Session-Based Social Recommendation via Dynamic Graph Attention Networks

By Weiping Song, Zhiping Xiao, Yifan Wang, Laurent Charlin, Ming Zhang, Jian Tang. 2019

468 citations recorded by the source corpus.

Online communities such as Facebook and Twitter are enormously popular and have become an essential part of the daily life of many of their users. Through these platforms, users can discover and create information that others will then consume. In that context, recommending relevant information to users becomes critical for viability. However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends. Moreover, the influencers may be context-dependent. That is, different friends may be relied upon for different topics. Modeling both signals is therefore essential for recommendations. We propose a recommender system for online communities based on a dynamic-graph-attention neural network. We model dynamic user behaviors with a recurrent neural network, and context-dependent social influence with a graph-attention neural network, which dynamically infers the influencers based on users' current interests. The whole model can be efficiently fit on large-scale data. Experimental results on several real-world data sets demonstrate the effectiveness of our proposed approach over several competitive baselines including state-of-the-art models.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems, Graph Learning, Recommender Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Hongzhi Yin
4. Tat-seng Chua
5. Meng Wang
6. Yong Li
7. Chen Gao
8. Fuli Feng

In Computer Networks and Communications

1. Gao Huang
2. Xiang Wang
3. Meng Wang
4. Xing Xie
5. Huan Liu
6. Jundong Li
7. Hui Xiong
8. Jian Tang

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Hongzhi Yin
4. Fuli Feng
5. Meng Wang
6. Yong Li
7. Chen Gao
8. Junliang Yu

In Graph Learning

1. Huan Liu
2. Jian Tang
3. Xiangnan He
4. Jundong Li
5. Yu Zheng
6. Fei Sun
7. Xing Xie
8. Qing He

In Recommender Systems

1. Xiang Wang
2. Xiangnan He
3. Meng Wang
4. Fuli Feng
5. Xing Xie
6. Yong Li
7. Chen Gao
8. Fuzhen Zhuang

Citations in the corpus

• Dynamic Neural Networks: A Survey (2021, background): “Others Document classification [146], Link prediction [221], Graph classification [113], Stereo confidence estimation [222], Recommendation systems [223]”
• Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning (2020, background): “For example, the context variable could be the strategy of an opponent in a game [69, 49, 77, 51], regimes in time-series forecasting [56, 19, 9] or the mood of a user when navigating a content platform in recommender systems [25, 72].”
• Next-item Recommendation with Sequential Hypergraphs (2020, methodology): “good success in next-item recommendation which aims to predict a user’s next actions based on the sequential interactions in the past [22, 25, 30, 35, 37, 39, 44].”
• A Survey of Graph Neural Networks for Social Recommender Systems (2022, methodology): “Miscellaneous Douban 2,848 39,586 894,887 35,770 [1, 10, 22, 24, 45, 47, 50, 66, 71, 72, 81, 83, 90, 110],”
• Graph Neural Networks in Recommender Systems: A Survey (2020, methodology): “Diferentiating Inluence by Attention: GraphRec [33], DifNet++ [171], DANSER [174], GAT-NSR [110], DGRec [130], TGRec [2]”
• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation (2021, background): “Song et al. develop DGRec [34] to model both users’ session-based interests as well as dynamic social influences.”
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks (2018, background): “Attention is first proposed in the context of neural machine translation [2] and has been proved effective in a variety of tasks such as question answering [35], text summarization [30], and recommender systems [14, 33, 43].”
• Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning (2020, background): “For example, the context variable could be the strategy of an opponent in a game [71, 50, 79, 53], regimes in time-series forecasting [58, 20, 9], the mood of a user when navigating a content platform in recommender systems [26, 74] or any unobserved variable in RL, e.”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, methodology): “Instead of performing GNNs on the user-user social graph, researchers have also considered jointly modeling the social diffusion process in the social network and the interest diffusion process in the user-item graph with heterogeneous GNN based models [158], [161], [162], [163],”
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “Also, there exist some works [6, 73, 157, 216, 230] that introduce additional information to further enhance the social recommendation.”
• A Survey on Knowledge Graph-Based Recommender Systems (2020, background): “Recently, Song et al. [127] designed a dynamic-graph-attention network to capture the user’s rapidly-changing interests by incorporating long term and short term interests from friends.”
• Causal Intervention for Leveraging Popularity Bias in Recommendation (2021, background): “2) Douban Movie: This dataset is collected from a popular review website Douban5 in China by [39].”