Neural Network Collaborative Filtering for Group Recommendation

In the group recommender system, most of methods through aggregating individual preferences of each member in the group to group preference, which neglect the correlation among the members of the group. In this paper, group recommendation based on neural collaborative filtering (GNCF) and convolutional neural collaborative filtering (GCNCF) frameworks are proposed, which simulate the interaction between the members of the group and make recommendations directly for the group. GNCF and GCNCF frameworks predict group ratings by learning user-item interaction matrices. They project sparse vectors to dense vectors by utilizing the full connection layer, and improve the non-linear capability of the model by using the deep neural networks. Comparing with the traditional method, our method builds a new group recommendation model, and its effectiveness is well demonstrated through experiments.

[1]  Hui Li,et al.  HBGG: a Hierarchical Bayesian Geographical Model for Group Recommendation , 2017, SDM.

[2]  Takashi Yagi,et al.  Group recommendation using feature space representing behavioral tendency and power balance among members , 2011, RecSys '11.

[3]  Hui Xiong,et al.  A Cocktail Approach for Travel Package Recommendation , 2014, IEEE Transactions on Knowledge and Data Engineering.

[4]  Yang Yang,et al.  Start from Scratch: Towards Automatically Identifying, Modeling, and Naming Visual Attributes , 2014, ACM Multimedia.

[5]  Jongtae Lim,et al.  Social group recommendation based on dynamic profiles and collaborative filtering , 2016, Neurocomputing.

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

[7]  Hugues Bersini,et al.  Collaborative Filtering with Recurrent Neural Networks , 2016, ArXiv.

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

[9]  Martha Larson,et al.  CARS2: Learning Context-aware Representations for Context-aware Recommendations , 2014, CIKM.

[10]  Francesco Ricci,et al.  Group recommendations with rank aggregation and collaborative filtering , 2010, RecSys '10.

[11]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[12]  Tommi S. Jaakkola,et al.  Maximum-Margin Matrix Factorization , 2004, NIPS.

[13]  Nitish Srivastava,et al.  Multimodal learning with deep Boltzmann machines , 2012, J. Mach. Learn. Res..

[14]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[15]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Wang Haiyan,et al.  Latent Group Recommendation Based on Dynamic Probabilistic Matrix Factorization Model Integrated with CNN , 2017 .

[18]  Shlomo Berkovsky,et al.  Group-based recipe recommendations: analysis of data aggregation strategies , 2010, RecSys '10.

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

[20]  Lars Schmidt-Thieme,et al.  Fast context-aware recommendations with factorization machines , 2011, SIGIR.

[21]  Benjamin Schrauwen,et al.  Deep content-based music recommendation , 2013, NIPS.

[22]  Yung-Ming Li,et al.  A social recommender mechanism for location-based group commerce , 2014, Inf. Sci..

[23]  Wei Cao,et al.  Deep Modeling of Group Preferences for Group-Based Recommendation , 2014, AAAI.