Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence GBPR: Group Preference Based Bayesian Personalized Ranking for One-Class Collaborative Filtering

By Weike Pan, Li Chen

225 citations recorded by the source corpus.

How researchers see this paper

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

1. Xiangnan He
2. Xiang Wang
3. Weike Pan
4. Xu Chen
5. Yongfeng Zhang
6. Ruining He
7. Immanuel Bayer
8. Zhong Ming

Citations in the corpus

• VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback (2015, methodology): “More recently BPR-MF has been extended to accommodate both users’ feedback and their social relations (Krohn-Grimberghe et al., 2012; Pan and Chen, 2013; Zhao, McAuley, and King, 2014).”
• Not All Links Are Created Equal: An Adaptive Embedding Approach for Social Personalized Ranking (2016, background): “…(CF) with implicit feedback [7] which is also called personalized ranking [7] is the consideration in this paper, since in most real applications, the collected data of user behaviors, e.g., assigning tags, purchasing products and watching videos, are usually implicit [5] without explicit feedback.”
• Adaptive Bayesian personalized ranking for heterogeneous implicit feedbacks (2015, methodology): “For the number of latent features, we have tried d 2 f10;20g [20].”
• Scalable and Interpretable Product Recommendations via Overlapping Co-Clustering (2016, background): “, [29], [40]) to only consider ratings greater than or equal to 3 as positive examples and ignore all other ratings.”
• Social Recommendation with Strong and Weak Ties (2016, background): “In a nutshell, the core idea is to learn a personalized ranking for each user based on the assumption that a user prefers an observed item over all non-observed items.”
• Compressed knowledge transfer via factorization machine for heterogeneous collaborative recommendation (2015, background): “However, the user groups in GBPR [20] are not mined from auxiliary data and fixed, but are randomly constructed during the learning procedure, which is thus not able to model real hybrid interaction since there is no membership matrix.”
• A Generic Coordinate Descent Framework for Learning from Implicit Feedback (2016, background): “Shifting from simple matrix factorization to more complex factorization models has shown large success in many implicit recommendation problems [2, 4, 18, 1, 9, 24].”