Correcting Popularity Bias in Recommender Systems via Item Loss Equalization

TL;DR

This paper introduces an in-training method for recommender systems that reduces popularity bias by equalizing item loss, improving fairness without significantly sacrificing accuracy.

Contribution

It proposes a novel item loss equalization technique inspired by fair risk minimization to mitigate popularity bias during model training.

Findings

Significantly reduces popularity bias in recommendations.

Maintains high recommendation accuracy.

Outperforms existing baselines in fairness metrics.

Abstract

Recommender Systems (RS) often suffer from popularity bias, where a small set of popular items dominate the recommendation results due to their high interaction rates, leaving many less popular items overlooked. This phenomenon disproportionately benefits users with mainstream tastes while neglecting those with niche interests, leading to unfairness among users and exacerbating disparities in recommendation quality across different user groups. In this paper, we propose an in-processing approach to address this issue by intervening in the training process of recommendation models. Drawing inspiration from fair empirical risk minimization in machine learning, we augment the objective function of the recommendation model with an additional term aimed at minimizing the disparity in loss values across different item groups during the training process. Our approach is evaluated through extensive experiments on two real-world datasets and compared against state-of-the-art baselines. The results demonstrate the superior efficacy of our method in mitigating the unfairness of popularity bias while incurring only negligible loss in recommendation accuracy.