Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure

ACM International Conference on Web Search and Data Mining (WSDM), pp. 882–890

Abstract

Sequential recommendation (SR) models are typically trained on user-item interactions which are affected by the system exposure bias, leading to the user preference learned from the biased SR model not being fully consistent with the true user preference. Exposure bias refers to the fact that user interactions are dependent upon the partial items exposed to the user. Existing debiasing methods do not make full use of the system exposure data and suffer from sub-optimal recommendation performance and high variance.

Authors 10

1. Jiyuan Yang

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

2. Yue Ding

   Shanghai Jiao Tong University

   Affiliation as printed

   Shanghai Jiao Tong University, Shanghai, China

3. Yidan Wang

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

4. Pengjie Ren

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

5. Zhumin Chen

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

6. Fei Cai

   National University of Defense Technology

   Affiliation as printed

   National University of Defense Technology, Changsha, China

7. Jun Ma

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

8. Rui Zhang
   Affiliation as printed

   ruizhang.info, Shenzhen, China

9. Zhaochun Ren Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, Netherlands

10. Xin Xin

    Shandong University

    Affiliation as printed

    Shandong University, Qingdao, China