A Neural Influence Diffusion Model for Social Recommendation

Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering (CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online social networks, social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a social platform, her potential embedding is influenced by her trusted users, with these trusted users are influenced by the trusted users' social connections. As social influence recursively propagates and diffuses in the social network, each user's interests change in the recursive process. Nevertheless, the current social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive social diffusion process for social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines for top-10 recommendation on the two datasets.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Neil Yorke-Smith,et al.  A Novel Recommendation Model Regularized with User Trust and Item Ratings , 2016, IEEE Transactions on Knowledge and Data Engineering.

[3]  Le Wu,et al.  Modeling Users' Preferences and Social Links in Social Networking Services: A Joint-Evolving Perspective , 2016, AAAI.

[4]  Nicholas Jing Yuan,et al.  Relevance Meets Coverage , 2016, ACM Trans. Intell. Syst. Technol..

[5]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[6]  Yiming Yang,et al.  Graph Convolutional Matrix Completion for Bipartite Edge Prediction , 2018, KDIR.

[7]  Éva Tardos,et al.  Maximizing the Spread of Influence through a Social Network , 2015, Theory Comput..

[8]  Fei Wang,et al.  Scalable Recommendation with Social Contextual Information , 2014, IEEE Transactions on Knowledge and Data Engineering.

[9]  Yuxiao Dong,et al.  DeepInf : Modeling Influence Locality in Large Social Networks , 2018 .

[10]  Neil Yorke-Smith,et al.  TrustSVD: Collaborative Filtering with Both the Explicit and Implicit Influence of User Trust and of Item Ratings , 2015, AAAI.

[11]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[12]  Steven B. Andrews,et al.  Power, Social Influence, and Sense Making: Effects of Network Centrality and Proximity on Employee Perceptions. , 1993 .

[13]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[14]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[15]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[16]  Xavier Bresson,et al.  Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks , 2017, NIPS.

[17]  Kevin Lewis,et al.  Social selection and peer influence in an online social network , 2011, Proceedings of the National Academy of Sciences.

[18]  Martin Ester,et al.  A matrix factorization technique with trust propagation for recommendation in social networks , 2010, RecSys '10.

[19]  Le Wu,et al.  Collaborative Neural Social Recommendation , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[20]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[21]  Lei Zheng,et al.  Spectral collaborative filtering , 2018, RecSys.

[22]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[23]  Dit-Yan Yeung,et al.  Collaborative Deep Learning for Recommender Systems , 2014, KDD.

[24]  Ravi Kumar,et al.  Influence and correlation in social networks , 2008, KDD.

[25]  Tat-Seng Chua,et al.  Item Silk Road: Recommending Items from Information Domains to Social Users , 2017, SIGIR.

[26]  Yuxiao Dong,et al.  DeepInf: Social Influence Prediction with Deep Learning , 2018, KDD.

[27]  Jeffrey T. Hancock,et al.  Experimental evidence of massive-scale emotional contagion through social networks , 2014, Proceedings of the National Academy of Sciences.

[28]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[29]  Jure Leskovec,et al.  Representation Learning on Graphs: Methods and Applications , 2017, IEEE Data Eng. Bull..

[30]  Chao Liu,et al.  Recommender systems with social regularization , 2011, WSDM '11.

[31]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[32]  Le Wu,et al.  A Hierarchical Attention Model for Social Contextual Image Recommendation , 2018, IEEE Transactions on Knowledge and Data Engineering.

[33]  Tao Mei,et al.  Personalized Recommendation Combining User Interest and Social Circle , 2014, IEEE Transactions on Knowledge and Data Engineering.

[34]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[35]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[36]  Hui Xiong,et al.  Influence Maximization over Large-Scale Social Networks: A Bounded Linear Approach , 2014, CIKM.

[37]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[38]  Max Welling,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.

[39]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[40]  Le Wu,et al.  Attentive Recurrent Social Recommendation , 2018, SIGIR.

[41]  Cameron Marlow,et al.  A 61-million-person experiment in social influence and political mobilization , 2012, Nature.

[42]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[43]  Hui Xiong,et al.  Enhancing Collaborative Filtering by User Interest Expansion via Personalized Ranking , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[44]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[45]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[46]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[47]  Tong Zhao,et al.  Leveraging Social Connections to Improve Personalized Ranking for Collaborative Filtering , 2014, CIKM.

[48]  Huan Liu,et al.  Social recommendation: a review , 2013, Social Network Analysis and Mining.

[49]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[50]  Junping Du,et al.  Modeling the Evolution of Users’ Preferences and Social Links in Social Networking Services , 2017, IEEE Transactions on Knowledge and Data Engineering.