arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09435cs.LG
收藏

公平意识在线元学习

Fairness-Aware Online Meta-learning

The University of Texas at Dallas(德克萨斯大学达拉斯分校)

Chen Zhao, Feng Chen, Bhavani Thuraisingham

摘要:

与离线工作方式相比,在线学习有两种研究范式:(1)在线元学习(OML)在一个接一个的任务被揭示的顺序设置中学习模型参数的良好先验(或学习学习)。虽然它提供了一个次线性的遗憾界限,这种技术完全忽略了公平学习的重要性,这是人类智力的一个重要标志。(2)在线公平意识学习。此设置捕获了许多关注公平性的分类问题。但它的目标是实现zero-shot泛化,而没有任何特定于任务的适应。因此,这限制了模型适应新到达数据的能力。为了克服这些问题,弥补这一差距,在本文中,我们首次提出了一种新的在线元学习算法,即FFML,这是在不公平预防的设置。FFML的关键部分是学习在线公平分类模型的原始和对偶参数的良好先验,这些参数分别与模型的准确性和公平性相关联。该问题是制定在一个双层凹凸优化的形式。理论分析给出了损失后悔和违反累积公平约束的次线性上界。我们的实验证明了FFML的多功能性,通过将其应用于三个真实世界的数据集上的分类,并在公平性和分类准确性之间的权衡上显示出比最好的先前工作有实质性的改进

英文摘要:

In contrast to offline working fashions, two research paradigms are devised for online learning: (1) Online Meta Learning (OML) learns good priors over model parameters (or learning to learn) in a sequential setting where tasks are revealed one after another. Although it provides a sub-linear regret bound, such techniques completely ignore the importance of learning with fairness which is a significant hallmark of human intelligence. (2) Online Fairness-Aware Learning. This setting captures many classification problems for which fairness is a concern. But it aims to attain zero-shot generalization without any task-specific adaptation. This therefore limits the capability of a model to adapt onto newly arrived data. To overcome such issues and bridge the gap, in this paper for the first time we proposed a novel online meta-learning algorithm, namely FFML, which is under the setting of unfairness prevention. The key part of FFML is to learn good priors of an online fair classification model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The problem is formulated in the form of a bi-level convex-concave optimization. Theoretic analysis provides sub-linear upper bounds for loss regret and for violation of cumulative fairness constraints. Our experiments demonstrate the versatility of FFML by applying it to classification on three real-world datasets and show substantial improvements over the best prior work on the tradeoff between fairness and classification 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。

↑