Fairness is a widely discussed topic in recommender systems, but its practical implementation faces challenges in defining sensitive features while maintaining recommendation accuracy. We propose feature fairness as the foundation to achieve equitable treatment across diverse groups defined by various feature combinations. This improves overall accuracy through balanced feature generalizability. We introduce unbiased feature learning through adversarial training, using adversarial perturbation to enhance feature representation. The adversaries improve model generalization for under-represented features. We adapt adversaries automatically based on two forms of feature biases: frequency and combination variety of feature values. This allows us to dynamically adjust perturbation strengths and adversarial training weights. Stronger perturbations are applied to feature values with fewer combination varieties to improve generalization, while higher weights for low-frequency features address training imbalances. We leverage the Adaptive Adversarial perturbation based on the widely-applied Factorization Machine (AAFM) as our backbone model. In experiments, AAFM surpasses strong baselines in both fairness and accuracy measures. AAFM excels in providing item- and user-fairness for single- and multi-feature tasks, showcasing their versatility and scalability. To maintain good accuracy, we find that adversarial perturbation must be well-managed: during training, perturbations should not overly persist and their strengths should decay.

翻译：公平性是推荐系统中广泛讨论的话题，但实际应用面临敏感特征定义与保持推荐准确性的挑战。我们提出以特征公平性为基础，通过多种特征组合定义的不同群体实现均衡对待。通过平衡特征泛化能力提升整体准确性。我们引入基于对抗训练的无偏特征学习，利用对抗扰动增强特征表示。对抗机制改善模型对欠表示特征的泛化能力。根据两种特征偏差形式（特征值的频率与组合多样性）自动调整对抗机制。通过动态调节扰动强度与对抗训练权重，对组合多样性较少的特征值施加更强扰动以提升泛化能力，同时为低频特征赋予更高权重以解决训练不平衡问题。我们采用基于广泛应用的因子分解机的自适应对抗扰动（AAFM）作为骨干模型。实验表明，AAFM在公平性与准确性指标上均超越强基线模型。AAFM在单特征与多特征任务中均能实现物品公平性与用户公平性，展现其通用性与可扩展性。为保持良好准确性，我们发现必须有效管理对抗扰动：训练过程中扰动不应持续过强，且其强度应随训练衰减。