Content-enhanced Bayesian Personalized Ranking

With the popularization of Knowledge Payment Products (KPP), more accurate recommendations are in great need to alleviate information overload of users. Bayesian Personalized Ranking (BPR) is one of the most representative pairwise ranking methods for recommendation, the performances of which greatly depend on the selection of negative feedback. However, traditional negative samplers may suffer from bias and noises. Therefore, in this paper, we focus on improving negative sampling strategy of BPR by incorporating side information of the knowledge products. We locate negative samples by calculating the cosine similarity among items by the textual features of KPP, under the assumption that a user shall have similar perceptions on items with similar content. We union our sampler strategy and the original one with different ratios. Compared to the original BPR that applies a uniform sampler on all the products, the join of our content-based sampler enhances BPR with a relative improvement over 4% on the ZhiHu Live dataset, which demonstrates the effectiveness of considering side information when capturing users' preferences on different items.

[1]  Jun Wang,et al.  Optimizing top-n collaborative filtering via dynamic negative item sampling , 2013, SIGIR.

[2]  Xiangnan He,et al.  A Generic Coordinate Descent Framework for Learning from Implicit Feedback , 2016, WWW.

[3]  Dongwon Lee,et al.  “Told you i didn't like it”: Exploiting uninteresting items for effective collaborative filtering , 2016, 2016 IEEE 32nd International Conference on Data Engineering (ICDE).

[4]  Zheng Qin,et al.  Spectrum-enhanced Pairwise Learning to Rank , 2019, WWW.

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

[6]  Xu Chen,et al.  Aesthetic-based Clothing Recommendation , 2018 .

[7]  Julian J. McAuley,et al.  VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback , 2015, AAAI.

[8]  James Caverlee,et al.  What Are You Known For?: Learning User Topical Profiles with Implicit and Explicit Footprints , 2017, SIGIR.

[9]  Congfu Xu,et al.  Adaptive Bayesian personalized ranking for heterogeneous implicit feedbacks , 2015, Knowl. Based Syst..

[10]  Yongfeng Zhang,et al.  Personalized Key Frame Recommendation , 2017, SIGIR.

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

[12]  Martha Larson,et al.  Bayesian Personalized Ranking with Multi-Channel User Feedback , 2016, RecSys.

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

[14]  Depeng Jin,et al.  Sampler Design for Bayesian Personalized Ranking by Leveraging View Data , 2018, IEEE Transactions on Knowledge and Data Engineering.

[15]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[16]  Dietmar Jannach,et al.  Using graded implicit feedback for bayesian personalized ranking , 2014, RecSys '14.

[17]  Qiang Yang,et al.  One-Class Collaborative Filtering , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[18]  Steffen Rendle,et al.  Improving pairwise learning for item recommendation from implicit feedback , 2014, WSDM.

[19]  Jure Leskovec,et al.  Hidden factors and hidden topics: understanding rating dimensions with review text , 2013, RecSys.

[20]  Depeng Jin,et al.  An Improved Sampler for Bayesian Personalized Ranking by Leveraging View Data , 2018, WWW.