竞争性算法公平性可能破坏整体系统公平，需重新审视公平设计。
Fairness under Competition
- 引入竞争企业场景，分析个体公平算法对整体生态的影响
- 即使各算法个体公平，整体系统仍可能不公平，且公平调整可能恶化全局公平
- 适用于关注算法协作与系统级公平的研究者与政策制定者
算法公平已成为机器学习中的核心议题，目前普遍做法是调整算法以满足如平等机会等公平要求。本文研究采用此类公平分类器对整体生态系统公平性的影响。我们首次提出在竞争企业背景下分析公平性的问题，揭示公平分类器无法保证生态系统公平。研究量化了在不同条件下，分类器相关性与数据重叠程度对公平损失的影响。结果表明，即便各分类器个体公平，其协同运作仍可能导致系统整体不公平；且提升单个算法的公平性反而可能降低整体公平水平。此外，我们提供了实验验证支持。本研究为算法公平设计提供了全新且关键的警示。
原文摘要 · Abstract (English)
Algorithmic fairness has emerged as a central issue in ML, and it has become standard practice to adjust ML algorithms so that they will satisfy fairness requirements such as Equal Opportunity. In this paper we consider the effects of adopting such fair classifiers on the overall level of ecosystem fairness. Specifically, we introduce the study of fairness with competing firms, and demonstrate the failure of fair classifiers in yielding fair ecosystems. Our results quantify the loss of fairness in systems, under a variety of conditions, based on classifiers' correlation and the level of their data overlap. We show that even if competing classifiers are individually fair, the ecosystem's outcome may be unfair; and that adjusting biased algorithms to improve their individual fairness may lead to an overall decline in ecosystem fairness. In addition to these theoretical results, we also provide supporting experimental evidence. Together, our model and results provide a novel and essential call for action.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。