Popularity bias is a pervasive challenge in recommender systems, where a few popular items dominate attention while the majority of less popular items remain underexposed. This imbalance can reduce recommendation quality and lead to unfair item exposure. Although existing mitigation methods address this issue to some extent, they often lack transparency in how they operate. In this paper, we propose a post-hoc approach, PopSteer, that leverages a Sparse Autoencoder (SAE) to both interpret and mitigate popularity bias in recommendation models. The SAE is trained to replicate a trained model's behavior while enabling neuron-level interpretability. By introducing synthetic users with strong preferences for either popular or unpopular items, we identify neurons encoding popularity signals through their activation patterns. We then steer recommendations by adjusting the activations of the most biased neurons. Experiments on three public datasets with a sequential recommendation model demonstrate that PopSteer significantly enhances fairness with minimal impact on accuracy, while providing interpretable insights and fine-grained control over the fairness-accuracy trade-off.

翻译：流行度偏差是推荐系统中普遍存在的挑战，少数热门项目占据主导关注，而大多数非热门项目则曝光不足。这种不平衡会降低推荐质量，并导致项目曝光不公平。尽管现有缓解方法在一定程度上解决了该问题，但其运作机制往往缺乏透明度。本文提出一种事后处理方法PopSteer，利用稀疏自编码器（SAE）来同时解释和缓解推荐模型中的流行度偏差。SAE经过训练以复现已训练模型的行为，同时实现神经元级别的可解释性。通过引入对热门或非热门项目具有强烈偏好的合成用户，我们根据神经元激活模式识别出编码流行度信号的神经元。随后，通过调整最具偏差神经元的激活状态来调控推荐结果。在三个公开数据集上使用序列推荐模型进行的实验表明，PopSteer在保持准确性影响最小的同时显著提升了公平性，并为公平性与准确性的权衡提供了可解释的洞见和细粒度控制。