Recommender systems (RSs) have become an indispensable part of online platforms. With the growing concerns of algorithmic fairness, RSs are not only expected to deliver high-quality personalized content, but are also demanded not to discriminate against users based on their demographic information. However, existing RSs could capture undesirable correlations between sensitive features and observed user behaviors, leading to biased recommendations. Most fair RSs tackle this problem by completely blocking the influences of sensitive features on recommendations. But since sensitive features may also affect user interests in a fair manner (e.g., race on culture-based preferences), indiscriminately eliminating all the influences of sensitive features inevitably degenerate the recommendations quality and necessary diversities. To address this challenge, we propose a path-specific fair RS (PSF-RS) for recommendations. Specifically, we summarize all fair and unfair correlations between sensitive features and observed ratings into two latent proxy mediators, where the concept of path-specific bias (PS-Bias) is defined based on path-specific counterfactual inference. Inspired by Pearl's minimal change principle, we address the PS-Bias by minimally transforming the biased factual world into a hypothetically fair world, where a fair RS model can be learned accordingly by solving a constrained optimization problem. For the technical part, we propose a feasible implementation of PSF-RS, i.e., PSF-VAE, with weakly-supervised variational inference, which robustly infers the latent mediators such that unfairness can be mitigated while necessary recommendation diversities can be maximally preserved simultaneously. Experiments conducted on semi-simulated and real-world datasets demonstrate the effectiveness of PSF-RS.

翻译：推荐系统（RSs）已成为在线平台不可或缺的组成部分。随着算法公平性问题的日益凸显，推荐系统不仅需要提供高质量个性化内容，还被要求不得基于用户人口统计信息进行歧视。然而，现有推荐系统可能捕捉到敏感特征与观测用户行为之间的不良相关性，导致推荐结果存在偏差。多数公平推荐系统通过完全阻断敏感特征对推荐的影响来解决该问题。但因敏感特征也可能以公平方式影响用户兴趣（例如种族对文化偏好的影响），不加区分地消除敏感特征的所有影响不可避免地会降低推荐质量与必要的多样性。为应对这一挑战，我们提出了一种路径特异性公平推荐系统（PSF-RS）。具体而言，我们将敏感特征与观测评分之间所有公平与不公平的相关性归纳为两个潜在代理中介变量，基于路径特异性反事实推理定义了路径特异性偏差（PS-Bias）概念。受Pearl最小改变原则启发，我们通过将存在偏差的事实世界最小程度地转化为假设的公平世界来消除PS-Bias，进而通过求解约束优化问题学习得到公平推荐模型。在技术实现层面，我们提出了PSF-RS的可行方案PSF-VAE，采用弱监督变分推理稳健地推断潜在中介变量，从而在缓解不公平性的同时最大程度保留必要的推荐多样性。在半仿真与真实数据集上的实验验证了PSF-RS的有效性。