arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12586cs.LGcs.ITmath.IT
收藏

一个公平风险最小化的随机优化框架

A Stochastic Optimization Framework for Fair Risk Minimization

University of Southern California(南加利福尼亚大学);University of Washington(华盛顿大学);Google Research(谷歌研究院)

Andrew Lowy, Sina Baharlouei, Rakesh Pavan, Meisam Razaviyayn, Ahmad Beirami

摘要:

尽管大规模经验风险最小化(ERM)在各种机器学习任务中实现高精度方面取得了成功,但公平ERM受到公平约束与随机优化不相容的阻碍。我们考虑离散敏感属性和潜在的大模型和数据集的公平分类问题,需要随机求解器。现有的处理中公平算法要么是不切实际的,在大规模的设置,因为他们需要大量的数据在每次迭代,或者他们不能保证收敛。在本文中,我们开发了第一个随机处理中的公平算法,保证收敛。对于人口均等,均衡的赔率,公平的机会均等的概念,我们提供了我们的算法略有变化-称为费米-并证明这些变化收敛于随机优化与任何批量大小。从经验上讲,我们表明,FERMI是服从多个(非二进制)敏感属性和非二进制目标的随机解算器,即使小批量大小为1。广泛的实验表明,FERMI实现了最有利的权衡之间的公平违反和测试精度在所有测试的设置相比,国家的最先进的基线人口均等,均等的赔率,平等的机会。这些优点在小批量和具有大量敏感属性的非二进制分类中尤为显著,使FERMI成为一种实用的、可扩展的公平算法。本文中所有实验的代码都可以在https://github.com/optimization-for-data-driven-science/FERMI上找到。

英文摘要:

Despite the success of large-scale empirical risk minimization (ERM) at achieving high accuracy across a variety of machine learning tasks, fair ERM is hindered by the incompatibility of fairness constraints with stochastic optimization. We consider the problem of fair classification with discrete sensitive attributes and potentially large models and data sets, requiring stochastic solvers. Existing in-processing fairness algorithms are either impractical in the large-scale setting because they require large batches of data at each iteration or they are not guaranteed to converge. In this paper, we develop the first stochastic in-processing fairness algorithm with guaranteed convergence. For demographic parity, equalized odds, and equal opportunity notions of fairness, we provide slight variations of our algorithm--called FERMI--and prove that each of these variations converges in stochastic optimization with any batch size. Empirically, we show that FERMI is amenable to stochastic solvers with multiple (non-binary) sensitive attributes and non-binary targets, performing well even with minibatch size as small as one. Extensive experiments show that FERMI achieves the most favorable tradeoffs between fairness violation and test accuracy across all tested setups compared with state-of-the-art baselines for demographic parity, equalized odds, equal opportunity. These benefits are especially significant with small batch sizes and for non-binary classification with large number of sensitive attributes, making FERMI a practical, scalable fairness algorithm. The code for all of the experiments in this paper is available at: https://github.com/optimization-for-data-driven-science/FERMI.

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。

↑