Collaborative Neural Social Recommendation

Wu, Le; Sun, Peijie; Hong, Richang; Ge, Yong; Wang, Meng

doi:10.1109/tsmc.2018.2872842

Cited by 84 publications

(26 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HGMF [52] introduces a hierarchical group matrix factorization technique to learn the user-group feature in a social network for recommendation. Unlike matrix factorization methods, graph neural network methods infer node embeddings directly from graphs and demonstrate the efectiveness from recent social recommendation work [24,57,58]. GraphRec [9] and GraphRec+ [10] uses graph attention networks to learn user and item embeddings for recommendation.…”

Section: Social Recommendationmentioning

confidence: 99%

Federated Social Recommendation with Graph Neural Network

Liu

Yang

Fan

et al. 2022

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Recommender systems have become prosperous nowadays, designed to predict users’ potential interests in items by learning embeddings. Recent developments of the Graph Neural Networks (GNNs) also provide recommender systems with powerful backbones to learn embeddings from a user-item graph. However, only leveraging the user-item interactions suffers from the cold-start issue due to the difficulty in data collection. Hence, current endeavors propose fusing social information with user-item interactions to alleviate it, which is the social recommendation problem. Existing work employs GNNs to aggregate both social links and user-item interactions simultaneously. However, they all require centralized storage of the social links and item interactions of users, which leads to privacy concerns. Additionally, according to strict privacy protection under General Data Protection Regulation, centralized data storage may not be feasible in the future, urging a decentralized framework of social recommendation. As a result, we design a federated learning recommender system for the social recommendation task, which is rather challenging because of its heterogeneity, personalization, and privacy protection requirements. To this end, we devise a novel framework Fe drated So cial recommendation with G raph neural network ( FeSoG ). Firstly, FeSoG adopts relational attention and aggregation to handle heterogeneity. Secondly, FeSoG infers user embeddings using local data to retain personalization. Last but not least, the proposed model employs pseudo-labeling techniques with item sampling to protect the privacy and enhance training. Extensive experiments on three real-world datasets justify the effectiveness of FeSoG in completing social recommendation and privacy protection. We are the first work proposing a federated learning framework for social recommendation to the best of our knowledge.

show abstract

Section: Social Recommendationmentioning

confidence: 99%

Federated Social Recommendation with Graph Neural Network

Liu

Yang

Fan

et al. 2022

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

show abstract

“…In order to verify the effectiveness of the IDiffNet, we compared it with the mainstream baseline models, including the classical collaborative filtering model (BPR (Rendle et al, 2012), FM (Rendle, 2010)), the classical social recommendation model (SocialMF (Jamali & Ester, 2010), TrustSVD (Guo et al, 2015), CNSR (Wu et al, 2018)) and the GNNs based model (GraphRec (Fan et al, 2019), PinSage (Ying et al, 2018), NGCF (Wang et al, 2019b), DiffNet (Wu et al, 2019a), DiffNet++ (Wu et al, 2020)). Among them, since the original PinSage was designed to generate high-quality item embedding, we take the…”

Section: Baselinesmentioning

confidence: 99%

Interest-aware influence diffusion model for social recommendation

Zhan

et al. 2021

J Intell Inf Syst

View full text Add to dashboard Cite

With the rapid development of social networks, the application of social relationships in recommendation systems has attracted more and more attention. The social recommendation system alleviates the problem of data sparsity by utilizing the preferences of users' friends, so as to better model the user embedding. The traditional social recommendation model optimizes the user embedding through the first-order neighbors' preference information, but it failed to model the social influence diffusion process from the global social network. Although the recently proposed DiffNet solves this problem to some extent, it ignores the fact that high-order adjacent users who have no common interests in the social network can also participate in graph convolution, which will make user embedding affected by negative information in social influence diffusion, thus affecting the performance of the recommendation system. Therefore, we propose a model named IDiffNet based on DiffNet. In IDiffNet, a self-supervised subgraph generation module is designed to identify users with similar interests according to user features. Thereby, the user social graph is decomposed into several user social subgraphs, and then user embedding is optimized through interest propagation on the subgraphs. Consequently, the IDiffNet can avoid the interaction of users with different interests in the user social network. Finally, we conducted a number of comparative experiments on two public datasets, and the results show that IDiffNet has better performance than current mainstream social recommendation models.

show abstract

“…Social scientists have long converged that a user's preference is similar to or influenced by her social connections, with the social theories of homophily and social influence [3]. With the prevalence of social networks, a popular research direction is to leverage the social data to improve recommendation performance [33], [23], [24], [51]. E.g., Ma et al proposed a latent factor based model with social regularization terms for recommendation [33].…”

Section: Related Workmentioning

confidence: 99%

A Hierarchical Attention Model for Social Contextual Image Recommendation

Chen

Hong

et al. 2020

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

Image based social networks are among the most popular social networking services in recent years. With tremendous images uploaded everyday, understanding users' preferences on user-generated images and making recommendations have become an urgent need. In fact, many hybrid models have been proposed to fuse various kinds of side information (e.g., image visual representation, social network) and user-item historical behavior for enhancing recommendation performance. However, due to the unique characteristics of the user generated images in social image platforms, the previous studies failed to capture the complex aspects that influence users' preferences in a unified framework. Moreover, most of these hybrid models relied on predefined weights in combining different kinds of information, which usually resulted in sub-optimal recommendation performance. To this end, in this paper, we develop a hierarchical attention model for social contextual image recommendation. In addition to basic latent user interest modeling in the popular matrix factorization based recommendation, we identify three key aspects (i.e., upload history, social influence, and owner admiration) that affect each user's latent preferences, where each aspect summarizes a contextual factor from the complex relationships between users and images. After that, we design a hierarchical attention network that naturally mirrors the hierarchical relationship (elements in each aspects level, and the aspect level) of users' latent interests with the identified key aspects. Specifically, by taking embeddings from state-of-the-art deep learning models that are tailored for each kind of data, the hierarchical attention network could learn to attend differently to more or less content. Finally, extensive experimental results on real-world datasets clearly show the superiority of our proposed model. !

show abstract

Collaborative Neural Social Recommendation

Cited by 84 publications

References 50 publications

Federated Social Recommendation with Graph Neural Network

Federated Social Recommendation with Graph Neural Network

Interest-aware influence diffusion model for social recommendation

A Hierarchical Attention Model for Social Contextual Image Recommendation

Contact Info

Product

Resources

About