Unbiased Collaborative Filtering with Fair Sampling
This addresses bias in recommender systems for users and developers, though it is incremental as it builds on existing bias mitigation techniques.
The paper tackles popularity bias in recommender systems by proposing a fair sampling method that equalizes selection probabilities for users and items, achieving state-of-the-art performance in point-wise and pair-wise recommendation tasks.
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.