通过公平采样消除推荐系统中的流行度偏差，提升长尾物品推荐效果。
Unbiased Collaborative Filtering with Fair Sampling
- 采用公平采样策略，使用户和物品被选为正负样本的概率相等
- 在点对点与成对推荐任务中均达到领先性能
- 无需估计倾向性分数，避免因估算误差导致的偏差残留
推荐系统利用大量用户交互数据建模偏好，但直接建模这些数据可能引入偏向热门商品的偏差。本文指出，这种流行度偏差源于训练过程中倾向性因素的影响。基于此洞察，我们提出一种公平采样（Fair Sampling, FS）方法，确保每个用户和每个物品作为正负样本的被选概率相等，从而缓解倾向性因素的影响。该方法无需估计倾向性分数，避免了因估计不准而无法完全消除流行度偏差的风险。大量实验表明，所提FS方法在点对点和成对推荐任务中均达到当前最优性能。代码已开源：https://github.com/jhliu0807/Fair-Sampling。
原文摘要 · Abstract (English)
Recommender systems leverage extensive user interaction data to model preferences; however, directly modeling these data may introduce biases that disproportionately favor popular items. In this paper, we demonstrate that popularity bias arises from the influence of propensity factors during training. Building on this insight, we propose a fair sampling (FS) method that ensures each user and each item has an equal likelihood of being selected as both positive and negative instances, thereby mitigating the influence of propensity factors. The proposed FS method does not require estimating propensity scores, thus avoiding the risk of failing to fully eliminate popularity bias caused by estimation inaccuracies. Comprehensive experiments demonstrate that the proposed FS method achieves state-of-the-art performance in both point-wise and pair-wise recommendation tasks. The code implementation is available at https://github.com/jhliu0807/Fair-Sampling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。