Unbiased Collaborative Filtering with Fair Sampling

TL;DR

This paper introduces a fair sampling method for recommender systems that reduces popularity bias by ensuring equal likelihood of user-item interactions without estimating propensity scores, leading to improved recommendation performance.

Contribution

The paper proposes a novel fair sampling approach that mitigates popularity bias in collaborative filtering without requiring propensity score estimation.

Findings

Achieves state-of-the-art results in recommendation tasks

Effectively reduces popularity bias in models

Does not rely on propensity score estimation

Abstract

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.