Multi-feedback Pairwise Ranking via Adversarial Training for Recommender  

作　　者：WANG Jianfang FU Zhiyuan NIU Mingxin ZHANG Pengbo ZHANG Qiuling 

机构地区：[1]College of Computer Science and Technology,Henan Polytechnic University,Jiaozuo 454003,China

出　　处：《Chinese Journal of Electronics》2020年第4期615-622,共8页电子学报（英文版）

摘　　要：Personalized recommendation systems predict potential demand by analyzing user preferences.Generally,user feedback information is inferred from implicit feedback or explicit feedback.Nevertheless,feedback can be contaminated by user’s mis-operations or malicious operations,and may thus lead to incorrect results.We propose a novel Multi-feedback pairwise ranking method via Adversarial training(AT-MPR)for recommender to enhance the robustness and overall performance in the event of rating pollution.The MPR method extends Bayesian personalized ranking(BPR)to cover three types of feedback:positive,negative,and unobserved.It obtains user preferences in a probabilistic way through multiple feedbacks at different levels.To reduce the impact of feedback noise,we train an MPR objective function using minimax adversarial training.Experiments on two datasets show that the AT-MPR model achieves satisfactory performance and outperforms the state-of-the-art implicit feedback collaborative ranking models in two evaluation metrics.

关 键 词：Adversarial training Pairwise ranking Collaborative filtering Recommender system 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]