English

Popularity Debiasing from Exposure to Interaction in Collaborative Filtering

Information Retrieval 2023-05-10 v1 Social and Information Networks

Abstract

Recommender systems often suffer from popularity bias, where popular items are overly recommended while sacrificing unpopular items. Existing researches generally focus on ensuring the number of recommendations exposure of each item is equal or proportional, using inverse propensity weighting, causal intervention, or adversarial training. However, increasing the exposure of unpopular items may not bring more clicks or interactions, resulting in skewed benefits and failing in achieving real reasonable popularity debiasing. In this paper, we propose a new criterion for popularity debiasing, i.e., in an unbiased recommender system, both popular and unpopular items should receive Interactions Proportional to the number of users who Like it, namely IPL criterion. Under the guidance of the criterion, we then propose a debiasing framework with IPL regularization term which is theoretically shown to achieve a win-win situation of both popularity debiasing and recommendation performance. Experiments conducted on four public datasets demonstrate that when equipping two representative collaborative filtering models with our framework, the popularity bias is effectively alleviated while maintaining the recommendation performance.

Keywords

Cite

@article{arxiv.2305.05204,
  title  = {Popularity Debiasing from Exposure to Interaction in Collaborative Filtering},
  author = {Yuanhao Liu and Qi Cao and Huawei Shen and Yunfan Wu and Shuchang Tao and Xueqi Cheng},
  journal= {arXiv preprint arXiv:2305.05204},
  year   = {2023}
}

Comments

Published as a SIGIR'23 short paper

R2 v1 2026-06-28T10:29:26.206Z