通过内部标签转移实现推荐系统的规范对齐
Normative Alignment of Recommender Systems via Internal Label Shift
- Technical University of Denmark(技术大学)
- University of California San Diego(加州大学圣地亚哥分校)
- Inria, Université Côte d'Azur(Inria与普罗旺斯大学)
- Copenhagen Business School(哥本哈根商学院)
- ZOZO Research(ZOZO研究)
- Pioneer Centre for Artificial Intelligence(先锋人工智能中心)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
研究如何使推荐系统输出与目标分布对齐,提出NAILS方法,通过修改用户条件项目分布,在保留原偏好且无需重训模型的情况下,将问题转化为层次分类框架内的标签转移,实现与全局规范目标对齐,且对用户参与度影响小。
AI中文摘要:
我们介绍了NAILS(通过内部标签转移实现推荐系统的规范对齐),这是一种简单且可扩展的方法,用于使推荐输出与项目级属性(如类别)上的目标分布对齐。仅针对用户参与度进行优化的推荐系统往往无法满足更广泛的规范目标,包括公平性、多样性和编辑价值。NAILS修改用户条件项目分布,以在保留现有推荐系统所学习的偏好且无需重新训练模型的情况下,诱导出指定的属性边际分布。我们将此问题表述为层次分类框架内的一种内部标签转移形式。从以利益相关者为中心的角度来看,NAILS使推荐输出能够与全局规范目标对齐。实证表明,NAILS能在对用户参与度影响最小的情况下持续改善属性级对齐,为价值驱动的推荐提供了实用机制。
英文摘要:
We introduce NAILS (Normative Alignment of Recommender Systems via Internal Label Shift), a simple and scalable method for aligning recommendation outputs with target distributions over item-level attributes, such as categories. Recommender systems optimized solely for user engagement often fail to satisfy broader normative objectives, including fairness, diversity, and editorial values. NAILS modifies the user-conditional item distribution to induce a specified marginal distribution over attributes while preserving the preferences learned by an existing recommender system and requiring no model retraining. We formulate this problem as a form of label shift applied internally within a hierarchical classification framework. By adopting a stakeholder-centric perspective, NAILS enables recommendation outputs to be aligned with global normative objectives. Empirically, we show that NAILS consistently improves attribute-level alignment with minimal impact on user engagement, providing a practical mechanism for value-driven recommendation.