Improving Recommendation Fairness via Data Augmentation

TL;DR

This paper proposes a data augmentation framework to improve fairness in recommendation systems by balancing training data distributions, applicable to various embedding-based models without predefined fairness metrics.

Contribution

It introduces a novel data augmentation approach that enhances recommendation fairness by addressing data imbalance, without requiring changes to existing recommendation architectures.

Findings

Outperforms existing fairness methods on real-world datasets

Applicable to any embedding-based recommendation system

Does not rely on predefined fairness metrics

Abstract

Collaborative filtering based recommendation learns users' preferences from all users' historical behavior data, and has been popular to facilitate decision making. R Recently, the fairness issue of recommendation has become more and more essential. A recommender system is considered unfair when it does not perform equally well for different user groups according to users' sensitive attributes~(e.g., gender, race). Plenty of methods have been proposed to alleviate unfairness by optimizing a predefined fairness goal or changing the distribution of unbalanced training data. However, they either suffered from the specific fairness optimization metrics or relied on redesigning the current recommendation architecture. In this paper, we study how to improve recommendation fairness from the data augmentation perspective. The recommendation model amplifies the inherent unfairness of imbalanced training data. We augment imbalanced training data towards balanced data distribution to improve fairness. The proposed framework is generally applicable to any embedding-based recommendation, and does not need to pre-define a fairness metric. Extensive experiments on two real-world datasets clearly demonstrate the superiority of our proposed framework. We publish the source code at https://github.com/newlei/FDA.