Graph Attention Networks for Neural Social Recommendation

Mu, Nan; Zha, Daren; He, Yuanye; Tang, Zhihao Gavin

doi:10.1109/ictai.2019.00183

Cited by 30 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To cope with this, one can leverage the social information of users [9,25,36,42]. In this way, we assume that users with social links also share similar item interests.…”

Section: Introductionmentioning

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

“…To cope with this, one can leverage the social information of users [9,25,36,42]. In this way, we assume that users with social links also share similar item interests.…”

Section: Introductionmentioning

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

“…To capture the high-order social relations, the graph construction methods can be divided into two directions: stacked graphs and hypergraph. Given that normal graph can only model the pairwise relations, normal graph-based methods [35,51,71,98,113,132,163,164,167,184,191,192] stacked multiple GNN layers to capture multi-hop high-order social relations. However, stacked GNN layers may suffer from the over-smoothing [18] problem, which may lead to significant performance degradation.…”

Section: Gnn In Socialmentioning

confidence: 99%

“…Graph GNN Social Signal Extraction DiffNet [164] social graph GCN sum-pooling GraphRec [35] social graph + user-item graph GAT concatenation DANSER [167] social graph + user-item graph GAT & GCN -DiffNet++ [163] heterogeneous graph GAT multi-level attention network MHCN [193] multi-channel hypergraph + user-item graph HyperGCN sum-pooling SEPT [191] triangle-graphs + user-item graph GCN -RecoGCN [182] heterogeneous graph Meta-path + GCN concatenation ESRF [192] motif-induced graph GAT sum-pooling GNN-SoR [51] heterogeneous graph GCN concatenation ASR [98] heterogeneous graph GAT concatenation GBGCN [196] heterogeneous graph GCN -DGRec [134] social graph GAT -SR-HGNN [184] social graph + user-item graph GCN concatenation KCGN [63] social graph + item-item graph GCN concatenation HGP [71] group-user graph + user-item graph GCN attention mechanism GAT-NSR [113] social graph + user-item graph GAT MLP HOSR [96] social graph + user-item graph GCN attention mechanism DiffNetLG [132] heterogeneous graph GCN concatenation TGRec [6] heterogeneous graph GCN attention mechanism concatenation [35], MLP [113] or attention mechanism [6,71,96]. DiffNet++ [163], a typical method with the second strategy, first aggregates the information in the user-item sub-graph and social sub-graph with the GAT mechanism and then combines the representations with the designed multilevel attention network at each layer.…”

Section: Modelmentioning

confidence: 99%

“…Early efforts in Social Recommendation only model the social network with GNN, such as DiffNet [164]. Then, the methods [35,51,71,98,113,132,163,164,167,184,191,192] that model both social network and user interactions with GNNs become the mainstream in GNN-based social recommendation. Moreover, some studies, such as MHCN [193] and HOSR [96], attempt to enhance the recommendation by modeling the high-order relations in social networks more sufficiently.…”

Section: Modelmentioning

confidence: 99%

“…MHCN [193] performs propagation with GCN on constructed hypergraph to obtain the high-order social relations. The methods with attention mechanism [35,98,113,134,163,167,192], such as GraphRec [35] and DiffNet++ [163], assume that the social influences from different neighbors on the social graph are different and assign different weights to the social influences from different friends.…”

Section: Introduce Additional Informationmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Chen¹,

Zheng²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach of recommender systems. In this survey, we conduct a comprehensive review of the literature in graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data, and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions of this area. We summarize the representative papers along with their codes repositories in https://github.com/tsinghua-fib-lab/GNN-Recommender-Systems.

show abstract