论文标题
公平及以后的二次度量启发
Quadratic Metric Elicitation for Fairness and Beyond
论文作者
论文摘要
度量启发是最新的框架，用于启发分类性能指标，可以最能根据任务和上下文来反映隐性用户偏好。但是，可用的启发策略仅限于预测率的线性（或准线性）函数，对于包括公平性在内的许多应用程序，这实际上是限制的。本文制定了一种策略，以引起更灵活的多类指标，该指标由二次功能的速率函数定义，旨在更好地反映人类的偏好。我们展示了它在启发基于二次违规的集体 - 婚姻指标中的应用。我们的策略仅需要相对的偏好反馈，对噪声是强大的，并且达到了近乎最佳的查询复杂性。我们将此策略进一步扩展到启发多项式指标，从而扩大了用例启发的用例。
Metric elicitation is a recent framework for eliciting classification performance metrics that best reflect implicit user preferences based on the task and context. However, available elicitation strategies have been limited to linear (or quasi-linear) functions of predictive rates, which can be practically restrictive for many applications including fairness. This paper develops a strategy for eliciting more flexible multiclass metrics defined by quadratic functions of rates, designed to reflect human preferences better. We show its application in eliciting quadratic violation-based group-fair metrics. Our strategy requires only relative preference feedback, is robust to noise, and achieves near-optimal query complexity. We further extend this strategy to eliciting polynomial metrics -- thus broadening the use cases for metric elicitation.
