Identifying and upweighting power-niche users to mitigate popularity bias in recommendations

Liu D., Weis E., Laber M., Eliassi-Rad T., and Klein B.

Proceedings of the ACM Web Conference (WWW) (2026)

Abstract

Recommender systems have been shown to exhibit popularity bias by over-recommending popular items and under-recommending rel- evant niche items. We seek to understand niche users in benchmark recommendation datasets as a step toward mitigating popularity bias. We find that, compared to mainstream users, niche-preferring users exhibit a longer-tailed activity-level distribution, indicating the existence of users who both prefer niche items and exhibit high activity levels on platforms. We partition users along two axes: (1) activity level (“power” vs. “light”) and (2) item-popularity prefer- ence (“mainstream” vs. “niche”), and show that in three benchmark datasets, the number of power-niche users (high activity and niche preference) is statistically significantly larger than expected. We also find that interaction data from power-niche users is especially valuable for improving recommendations for not only niche but also mainstream users. In contrast, many existing popularity bias mitiga- tion methods have focused on upweighting niche users regardless of activity level. Motivated by the value of power-niche user data, we propose PAIR (Popularity-and-Activity-Informed Reweighting), a framework for reweighting the Bayesian Personalized Ranking (BPR) loss that simultaneously reweights based on user activity level and item popularity, upweighting power-niche users the most. We instantiate the framework on both deep and shallow collabora- tive filtering models, and experiments on benchmark datasets show that PAIR reduces popularity bias and can increase overall perfor- mance. Although existing popularity-bias mitigation methods yield a trade-off between performance and bias, our results suggest that considering both user activity level and popularity preference leads to Pareto-dominant performance.

Paper

Citation

@inproceedings{liu2026_identifyingupweightingpowerniche,
  title = {Identifying and Upweighting Power-Niche Users to Mitigate Popularity Bias in Recommendations},
  booktitle = {Proceedings of the ACM Web Conference 2026},
  author = {Liu, David and Weis, Erik and Laber, Moritz and Eliassi-Rad, Tina and Klein, Brennan},
  year = {2026},
  pages = {6830--6840},
  series = {{{WWW}} '26},
  isbn = {979-8-4007-2307-0}
  doi = {10.1145/3774904.3792679},
  url = {https://dl.acm.org/doi/10.1145/3774904.3792679},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
}