arXiv 2102.003112021-02cs.AImath.OC

通过社会福利优化实现公平

Fairness through Social Welfare Optimization

Stevens Institute of Technology（史蒂文斯理工学院）；Carnegie Mellon University（卡内基梅隆大学）

Violet Xinying Chen, J. N. Hooker

备注：: 23 pages, 3 figures

摘要：

我们提出了社会福利优化作为一个通用的范式，在人工智能系统中的公平性。我们认为，优化模型允许制定广泛的公平标准作为社会福利函数，同时使人工智能能够利用高度先进的解决方案技术。人们可以通过将公平纳入社会福利职能，实现所有群体的公平，而不是试图减少选定群体之间的偏见。这也使得能够更全面地核算所涉个人的福利。我们展示了如何将社会福利优化与基于规则的AI和机器学习相结合，使用处理中或后处理方法。我们目前的实证结果，从一个案例研究作为这些整合策略的有效性和潜力的初步审查。

英文摘要：

We propose social welfare optimization as a general paradigm for formalizing fairness in AI systems. We argue that optimization models allow formulation of a wide range of fairness criteria as social welfare functions, while enabling AI to take advantage of highly advanced solution technology. Rather than attempting to reduce bias between selected groups, one can achieve equity across all groups by incorporating fairness into the social welfare function. This also allows a fuller accounting of the welfare of the individuals involved. We show how to integrate social welfare optimization with both rule-based AI and machine learning, using either an in-processing or a post-processing approach. We present empirical results from a case study as a preliminary examination of the validity and potential of these integration strategies.

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。

摘要：

英文摘要：

相关论文