arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.04279cs.IR
收藏

推荐系统中上采样和正则化对公平性的影响

Interplay between Upsampling and Regularization for Provider Fairness in Recommender Systems

Ludovico Boratto, Gianni Fenu, Mirko Marras

摘要:

考虑推荐对项目提供者的影响是多方面推荐系统的任务之一。物品供应商是在线平台的关键利益相关者,他们的收入和计划受到其物品在推荐列表中的曝光度的影响。以前的工作表明,某些少数群体的供应商,其特点是一个共同的敏感属性(如,性别或种族)受到间接和无意歧视的影响不成比例。我们的研究在本文中处理的情况下,($i$)相同的供应商是与多个项目的列表建议给用户,($ii$)一个项目是由一个以上的供应商联合创建的,和($iii$)预测用户项目的相关性分数有偏见地估计供应商组的项目。在这种情况下,我们评估的相关性,可见性和曝光的差异,通过模拟不同的代表性的少数群体的目录和互动。基于出现的不公平的结果,我们设计了一种治疗方法,结合观察上采样和损失正则化,同时学习用户项目相关性得分。对真实数据的实验表明,我们的处理导致较低的不同相关性。由此产生的推荐列表显示出更公平的可见性和曝光率,更高的少数项目覆盖率,以及推荐效用的可忽略损失。

英文摘要:

Considering the impact of recommendations on item providers is one of the duties of multi-sided recommender systems. Item providers are key stakeholders in online platforms, and their earnings and plans are influenced by the exposure their items receive in recommended lists. Prior work showed that certain minority groups of providers, characterized by a common sensitive attribute (e.g., gender or race), are being disproportionately affected by indirect and unintentional discrimination. Our study in this paper handles a situation where ($i$) the same provider is associated with multiple items of a list suggested to a user, ($ii$) an item is created by more than one provider jointly, and ($iii$) predicted user-item relevance scores are biasedly estimated for items of provider groups. Under this scenario, we assess disparities in relevance, visibility, and exposure, by simulating diverse representations of the minority group in the catalog and the interactions. Based on emerged unfair outcomes, we devise a treatment that combines observation upsampling and loss regularization, while learning user-item relevance scores. Experiments on real-world data demonstrate that our treatment leads to lower disparate relevance. The resulting recommended lists show fairer visibility and exposure, higher minority item coverage, and negligible loss in recommendation utility.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑