论文标题
部分可观测时空混沌系统的无模型预测
FairGrad: Fairness Aware Gradient Descent
论文作者
论文摘要
我们解决了分类中群体公平性的问题，目的是学习不会不公正地歧视人群亚组的模型。大多数现有方法仅限于简单的二元任务，或者涉及难以实施培训机制，从而降低了其实际适用性。在本文中，我们提出了Fairgrad，这是一种基于重新加权方案来实施公平性的方法，该计划根据是否有优势地迭代地学习特定权重。 Fairgrad易于实施，适合各种标准的公平定义，并带有最小的开销。此外，我们表明，它与各种数据集的标准基线具有竞争力，包括自然语言处理和计算机视觉中使用的数据集。 Fairgrad可作为PYPI软件包提供-https：//pypi.org/project/fairgrad
We address the problem of group fairness in classification, where the objective is to learn models that do not unjustly discriminate against subgroups of the population. Most existing approaches are limited to simple binary tasks or involve difficult to implement training mechanisms which reduces their practical applicability. In this paper, we propose FairGrad, a method to enforce fairness based on a re-weighting scheme that iteratively learns group specific weights based on whether they are advantaged or not. FairGrad is easy to implement, accommodates various standard fairness definitions, and comes with minimal overhead. Furthermore, we show that it is competitive with standard baselines over various datasets including ones used in natural language processing and computer vision. FairGrad is available as a PyPI package at - https://pypi.org/project/fairgrad
