF framework and build social recommender systems. Besides, implicit correlations information (e.g., top-k similar neighbors) induced by similarity measurement based approaches [17], [18] is utilized to improve MF and build the so-called implicit social recommender systems.…”

Section: Introductionmentioning

confidence: 99%

“…For example, in [12], a user social regularization term is integrated into the objective function of MF to help shape the users' latent space. However, the utilization of the explicit user-user social connections suffers from two main weaknesses: (a) there is no available indication about reliable social relationship in most real-life systems such as Netflix or Ebay or (even there is) the explicit relationship indication is usually very sparse (e.g., the trust density in Epinions is 0.03%), thus most of the social recommendation algorithms can not be applied to real systems; (b) an active user can be socially connected with others who have different taste/preference [18] so that social relationship fails to encode the comprehensive correlation between the diverse tastes of two users toward different kinds of items. As for the implicit social recommender systems, they infer and incorporate implicit correlations information into MF based on the explicit rating feedbacks.…”

Section: Introductionmentioning

confidence: 99%

“…As for the implicit social recommender systems, they infer and incorporate implicit correlations information into MF based on the explicit rating feedbacks. For instance, in [18], an implicit network embedding method CUNE is proposed to compute similarities among users and generate top-k similar neighbors of each user and further incorporate them into MF. Although enhancing MF with inferred correlations, current implicit social recommendation approaches have two main limitations: (a) the rating-based similarity measurements (e.g., Pearson correlation coefficient) are easy to find direct neighbors yet provide no correlation information for non-neighboring nodes on user-item ratings bipartite network; (b) the methods (e.g., CUNE) generating top-k implicit neighbors ignore correlations between a user and their non-top-k neighbors which may still contain some potential useful information, so that they fail to explore implicit information comprehensively.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

ImWalkMF: Joint matrix factorization and implicit walk integrative learning for recommendation

Zhang

et al. 2017

2017 IEEE International Conference on Big Data (Big Data)

Self Cite

View full text Add to dashboard Cite

Abstract-Data sparsity and cold-start problems are prevalent in recommender systems. To address such problems, both the observable explicit social information (e.g., user-user trust connections) and the inferable implicit correlations (e.g., implicit neighbors computed by similarity measurement) have been introduced to complement user-item ratings data for improving the performances of traditional model-based recommendation algorithms such as matrix factorization. Although effective, (1) the utilization of the explicit user-user social relationships suffers from the weakness of unavailability in real systems such as Netflix or the issue of sparse observable content like 0.03% trust density in Epinions, thus there is no or little explicit social information that can be employed to improve baseline model in real applications; (2) the current similarity measurement approaches focus on inferring implicit correlations between a user (item) and their direct neighbors or top-k similar neighbors based on user-item ratings bipartite network, so that they fail to comprehensively unfold the indirect potential relationships among users and items. To solve these issues regarding both explicit/implicit social recommendation algorithms, we design a joint model of matrix factorization and implicit walk integrative learning, i.e., ImWalkMF, which only uses explicit ratings information yet models both direct rating feedbacks and multiple direct/indirect implicit correlations among users and items from a random walk perspective. We further propose a combined strategy for training two independent components in the proposed model based on sampling. The experimental results on two real-world sparse datasets demonstrate that ImWalkMF outperforms the traditional regularized/probabilistic matrix factorization models as well as other competitive baselines that utilize explicit/implicit social information.

show abstract

Section: B Social Recommendation Systemsmentioning

confidence: 99%

Section: ) Baselinesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ImWalkMF: Joint matrix factorization and implicit walk integrative learning for recommendation

Zhang

et al. 2017

2017 IEEE International Conference on Big Data (Big Data)

Self Cite

View full text Add to dashboard Cite

show abstract

Social recommendation algorithms with user feedback information

Zuo

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Summary Social media information can effectively improve the performance of personalized recommendation model. However, the feedback information in the social media which can accurately reflect users' implicit preferences is often ignored by most existing methods. To improve the users' experience and reduce the push of unwelcome information, in this article, we propose a new social recommendation algorithm with user feedback information. Different from the existing recommendation methods based on probability matrix decomposition, we incorporate the user implicit feedback information into the user rating prediction function. To reduce the data sparsity of implicit feedback information, we also adopt social network trust calculation in our algorithm. As a result, we can not only optimize the recommendation list but also filter out most of disgusting content. Compared with PMF, UserCF, CUNE, and TrustSVD, but slightly lower than RSTE, the experimental results of our model on real‐world datasets demonstrate the effectiveness of our proposed method, and further verify that the user experience is significantly improved without obviously reducing the accuracy of the recommendation.

show abstract

Social‐trust‐aware variational recommendation

Walker

Zhang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Most existing studies that employ social-trust information to solve the data sparsity issue in recommender systems assume that socially connected users have equal influence on each other. However, this assumption does not hold in practice since users and their friends may not have similar interests because social connections are multifaceted and exhibit heterogeneous strengths in different scenarios. Therefore, estimating the diverse levels of influence among entities (users/items/social connections) is very important in advancing social recommender systems. Towards this goal, we propose a new model named Social-Trust-Aware Variational Recommendation (SOAP-VAE). Particularly, SOAP-VAE leverages graph attention network techniques to capture the varying levels of influence and the complex interaction patterns among all the entities collectively and holistically. In doing so, heterogeneity among entities is obtained seamlessly. Consequently, we generate social-trustaware item embedding representations in which the right level of influence has been integrated. Next, based on these rich social-trust-aware item representations, we formulate the first-ever social-trust-aware prior in literature. Unlike priors utilized in earlier VAE-based recommendation models, this novel prior aids in dealing with the issue of posterior-collapse and can effectively capture the uncertainty of latent space. In effect, the model produces better latent representations, which significantly alleviates the data sparsity issue. Finally, we empirically show that SOAP-VAE outperforms several state-of-the-art baselines on three real-world data sets.

show abstract

Collaborative User Network Embedding for Social Recommender Systems

Cited by 98 publications

References 18 publications

ImWalkMF: Joint matrix factorization and implicit walk integrative learning for recommendation

ImWalkMF: Joint matrix factorization and implicit walk integrative learning for recommendation

Social recommendation algorithms with user feedback information

Social‐trust‐aware variational recommendation

Contact Info

Product

Resources

About