arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.08571cs.AIcs.IRcs.ITcs.LGmath.ITstat.ML
收藏

检索中的多群体比例代表性

Multi-Group Proportional Representation in Retrieval

Harvard University(哈佛大学);University of Minnesota(明尼苏达大学)

Alex Oesterling, Claudio Mayrink Verdun, Carol Xuan Long, Alexander Glynn, Lucas Monteiro Paes, Sajani Vithana, Martina Cardone, Flavio P. Calmon

AI总结:

针对图像检索现有方法忽略交叉群体代表性的问题,提出衡量交叉群体代表性的MPR指标及优化算法,可在低准确率损失下实现多交叉群体的比例代表性。

摘要:

图像搜索与检索任务可能延续有害刻板印象、抹除文化身份并加剧社会不平等。当前缓解这类代表性危害的方法,是在由少量(通常是二元的)属性定义的人群群体间平衡检索到的条目数量。但现有多数方法忽略了由性别、种族、族裔等群体属性组合所确定的交叉群体。我们提出了多群体比例代表性(Multi-Group Proportional Representation,MPR),这是一种衡量交叉群体间代表性的新型指标。我们开发了估算MPR的实用方法,提供了理论保证,并提出了保障检索中MPR的优化算法。我们证明,现有针对均等和比例代表性指标优化的方法可能无法提升MPR。关键的是,我们的研究表明,优化MPR能在由丰富函数类定义的多个交叉群体间实现更具比例性的代表性,且通常对检索准确率的影响极小。

英文摘要:

Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups defined by a small number of (often binary) attributes. However, most existing methods overlook intersectional groups determined by combinations of group attributes, such as gender, race, and ethnicity. We introduce Multi-Group Proportional Representation (MPR), a novel metric that measures representation across intersectional groups. We develop practical methods for estimating MPR, provide theoretical guarantees, and propose optimization algorithms to ensure MPR in retrieval. We demonstrate that existing methods optimizing for equal and proportional representation metrics may fail to promote MPR. Crucially, our work shows that optimizing MPR yields more proportional representation across multiple intersectional groups specified by a rich function class, often with minimal compromise in retrieval accuracy.

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。

↑